/flipv2/20121112-100543-2.5K-ReLST-Wallace/stdout-flip-2.5K_1.txt
Plain Text | 16440 lines | 15705 code | 735 blank | 0 comment | 0 complexity | 65c053b700960c62ea6c2bac5dde26ac MD5 | raw file
1Seeding... 1 2dir: dir isL 3Python-Soar Flip environment. 4To accept commands from an external sml process, you'll need to 5type 'slave <log file> <n decisons>' at the prompt... 6sourcing 'flip_predict.soar' 7*********** 8Total: 11 productions sourced. 9 10seeding Soar with 1 ... 11 12soar> Entering slave mode: 13 - log file 'rl-slave-2.5K_1.log'.... 14 - will exit slave mode after 2500 decisions 15 waiting for commands from an externally connected sml process... 16-/|sleeping... 17\sleeping... 18-sleeping... 19/sleeping... 20|sleeping... 21\-/|\-/|\sleeping... 22-/|\-/1: O: O1 (predict-yes) 23I see 0 and I'm going to do: predict-yes 24ENV: Agent did: predict-yes for direction L in state State-A 25In State-A moving L 26ENV: (next state, see, prediction correct?) = (State-A, 0, False) 27predict error 1 28dir: dir isU 29rule alias: '*' 30 31rule alias: '*' 32 33|\-/|\-/2: O: O4 (predict-no) 34I see 0 and I'm going to do: predict-no 35ENV: Agent did: predict-no for direction U in state State-A 36In State-A moving U 37ENV: (next state, see, prediction correct?) = (State-A, 0, True) 38predict error 0 39dir: dir isU 40|\-3: O: O5 (predict-yes) 41I see 1 and I'm going to do: predict-yes 42ENV: Agent did: predict-yes for direction U in state State-A 43In State-A moving U 44ENV: (next state, see, prediction correct?) = (State-A, 0, False) 45predict error 1 46dir: dir isL 47/4: O: O7 (predict-yes) 48I see 0 and I'm going to do: predict-yes 49ENV: Agent did: predict-yes for direction L in state State-A 50In State-A moving L 51ENV: (next state, see, prediction correct?) = (State-A, 0, False) 52predict error 1 53dir: dir isR 54|\-5: O: O10 (predict-no) 55I see 0 and I'm going to do: predict-no 56ENV: Agent did: predict-no for direction R in state State-A 57In State-A moving R 58ENV: (next state, see, prediction correct?) = (State-B, 1, False) 59predict error 1 60dir: dir isR 61/|6: O: O11 (predict-yes) 62I see 0 and I'm going to do: predict-yes 63ENV: Agent did: predict-yes for direction R in state State-B 64In State-B moving R 65ENV: (next state, see, prediction correct?) = (State-B, 0, False) 66predict error 1 67dir: dir isR 68\-/|7: O: O13 (predict-yes) 69I see 0 and I'm going to do: predict-yes 70ENV: Agent did: predict-yes for direction R in state State-B 71In State-B moving R 72ENV: (next state, see, prediction correct?) = (State-B, 0, False) 73predict error 1 74dir: dir isU 75\-/|8: O: O16 (predict-no) 76I see 0 and I'm going to do: predict-no 77ENV: Agent did: predict-no for direction U in state State-B 78In State-B moving U 79ENV: (next state, see, prediction correct?) = (State-B, 0, True) 80predict error 0 81dir: dir isL 82\-9: O: O18 (predict-no) 83I see 1 and I'm going to do: predict-no 84ENV: Agent did: predict-no for direction L in state State-B 85In State-B moving L 86ENV: (next state, see, prediction correct?) = (State-A, 1, False) 87predict error 1 88dir: dir isL 89/|\10: O: O20 (predict-no) 90I see 0 and I'm going to do: predict-no 91ENV: Agent did: predict-no for direction L in state State-A 92In State-A moving L 93ENV: (next state, see, prediction correct?) = (State-A, 0, True) 94predict error 0 95dir: dir isU 96-/|11: O: O22 (predict-no) 97I see 1 and I'm going to do: predict-no 98ENV: Agent did: predict-no for direction U in state State-A 99In State-A moving U 100ENV: (next state, see, prediction correct?) = (State-A, 0, True) 101predict error 0 102dir: dir isR 103rule alias: '*' 104 105rule alias: '*' 106 107rule alias: '*' 108 109rule alias: '*' 110 111\12: O: O23 (predict-yes) 112I see 1 and I'm going to do: predict-yes 113ENV: Agent did: predict-yes for direction R in state State-A 114In State-A moving R 115ENV: (next state, see, prediction correct?) = (State-B, 1, True) 116predict error 0 117dir: dir isU 118-/|13: O: O26 (predict-no) 119I see 1 and I'm going to do: predict-no 120ENV: Agent did: predict-no for direction U in state State-B 121In State-B moving U 122ENV: (next state, see, prediction correct?) = (State-B, 0, True) 123predict error 0 124dir: dir isL 125\-14: O: O28 (predict-no) 126I see 1 and I'm going to do: predict-no 127ENV: Agent did: predict-no for direction L in state State-B 128In State-B moving L 129ENV: (next state, see, prediction correct?) = (State-A, 1, False) 130predict error 1 131dir: dir isR 132/|15: O: O30 (predict-no) 133I see 0 and I'm going to do: predict-no 134ENV: Agent did: predict-no for direction R in state State-A 135In State-A moving R 136ENV: (next state, see, prediction correct?) = (State-B, 1, False) 137predict error 1 138dir: dir isU 139\-/16: O: O32 (predict-no) 140I see 0 and I'm going to do: predict-no 141ENV: Agent did: predict-no for direction U in state State-B 142In State-B moving U 143ENV: (next state, see, prediction correct?) = (State-B, 0, True) 144predict error 0 145dir: dir isL 146|\-17: O: O33 (predict-yes) 147I see 1 and I'm going to do: predict-yes 148ENV: Agent did: predict-yes for direction L in state State-B 149In State-B moving L 150ENV: (next state, see, prediction correct?) = (State-A, 1, True) 151predict error 0 152dir: dir isU 153/|18: O: O36 (predict-no) 154I see 1 and I'm going to do: predict-no 155ENV: Agent did: predict-no for direction U in state State-A 156In State-A moving U 157ENV: (next state, see, prediction correct?) = (State-A, 0, True) 158predict error 0 159dir: dir isU 160\-/19: O: O38 (predict-no) 161I see 1 and I'm going to do: predict-no 162ENV: Agent did: predict-no for direction U in state State-A 163In State-A moving U 164ENV: (next state, see, prediction correct?) = (State-A, 0, True) 165predict error 0 166dir: dir isL 167|\-20: O: O39 (predict-yes) 168I see 1 and I'm going to do: predict-yes 169ENV: Agent did: predict-yes for direction L in state State-A 170In State-A moving L 171ENV: (next state, see, prediction correct?) = (State-A, 0, False) 172predict error 1 173dir: dir isL 174/|\21: O: O41 (predict-yes) 175I see 0 and I'm going to do: predict-yes 176ENV: Agent did: predict-yes for direction L in state State-A 177In State-A moving L 178ENV: (next state, see, prediction correct?) = (State-A, 0, False) 179predict error 1 180dir: dir isR 181-22: O: O43 (predict-yes) 182I see 0 and I'm going to do: predict-yes 183ENV: Agent did: predict-yes for direction R in state State-A 184In State-A moving R 185ENV: (next state, see, prediction correct?) = (State-B, 1, True) 186predict error 0 187dir: dir isU 188/|23: O: O46 (predict-no) 189I see 1 and I'm going to do: predict-no 190ENV: Agent did: predict-no for direction U in state State-B 191In State-B moving U 192ENV: (next state, see, prediction correct?) = (State-B, 0, True) 193predict error 0 194dir: dir isR 195\-/24: O: O47 (predict-yes) 196I see 1 and I'm going to do: predict-yes 197ENV: Agent did: predict-yes for direction R in state State-B 198In State-B moving R 199ENV: (next state, see, prediction correct?) = (State-B, 0, False) 200predict error 1 201dir: dir isL 202|\25: O: O50 (predict-no) 203I see 0 and I'm going to do: predict-no 204ENV: Agent did: predict-no for direction L in state State-B 205In State-B moving L 206ENV: (next state, see, prediction correct?) = (State-A, 1, False) 207predict error 1 208dir: dir isR 209-/|26: O: O52 (predict-no) 210I see 0 and I'm going to do: predict-no 211ENV: Agent did: predict-no for direction R in state State-A 212In State-A moving R 213ENV: (next state, see, prediction correct?) = (State-B, 1, False) 214predict error 1 215dir: dir isL 216\-27: O: O54 (predict-no) 217I see 0 and I'm going to do: predict-no 218ENV: Agent did: predict-no for direction L in state State-B 219In State-B moving L 220ENV: (next state, see, prediction correct?) = (State-A, 1, False) 221predict error 1 222dir: dir isL 223/|28: O: O56 (predict-no) 224I see 0 and I'm going to do: predict-no 225ENV: Agent did: predict-no for direction L in state State-A 226In State-A moving L 227ENV: (next state, see, prediction correct?) = (State-A, 0, True) 228predict error 0 229dir: dir isR 230\-/29: O: O57 (predict-yes) 231I see 1 and I'm going to do: predict-yes 232ENV: Agent did: predict-yes for direction R in state State-A 233In State-A moving R 234ENV: (next state, see, prediction correct?) = (State-B, 1, True) 235predict error 0 236dir: dir isR 237|\-30: O: O59 (predict-yes) 238I see 1 and I'm going to do: predict-yes 239ENV: Agent did: predict-yes for direction R in state State-B 240In State-B moving R 241ENV: (next state, see, prediction correct?) = (State-B, 0, False) 242predict error 1 243dir: dir isL 244/|\31: O: O62 (predict-no) 245I see 0 and I'm going to do: predict-no 246ENV: Agent did: predict-no for direction L in state State-B 247In State-B moving L 248ENV: (next state, see, prediction correct?) = (State-A, 1, False) 249predict error 1 250dir: dir isL 251-32: O: O64 (predict-no) 252I see 0 and I'm going to do: predict-no 253ENV: Agent did: predict-no for direction L in state State-A 254In State-A moving L 255ENV: (next state, see, prediction correct?) = (State-A, 0, True) 256predict error 0 257dir: dir isL 258/|\33: O: O66 (predict-no) 259I see 1 and I'm going to do: predict-no 260ENV: Agent did: predict-no for direction L in state State-A 261In State-A moving L 262ENV: (next state, see, prediction correct?) = (State-A, 0, True) 263predict error 0 264dir: dir isR 265-/|34: O: O67 (predict-yes) 266I see 1 and I'm going to do: predict-yes 267ENV: Agent did: predict-yes for direction R in state State-A 268In State-A moving R 269ENV: (next state, see, prediction correct?) = (State-B, 1, True) 270predict error 0 271dir: dir isL 272\-/35: O: O70 (predict-no) 273I see 1 and I'm going to do: predict-no 274ENV: Agent did: predict-no for direction L in state State-B 275In State-B moving L 276ENV: (next state, see, prediction correct?) = (State-A, 1, False) 277predict error 1 278dir: dir isL 279|\-/36: O: O72 (predict-no) 280I see 0 and I'm going to do: predict-no 281ENV: Agent did: predict-no for direction L in state State-A 282In State-A moving L 283ENV: (next state, see, prediction correct?) = (State-A, 0, True) 284predict error 0 285dir: dir isU 286|\-37: O: O74 (predict-no) 287I see 1 and I'm going to do: predict-no 288ENV: Agent did: predict-no for direction U in state State-A 289In State-A moving U 290ENV: (next state, see, prediction correct?) = (State-A, 0, True) 291predict error 0 292dir: dir isR 293/|\38: O: O76 (predict-no) 294I see 1 and I'm going to do: predict-no 295ENV: Agent did: predict-no for direction R in state State-A 296In State-A moving R 297ENV: (next state, see, prediction correct?) = (State-B, 1, False) 298predict error 1 299dir: dir isR 300-/|39: O: O77 (predict-yes) 301I see 0 and I'm going to do: predict-yes 302ENV: Agent did: predict-yes for direction R in state State-B 303In State-B moving R 304ENV: (next state, see, prediction correct?) = (State-B, 0, False) 305predict error 1 306dir: dir isL 307\-/40: O: O80 (predict-no) 308I see 0 and I'm going to do: predict-no 309ENV: Agent did: predict-no for direction L in state State-B 310In State-B moving L 311ENV: (next state, see, prediction correct?) = (State-A, 1, False) 312predict error 1 313dir: dir isU 314|\-41: O: O82 (predict-no) 315I see 0 and I'm going to do: predict-no 316ENV: Agent did: predict-no for direction U in state State-A 317In State-A moving U 318ENV: (next state, see, prediction correct?) = (State-A, 0, True) 319predict error 0 320dir: dir isU 321/42: O: O84 (predict-no) 322I see 1 and I'm going to do: predict-no 323ENV: Agent did: predict-no for direction U in state State-A 324In State-A moving U 325ENV: (next state, see, prediction correct?) = (State-A, 0, True) 326predict error 0 327dir: dir isL 328|\43: O: O85 (predict-yes) 329I see 1 and I'm going to do: predict-yes 330ENV: Agent did: predict-yes for direction L in state State-A 331In State-A moving L 332ENV: (next state, see, prediction correct?) = (State-A, 0, False) 333predict error 1 334dir: dir isL 335-/|44: O: O88 (predict-no) 336I see 0 and I'm going to do: predict-no 337ENV: Agent did: predict-no for direction L in state State-A 338In State-A moving L 339ENV: (next state, see, prediction correct?) = (State-A, 0, True) 340predict error 0 341dir: dir isU 342\-/45: O: O90 (predict-no) 343I see 1 and I'm going to do: predict-no 344ENV: Agent did: predict-no for direction U in state State-A 345In State-A moving U 346ENV: (next state, see, prediction correct?) = (State-A, 0, True) 347predict error 0 348dir: dir isU 349|\-46: O: O92 (predict-no) 350I see 1 and I'm going to do: predict-no 351ENV: Agent did: predict-no for direction U in state State-A 352In State-A moving U 353ENV: (next state, see, prediction correct?) = (State-A, 0, True) 354predict error 0 355dir: dir isU 356/|\47: O: O94 (predict-no) 357I see 1 and I'm going to do: predict-no 358ENV: Agent did: predict-no for direction U in state State-A 359In State-A moving U 360ENV: (next state, see, prediction correct?) = (State-A, 0, True) 361predict error 0 362dir: dir isR 363-/48: O: O95 (predict-yes) 364I see 1 and I'm going to do: predict-yes 365ENV: Agent did: predict-yes for direction R in state State-A 366In State-A moving R 367ENV: (next state, see, prediction correct?) = (State-B, 1, True) 368predict error 0 369dir: dir isU 370|\-49: O: O98 (predict-no) 371I see 1 and I'm going to do: predict-no 372ENV: Agent did: predict-no for direction U in state State-B 373In State-B moving U 374ENV: (next state, see, prediction correct?) = (State-B, 0, True) 375predict error 0 376dir: dir isU 377/|\50: O: O100 (predict-no) 378I see 1 and I'm going to do: predict-no 379ENV: Agent did: predict-no for direction U in state State-B 380In State-B moving U 381ENV: (next state, see, prediction correct?) = (State-B, 0, True) 382predict error 0 383dir: dir isL 384-/|\-/|sleeping... 385\sleeping... 386-sleeping... 387/sleeping... 388|sleeping... 389\sleeping... 390-sleeping... 391/sleeping... 392|sleeping... 393\sleeping... 394-sleeping... 395/sleeping... 396|sleeping... 397\sleeping... 398-sleeping... 399/sleeping... 400|sleeping... 401\sleeping... 402-sleeping... 403/sleeping... 404|sleeping... 405\sleeping... 406-sleeping... 407/sleeping... 408|sleeping... 409\sleeping... 410-sleeping... 411/sleeping... 412|sleeping... 413\sleeping... 414-sleeping... 415/sleeping... 416|sleeping... 417\sleeping... 418-sleeping... 419/sleeping... 420|sleeping... 421\51: O: O102 (predict-no) 422I see 1 and I'm going to do: predict-no 423ENV: Agent did: predict-no for direction L in state State-B 424In State-B moving L 425ENV: (next state, see, prediction correct?) = (State-A, 1, False) 426predict error 1 427dir: dir isR 428rule alias: '*' 429 430rule alias: '*' 431 432-52: O: O104 (predict-no) 433I see 0 and I'm going to do: predict-no 434ENV: Agent did: predict-no for direction R in state State-A 435In State-A moving R 436ENV: (next state, see, prediction correct?) = (State-B, 1, False) 437predict error 1 438dir: dir isU 439/|53: O: O106 (predict-no) 440I see 0 and I'm going to do: predict-no 441ENV: Agent did: predict-no for direction U in state State-B 442In State-B moving U 443ENV: (next state, see, prediction correct?) = (State-B, 0, True) 444predict error 0 445dir: dir isU 446\-/54: O: O108 (predict-no) 447I see 1 and I'm going to do: predict-no 448ENV: Agent did: predict-no for direction U in state State-B 449In State-B moving U 450ENV: (next state, see, prediction correct?) = (State-B, 0, True) 451predict error 0 452dir: dir isR 453|\55: O: O109 (predict-yes) 454I see 1 and I'm going to do: predict-yes 455ENV: Agent did: predict-yes for direction R in state State-B 456In State-B moving R 457ENV: (next state, see, prediction correct?) = (State-B, 0, False) 458predict error 1 459dir: dir isR 460-/|56: O: O111 (predict-yes) 461I see 0 and I'm going to do: predict-yes 462ENV: Agent did: predict-yes for direction R in state State-B 463In State-B moving R 464ENV: (next state, see, prediction correct?) = (State-B, 0, False) 465predict error 1 466dir: dir isL 467\-/57: O: O114 (predict-no) 468I see 0 and I'm going to do: predict-no 469ENV: Agent did: predict-no for direction L in state State-B 470In State-B moving L 471ENV: (next state, see, prediction correct?) = (State-A, 1, False) 472predict error 1 473dir: dir isL 474|\58: O: O116 (predict-no) 475I see 0 and I'm going to do: predict-no 476ENV: Agent did: predict-no for direction L in state State-A 477In State-A moving L 478ENV: (next state, see, prediction correct?) = (State-A, 0, True) 479predict error 0 480dir: dir isU 481-/|59: O: O118 (predict-no) 482I see 1 and I'm going to do: predict-no 483ENV: Agent did: predict-no for direction U in state State-A 484In State-A moving U 485ENV: (next state, see, prediction correct?) = (State-A, 0, True) 486predict error 0 487dir: dir isR 488\-60: O: O119 (predict-yes) 489I see 1 and I'm going to do: predict-yes 490ENV: Agent did: predict-yes for direction R in state State-A 491In State-A moving R 492ENV: (next state, see, prediction correct?) = (State-B, 1, True) 493predict error 0 494dir: dir isL 495/61: O: O122 (predict-no) 496I see 1 and I'm going to do: predict-no 497ENV: Agent did: predict-no for direction L in state State-B 498In State-B moving L 499ENV: (next state, see, prediction correct?) = (State-A, 1, False) 500predict error 1 501dir: dir isR 502rule alias: '*' 503 504rule alias: '*' 505 506rule alias: '*' 507 508rule alias: '*' 509 510rule alias: '*' 511 512rule alias: '*' 513 514rule alias: '*' 515 516rule alias: '*' 517 518rule alias: '*' 519 520rule alias: '*' 521 522|62: O: O123 (predict-yes) 523I see 0 and I'm going to do: predict-yes 524ENV: Agent did: predict-yes for direction R in state State-A 525In State-A moving R 526ENV: (next state, see, prediction correct?) = (State-B, 1, True) 527predict error 0 528dir: dir isU 529\-/63: O: O126 (predict-no) 530I see 1 and I'm going to do: predict-no 531ENV: Agent did: predict-no for direction U in state State-B 532In State-B moving U 533ENV: (next state, see, prediction correct?) = (State-B, 0, True) 534predict error 0 535dir: dir isU 536|\-64: O: O128 (predict-no) 537I see 1 and I'm going to do: predict-no 538ENV: Agent did: predict-no for direction U in state State-B 539In State-B moving U 540ENV: (next state, see, prediction correct?) = (State-B, 0, True) 541predict error 0 542dir: dir isR 543/|65: O: O129 (predict-yes) 544I see 1 and I'm going to do: predict-yes 545ENV: Agent did: predict-yes for direction R in state State-B 546In State-B moving R 547ENV: (next state, see, prediction correct?) = (State-B, 0, False) 548predict error 1 549dir: dir isR 550\-/66: O: O132 (predict-no) 551I see 0 and I'm going to do: predict-no 552ENV: Agent did: predict-no for direction R in state State-B 553In State-B moving R 554ENV: (next state, see, prediction correct?) = (State-B, 0, True) 555predict error 0 556dir: dir isR 557|\-67: O: O134 (predict-no) 558I see 1 and I'm going to do: predict-no 559ENV: Agent did: predict-no for direction R in state State-B 560In State-B moving R 561ENV: (next state, see, prediction correct?) = (State-B, 0, True) 562predict error 0 563dir: dir isU 564/|68: O: O136 (predict-no) 565I see 1 and I'm going to do: predict-no 566ENV: Agent did: predict-no for direction U in state State-B 567In State-B moving U 568ENV: (next state, see, prediction correct?) = (State-B, 0, True) 569predict error 0 570dir: dir isR 571\-/69: O: O137 (predict-yes) 572I see 1 and I'm going to do: predict-yes 573ENV: Agent did: predict-yes for direction R in state State-B 574In State-B moving R 575ENV: (next state, see, prediction correct?) = (State-B, 0, False) 576predict error 1 577dir: dir isR 578|\-70: O: O139 (predict-yes) 579I see 0 and I'm going to do: predict-yes 580ENV: Agent did: predict-yes for direction R in state State-B 581In State-B moving R 582ENV: (next state, see, prediction correct?) = (State-B, 0, False) 583predict error 1 584dir: dir isR 585/71: O: O142 (predict-no) 586I see 0 and I'm going to do: predict-no 587ENV: Agent did: predict-no for direction R in state State-B 588In State-B moving R 589ENV: (next state, see, prediction correct?) = (State-B, 0, True) 590predict error 0 591dir: dir isL 592rule alias: '*' 593 594|72: O: O144 (predict-no) 595I see 1 and I'm going to do: predict-no 596ENV: Agent did: predict-no for direction L in state State-B 597In State-B moving L 598ENV: (next state, see, prediction correct?) = (State-A, 1, False) 599predict error 1 600dir: dir isL 601\-/73: O: O146 (predict-no) 602I see 0 and I'm going to do: predict-no 603ENV: Agent did: predict-no for direction L in state State-A 604In State-A moving L 605ENV: (next state, see, prediction correct?) = (State-A, 0, True) 606predict error 0 607dir: dir isU 608|\74: O: O148 (predict-no) 609I see 1 and I'm going to do: predict-no 610ENV: Agent did: predict-no for direction U in state State-A 611In State-A moving U 612ENV: (next state, see, prediction correct?) = (State-A, 0, True) 613predict error 0 614dir: dir isU 615-/75: O: O149 (predict-yes) 616I see 1 and I'm going to do: predict-yes 617ENV: Agent did: predict-yes for direction U in state State-A 618In State-A moving U 619ENV: (next state, see, prediction correct?) = (State-A, 0, False) 620predict error 1 621dir: dir isR 622|\76: O: O152 (predict-no) 623I see 0 and I'm going to do: predict-no 624ENV: Agent did: predict-no for direction R in state State-A 625In State-A moving R 626ENV: (next state, see, prediction correct?) = (State-B, 1, False) 627predict error 1 628dir: dir isR 629-/|77: O: O153 (predict-yes) 630I see 0 and I'm going to do: predict-yes 631ENV: Agent did: predict-yes for direction R in state State-B 632In State-B moving R 633ENV: (next state, see, prediction correct?) = (State-B, 0, False) 634predict error 1 635dir: dir isL 636\-/78: O: O156 (predict-no) 637I see 0 and I'm going to do: predict-no 638ENV: Agent did: predict-no for direction L in state State-B 639In State-B moving L 640ENV: (next state, see, prediction correct?) = (State-A, 1, False) 641predict error 1 642dir: dir isR 643|\-79: O: O158 (predict-no) 644I see 0 and I'm going to do: predict-no 645ENV: Agent did: predict-no for direction R in state State-A 646In State-A moving R 647ENV: (next state, see, prediction correct?) = (State-B, 1, False) 648predict error 1 649dir: dir isU 650/|\80: O: O160 (predict-no) 651I see 0 and I'm going to do: predict-no 652ENV: Agent did: predict-no for direction U in state State-B 653In State-B moving U 654ENV: (next state, see, prediction correct?) = (State-B, 0, True) 655predict error 0 656dir: dir isU 657-/81: O: O162 (predict-no) 658I see 1 and I'm going to do: predict-no 659ENV: Agent did: predict-no for direction U in state State-B 660In State-B moving U 661ENV: (next state, see, prediction correct?) = (State-B, 0, True) 662predict error 0 663dir: dir isR 664rule alias: '*' 665 666|82: O: O163 (predict-yes) 667I see 1 and I'm going to do: predict-yes 668ENV: Agent did: predict-yes for direction R in state State-B 669In State-B moving R 670ENV: (next state, see, prediction correct?) = (State-B, 0, False) 671predict error 1 672dir: dir isU 673\-/|83: O: O166 (predict-no) 674I see 0 and I'm going to do: predict-no 675ENV: Agent did: predict-no for direction U in state State-B 676In State-B moving U 677ENV: (next state, see, prediction correct?) = (State-B, 0, True) 678predict error 0 679dir: dir isL 680\-/84: O: O168 (predict-no) 681I see 1 and I'm going to do: predict-no 682ENV: Agent did: predict-no for direction L in state State-B 683In State-B moving L 684ENV: (next state, see, prediction correct?) = (State-A, 1, False) 685predict error 1 686dir: dir isR 687|\-85: O: O170 (predict-no) 688I see 0 and I'm going to do: predict-no 689ENV: Agent did: predict-no for direction R in state State-A 690In State-A moving R 691ENV: (next state, see, prediction correct?) = (State-B, 1, False) 692predict error 1 693dir: dir isU 694/|\86: O: O172 (predict-no) 695I see 0 and I'm going to do: predict-no 696ENV: Agent did: predict-no for direction U in state State-B 697In State-B moving U 698ENV: (next state, see, prediction correct?) = (State-B, 0, True) 699predict error 0 700dir: dir isR 701-/|87: O: O174 (predict-no) 702I see 1 and I'm going to do: predict-no 703ENV: Agent did: predict-no for direction R in state State-B 704In State-B moving R 705ENV: (next state, see, prediction correct?) = (State-B, 0, True) 706predict error 0 707dir: dir isR 708\-/88: O: O176 (predict-no) 709I see 1 and I'm going to do: predict-no 710ENV: Agent did: predict-no for direction R in state State-B 711In State-B moving R 712ENV: (next state, see, prediction correct?) = (State-B, 0, True) 713predict error 0 714dir: dir isL 715|\-89: O: O177 (predict-yes) 716I see 1 and I'm going to do: predict-yes 717ENV: Agent did: predict-yes for direction L in state State-B 718In State-B moving L 719ENV: (next state, see, prediction correct?) = (State-A, 1, True) 720predict error 0 721dir: dir isR 722/|\90: O: O179 (predict-yes) 723I see 1 and I'm going to do: predict-yes 724ENV: Agent did: predict-yes for direction R in state State-A 725In State-A moving R 726ENV: (next state, see, prediction correct?) = (State-B, 1, True) 727predict error 0 728dir: dir isU 729-/91: O: O182 (predict-no) 730I see 1 and I'm going to do: predict-no 731ENV: Agent did: predict-no for direction U in state State-B 732In State-B moving U 733ENV: (next state, see, prediction correct?) = (State-B, 0, True) 734predict error 0 735dir: dir isL 736rule alias: '*' 737 738rule alias: '*' 739 740rule alias: '*' 741 742|92: O: O184 (predict-no) 743I see 1 and I'm going to do: predict-no 744ENV: Agent did: predict-no for direction L in state State-B 745In State-B moving L 746ENV: (next state, see, prediction correct?) = (State-A, 1, False) 747predict error 1 748dir: dir isU 749\-93: O: O186 (predict-no) 750I see 0 and I'm going to do: predict-no 751ENV: Agent did: predict-no for direction U in state State-A 752In State-A moving U 753ENV: (next state, see, prediction correct?) = (State-A, 0, True) 754predict error 0 755dir: dir isU 756/|94: O: O188 (predict-no) 757I see 1 and I'm going to do: predict-no 758ENV: Agent did: predict-no for direction U in state State-A 759In State-A moving U 760ENV: (next state, see, prediction correct?) = (State-A, 0, True) 761predict error 0 762dir: dir isU 763\-/95: O: O190 (predict-no) 764I see 1 and I'm going to do: predict-no 765ENV: Agent did: predict-no for direction U in state State-A 766In State-A moving U 767ENV: (next state, see, prediction correct?) = (State-A, 0, True) 768predict error 0 769dir: dir isU 770|\-96: O: O191 (predict-yes) 771I see 1 and I'm going to do: predict-yes 772ENV: Agent did: predict-yes for direction U in state State-A 773In State-A moving U 774ENV: (next state, see, prediction correct?) = (State-A, 0, False) 775predict error 1 776dir: dir isU 777/|\-97: O: O194 (predict-no) 778I see 0 and I'm going to do: predict-no 779ENV: Agent did: predict-no for direction U in state State-A 780In State-A moving U 781ENV: (next state, see, prediction correct?) = (State-A, 0, True) 782predict error 0 783dir: dir isR 784/|\98: O: O196 (predict-no) 785I see 1 and I'm going to do: predict-no 786ENV: Agent did: predict-no for direction R in state State-A 787In State-A moving R 788ENV: (next state, see, prediction correct?) = (State-B, 1, False) 789predict error 1 790dir: dir isR 791-/99: O: O198 (predict-no) 792I see 0 and I'm going to do: predict-no 793ENV: Agent did: predict-no for direction R in state State-B 794In State-B moving R 795ENV: (next state, see, prediction correct?) = (State-B, 0, True) 796predict error 0 797dir: dir isR 798|\-100: O: O200 (predict-no) 799I see 1 and I'm going to do: predict-no 800ENV: Agent did: predict-no for direction R in state State-B 801In State-B moving R 802ENV: (next state, see, prediction correct?) = (State-B, 0, True) 803predict error 0 804dir: dir isL 805/|\101: O: O201 (predict-yes) 806I see 1 and I'm going to do: predict-yes 807ENV: Agent did: predict-yes for direction L in state State-B 808In State-B moving L 809ENV: (next state, see, prediction correct?) = (State-A, 1, True) 810predict error 0 811dir: dir isU 812rule alias: '*' 813 814rule alias: '*' 815 816-/|\-/|\-/|\-/|\-/|\-/|\-/|\-sleeping... 817/sleeping... 818|sleeping... 819\sleeping... 820-sleeping... 821/sleeping... 822|sleeping... 823\sleeping... 824-sleeping... 825/sleeping... 826|sleeping... 827\sleeping... 828-sleeping... 829/sleeping... 830|sleeping... 831\sleeping... 832-sleeping... 833/sleeping... 834|102: O: O203 (predict-yes) 835I see 1 and I'm going to do: predict-yes 836ENV: Agent did: predict-yes for direction U in state State-A 837In State-A moving U 838ENV: (next state, see, prediction correct?) = (State-A, 0, False) 839predict error 1 840dir: dir isR 841\-/|103: O: O206 (predict-no) 842I see 0 and I'm going to do: predict-no 843ENV: Agent did: predict-no for direction R in state State-A 844In State-A moving R 845ENV: (next state, see, prediction correct?) = (State-B, 1, False) 846predict error 1 847dir: dir isL 848\-/104: O: O207 (predict-yes) 849I see 0 and I'm going to do: predict-yes 850ENV: Agent did: predict-yes for direction L in state State-B 851In State-B moving L 852ENV: (next state, see, prediction correct?) = (State-A, 1, True) 853predict error 0 854dir: dir isR 855|\105: O: O210 (predict-no) 856I see 1 and I'm going to do: predict-no 857ENV: Agent did: predict-no for direction R in state State-A 858In State-A moving R 859ENV: (next state, see, prediction correct?) = (State-B, 1, False) 860predict error 1 861dir: dir isR 862-/106: O: O211 (predict-yes) 863I see 0 and I'm going to do: predict-yes 864ENV: Agent did: predict-yes for direction R in state State-B 865In State-B moving R 866ENV: (next state, see, prediction correct?) = (State-B, 0, False) 867predict error 1 868dir: dir isR 869|\-107: O: O213 (predict-yes) 870I see 0 and I'm going to do: predict-yes 871ENV: Agent did: predict-yes for direction R in state State-B 872In State-B moving R 873ENV: (next state, see, prediction correct?) = (State-B, 0, False) 874predict error 1 875dir: dir isR 876/|\-sleeping... 877/108: O: O216 (predict-no) 878I see 0 and I'm going to do: predict-no 879ENV: Agent did: predict-no for direction R in state State-B 880In State-B moving R 881ENV: (next state, see, prediction correct?) = (State-B, 0, True) 882predict error 0 883dir: dir isR 884|\109: O: O218 (predict-no) 885I see 1 and I'm going to do: predict-no 886ENV: Agent did: predict-no for direction R in state State-B 887In State-B moving R 888ENV: (next state, see, prediction correct?) = (State-B, 0, True) 889predict error 0 890dir: dir isR 891-110: O: O220 (predict-no) 892I see 1 and I'm going to do: predict-no 893ENV: Agent did: predict-no for direction R in state State-B 894In State-B moving R 895ENV: (next state, see, prediction correct?) = (State-B, 0, True) 896predict error 0 897dir: dir isR 898/|\111: O: O222 (predict-no) 899I see 1 and I'm going to do: predict-no 900ENV: Agent did: predict-no for direction R in state State-B 901In State-B moving R 902ENV: (next state, see, prediction correct?) = (State-B, 0, True) 903predict error 0 904dir: dir isR 905rule alias: '*' 906 907rule alias: '*' 908 909rule alias: '*' 910 911rule alias: '*' 912 913rule alias: '*' 914 915rule alias: '*' 916 917rule alias: '*' 918 919rule alias: '*' 920 921-112: O: O223 (predict-yes) 922I see 1 and I'm going to do: predict-yes 923ENV: Agent did: predict-yes for direction R in state State-B 924In State-B moving R 925ENV: (next state, see, prediction correct?) = (State-B, 0, False) 926predict error 1 927dir: dir isL 928/|\113: O: O225 (predict-yes) 929I see 0 and I'm going to do: predict-yes 930ENV: Agent did: predict-yes for direction L in state State-B 931In State-B moving L 932ENV: (next state, see, prediction correct?) = (State-A, 1, True) 933predict error 0 934dir: dir isL 935-/|114: O: O227 (predict-yes) 936I see 1 and I'm going to do: predict-yes 937ENV: Agent did: predict-yes for direction L in state State-A 938In State-A moving L 939ENV: (next state, see, prediction correct?) = (State-A, 0, False) 940predict error 1 941dir: dir isL 942\-/115: O: O229 (predict-yes) 943I see 0 and I'm going to do: predict-yes 944ENV: Agent did: predict-yes for direction L in state State-A 945In State-A moving L 946ENV: (next state, see, prediction correct?) = (State-A, 0, False) 947predict error 1 948dir: dir isR 949|\-/116: O: O232 (predict-no) 950I see 0 and I'm going to do: predict-no 951ENV: Agent did: predict-no for direction R in state State-A 952In State-A moving R 953ENV: (next state, see, prediction correct?) = (State-B, 1, False) 954predict error 1 955dir: dir isU 956|\-117: O: O234 (predict-no) 957I see 0 and I'm going to do: predict-no 958ENV: Agent did: predict-no for direction U in state State-B 959In State-B moving U 960ENV: (next state, see, prediction correct?) = (State-B, 0, True) 961predict error 0 962dir: dir isU 963/|118: O: O236 (predict-no) 964I see 1 and I'm going to do: predict-no 965ENV: Agent did: predict-no for direction U in state State-B 966In State-B moving U 967ENV: (next state, see, prediction correct?) = (State-B, 0, True) 968predict error 0 969dir: dir isU 970\-/119: O: O238 (predict-no) 971I see 1 and I'm going to do: predict-no 972ENV: Agent did: predict-no for direction U in state State-B 973In State-B moving U 974ENV: (next state, see, prediction correct?) = (State-B, 0, True) 975predict error 0 976dir: dir isU 977|\-120: O: O239 (predict-yes) 978I see 1 and I'm going to do: predict-yes 979ENV: Agent did: predict-yes for direction U in state State-B 980In State-B moving U 981ENV: (next state, see, prediction correct?) = (State-B, 0, False) 982predict error 1 983dir: dir isL 984/|\121: O: O241 (predict-yes) 985I see 0 and I'm going to do: predict-yes 986ENV: Agent did: predict-yes for direction L in state State-B 987In State-B moving L 988ENV: (next state, see, prediction correct?) = (State-A, 1, True) 989predict error 0 990dir: dir isU 991rule alias: '*' 992 993rule alias: '*' 994 995rule alias: '*' 996 997rule alias: '*' 998 999rule alias: '*' 1000 1001rule alias: '*' 1002 1003rule alias: '*' 1004 1005rule alias: '*' 1006 1007-122: O: O244 (predict-no) 1008I see 1 and I'm going to do: predict-no 1009ENV: Agent did: predict-no for direction U in state State-A 1010In State-A moving U 1011ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1012predict error 0 1013dir: dir isU 1014/|123: O: O246 (predict-no) 1015I see 1 and I'm going to do: predict-no 1016ENV: Agent did: predict-no for direction U in state State-A 1017In State-A moving U 1018ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1019predict error 0 1020dir: dir isL 1021\-124: O: O247 (predict-yes) 1022I see 1 and I'm going to do: predict-yes 1023ENV: Agent did: predict-yes for direction L in state State-A 1024In State-A moving L 1025ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1026predict error 1 1027dir: dir isL 1028/|\125: O: O249 (predict-yes) 1029I see 0 and I'm going to do: predict-yes 1030ENV: Agent did: predict-yes for direction L in state State-A 1031In State-A moving L 1032ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1033predict error 1 1034dir: dir isL 1035-/126: O: O251 (predict-yes) 1036I see 0 and I'm going to do: predict-yes 1037ENV: Agent did: predict-yes for direction L in state State-A 1038In State-A moving L 1039ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1040predict error 1 1041dir: dir isU 1042|\-127: O: O254 (predict-no) 1043I see 0 and I'm going to do: predict-no 1044ENV: Agent did: predict-no for direction U in state State-A 1045In State-A moving U 1046ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1047predict error 0 1048dir: dir isL 1049/|128: O: O255 (predict-yes) 1050I see 1 and I'm going to do: predict-yes 1051ENV: Agent did: predict-yes for direction L in state State-A 1052In State-A moving L 1053ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1054predict error 1 1055dir: dir isL 1056\-/129: O: O257 (predict-yes) 1057I see 0 and I'm going to do: predict-yes 1058ENV: Agent did: predict-yes for direction L in state State-A 1059In State-A moving L 1060ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1061predict error 1 1062dir: dir isR 1063|\-130: O: O260 (predict-no) 1064I see 0 and I'm going to do: predict-no 1065ENV: Agent did: predict-no for direction R in state State-A 1066In State-A moving R 1067ENV: (next state, see, prediction correct?) = (State-B, 1, False) 1068predict error 1 1069dir: dir isR 1070/|\131: O: O262 (predict-no) 1071I see 0 and I'm going to do: predict-no 1072ENV: Agent did: predict-no for direction R in state State-B 1073In State-B moving R 1074ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1075predict error 0 1076dir: dir isL 1077-132: O: O263 (predict-yes) 1078I see 1 and I'm going to do: predict-yes 1079ENV: Agent did: predict-yes for direction L in state State-B 1080In State-B moving L 1081ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1082predict error 0 1083dir: dir isL 1084/|133: O: O265 (predict-yes) 1085I see 1 and I'm going to do: predict-yes 1086ENV: Agent did: predict-yes for direction L in state State-A 1087In State-A moving L 1088ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1089predict error 1 1090dir: dir isR 1091\-134: O: O268 (predict-no) 1092I see 0 and I'm going to do: predict-no 1093ENV: Agent did: predict-no for direction R in state State-A 1094In State-A moving R 1095ENV: (next state, see, prediction correct?) = (State-B, 1, False) 1096predict error 1 1097dir: dir isL 1098/|135: O: O270 (predict-no) 1099I see 0 and I'm going to do: predict-no 1100ENV: Agent did: predict-no for direction L in state State-B 1101In State-B moving L 1102ENV: (next state, see, prediction correct?) = (State-A, 1, False) 1103predict error 1 1104dir: dir isL 1105\-/136: O: O271 (predict-yes) 1106I see 0 and I'm going to do: predict-yes 1107ENV: Agent did: predict-yes for direction L in state State-A 1108In State-A moving L 1109ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1110predict error 1 1111dir: dir isU 1112|137: O: O274 (predict-no) 1113I see 0 and I'm going to do: predict-no 1114ENV: Agent did: predict-no for direction U in state State-A 1115In State-A moving U 1116ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1117predict error 0 1118dir: dir isR 1119\-/138: O: O276 (predict-no) 1120I see 1 and I'm going to do: predict-no 1121ENV: Agent did: predict-no for direction R in state State-A 1122In State-A moving R 1123ENV: (next state, see, prediction correct?) = (State-B, 1, False) 1124predict error 1 1125dir: dir isL 1126|\-139: O: O277 (predict-yes) 1127I see 0 and I'm going to do: predict-yes 1128ENV: Agent did: predict-yes for direction L in state State-B 1129In State-B moving L 1130ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1131predict error 0 1132dir: dir isR 1133/|140: O: O279 (predict-yes) 1134I see 1 and I'm going to do: predict-yes 1135ENV: Agent did: predict-yes for direction R in state State-A 1136In State-A moving R 1137ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1138predict error 0 1139dir: dir isL 1140\-141: O: O282 (predict-no) 1141I see 1 and I'm going to do: predict-no 1142ENV: Agent did: predict-no for direction L in state State-B 1143In State-B moving L 1144ENV: (next state, see, prediction correct?) = (State-A, 1, False) 1145predict error 1 1146dir: dir isR 1147/142: O: O283 (predict-yes) 1148I see 0 and I'm going to do: predict-yes 1149ENV: Agent did: predict-yes for direction R in state State-A 1150In State-A moving R 1151ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1152predict error 0 1153dir: dir isR 1154|\-143: O: O286 (predict-no) 1155I see 1 and I'm going to do: predict-no 1156ENV: Agent did: predict-no for direction R in state State-B 1157In State-B moving R 1158ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1159predict error 0 1160dir: dir isL 1161/|144: O: O287 (predict-yes) 1162I see 1 and I'm going to do: predict-yes 1163ENV: Agent did: predict-yes for direction L in state State-B 1164In State-B moving L 1165ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1166predict error 0 1167dir: dir isL 1168\-/145: O: O289 (predict-yes) 1169I see 1 and I'm going to do: predict-yes 1170ENV: Agent did: predict-yes for direction L in state State-A 1171In State-A moving L 1172ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1173predict error 1 1174dir: dir isU 1175|\-146: O: O292 (predict-no) 1176I see 0 and I'm going to do: predict-no 1177ENV: Agent did: predict-no for direction U in state State-A 1178In State-A moving U 1179ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1180predict error 0 1181dir: dir isR 1182/|\147: O: O294 (predict-no) 1183I see 1 and I'm going to do: predict-no 1184ENV: Agent did: predict-no for direction R in state State-A 1185In State-A moving R 1186ENV: (next state, see, prediction correct?) = (State-B, 1, False) 1187predict error 1 1188dir: dir isL 1189-148: O: O295 (predict-yes) 1190I see 0 and I'm going to do: predict-yes 1191ENV: Agent did: predict-yes for direction L in state State-B 1192In State-B moving L 1193ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1194predict error 0 1195dir: dir isR 1196/|\149: O: O297 (predict-yes) 1197I see 1 and I'm going to do: predict-yes 1198ENV: Agent did: predict-yes for direction R in state State-A 1199In State-A moving R 1200ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1201predict error 0 1202dir: dir isU 1203-/|150: O: O300 (predict-no) 1204I see 1 and I'm going to do: predict-no 1205ENV: Agent did: predict-no for direction U in state State-B 1206In State-B moving U 1207ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1208predict error 0 1209dir: dir isL 1210\-/151: O: O301 (predict-yes) 1211I see 1 and I'm going to do: predict-yes 1212ENV: Agent did: predict-yes for direction L in state State-B 1213In State-B moving L 1214ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1215predict error 0 1216dir: dir isL 1217|152: O: O303 (predict-yes) 1218I see 1 and I'm going to do: predict-yes 1219ENV: Agent did: predict-yes for direction L in state State-A 1220In State-A moving L 1221ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1222predict error 1 1223dir: dir isL 1224\-153: O: O305 (predict-yes) 1225I see 0 and I'm going to do: predict-yes 1226ENV: Agent did: predict-yes for direction L in state State-A 1227In State-A moving L 1228ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1229predict error 1 1230dir: dir isU 1231/|\154: O: O308 (predict-no) 1232I see 0 and I'm going to do: predict-no 1233ENV: Agent did: predict-no for direction U in state State-A 1234In State-A moving U 1235ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1236predict error 0 1237dir: dir isL 1238-/|155: O: O309 (predict-yes) 1239I see 1 and I'm going to do: predict-yes 1240ENV: Agent did: predict-yes for direction L in state State-A 1241In State-A moving L 1242ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1243predict error 1 1244dir: dir isU 1245\-156: O: O312 (predict-no) 1246I see 0 and I'm going to do: predict-no 1247ENV: Agent did: predict-no for direction U in state State-A 1248In State-A moving U 1249ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1250predict error 0 1251dir: dir isU 1252/|157: O: O313 (predict-yes) 1253I see 1 and I'm going to do: predict-yes 1254ENV: Agent did: predict-yes for direction U in state State-A 1255In State-A moving U 1256ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1257predict error 1 1258dir: dir isR 1259\-158: O: O315 (predict-yes) 1260I see 0 and I'm going to do: predict-yes 1261ENV: Agent did: predict-yes for direction R in state State-A 1262In State-A moving R 1263ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1264predict error 0 1265dir: dir isL 1266/159: O: O317 (predict-yes) 1267I see 1 and I'm going to do: predict-yes 1268ENV: Agent did: predict-yes for direction L in state State-B 1269In State-B moving L 1270ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1271predict error 0 1272dir: dir isU 1273|\-160: O: O320 (predict-no) 1274I see 1 and I'm going to do: predict-no 1275ENV: Agent did: predict-no for direction U in state State-A 1276In State-A moving U 1277ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1278predict error 0 1279dir: dir isU 1280/|161: O: O322 (predict-no) 1281I see 1 and I'm going to do: predict-no 1282ENV: Agent did: predict-no for direction U in state State-A 1283In State-A moving U 1284ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1285predict error 0 1286dir: dir isR 1287\162: O: O323 (predict-yes) 1288I see 1 and I'm going to do: predict-yes 1289ENV: Agent did: predict-yes for direction R in state State-A 1290In State-A moving R 1291ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1292predict error 0 1293dir: dir isL 1294-/163: O: O325 (predict-yes) 1295I see 1 and I'm going to do: predict-yes 1296ENV: Agent did: predict-yes for direction L in state State-B 1297In State-B moving L 1298ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1299predict error 0 1300dir: dir isR 1301|\-164: O: O327 (predict-yes) 1302I see 1 and I'm going to do: predict-yes 1303ENV: Agent did: predict-yes for direction R in state State-A 1304In State-A moving R 1305ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1306predict error 0 1307dir: dir isR 1308/|\165: O: O329 (predict-yes) 1309I see 1 and I'm going to do: predict-yes 1310ENV: Agent did: predict-yes for direction R in state State-B 1311In State-B moving R 1312ENV: (next state, see, prediction correct?) = (State-B, 0, False) 1313predict error 1 1314dir: dir isR 1315-/166: O: O332 (predict-no) 1316I see 0 and I'm going to do: predict-no 1317ENV: Agent did: predict-no for direction R in state State-B 1318In State-B moving R 1319ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1320predict error 0 1321dir: dir isL 1322|\-167: O: O333 (predict-yes) 1323I see 1 and I'm going to do: predict-yes 1324ENV: Agent did: predict-yes for direction L in state State-B 1325In State-B moving L 1326ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1327predict error 0 1328dir: dir isR 1329/|168: O: O335 (predict-yes) 1330I see 1 and I'm going to do: predict-yes 1331ENV: Agent did: predict-yes for direction R in state State-A 1332In State-A moving R 1333ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1334predict error 0 1335dir: dir isL 1336\-169: O: O337 (predict-yes) 1337I see 1 and I'm going to do: predict-yes 1338ENV: Agent did: predict-yes for direction L in state State-B 1339In State-B moving L 1340ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1341predict error 0 1342dir: dir isL 1343/|170: O: O339 (predict-yes) 1344I see 1 and I'm going to do: predict-yes 1345ENV: Agent did: predict-yes for direction L in state State-A 1346In State-A moving L 1347ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1348predict error 1 1349dir: dir isU 1350\-171: O: O341 (predict-yes) 1351I see 0 and I'm going to do: predict-yes 1352ENV: Agent did: predict-yes for direction U in state State-A 1353In State-A moving U 1354ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1355predict error 1 1356dir: dir isU 1357/172: O: O344 (predict-no) 1358I see 0 and I'm going to do: predict-no 1359ENV: Agent did: predict-no for direction U in state State-A 1360In State-A moving U 1361ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1362predict error 0 1363dir: dir isL 1364|\173: O: O345 (predict-yes) 1365I see 1 and I'm going to do: predict-yes 1366ENV: Agent did: predict-yes for direction L in state State-A 1367In State-A moving L 1368ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1369predict error 1 1370dir: dir isU 1371-/|174: O: O348 (predict-no) 1372I see 0 and I'm going to do: predict-no 1373ENV: Agent did: predict-no for direction U in state State-A 1374In State-A moving U 1375ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1376predict error 0 1377dir: dir isL 1378\-/175: O: O350 (predict-no) 1379I see 1 and I'm going to do: predict-no 1380ENV: Agent did: predict-no for direction L in state State-A 1381In State-A moving L 1382ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1383predict error 0 1384dir: dir isU 1385|\-/176: O: O352 (predict-no) 1386I see 1 and I'm going to do: predict-no 1387ENV: Agent did: predict-no for direction U in state State-A 1388In State-A moving U 1389ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1390predict error 0 1391dir: dir isU 1392|\-177: O: O354 (predict-no) 1393I see 1 and I'm going to do: predict-no 1394ENV: Agent did: predict-no for direction U in state State-A 1395In State-A moving U 1396ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1397predict error 0 1398dir: dir isR 1399/|\-178: O: O355 (predict-yes) 1400I see 1 and I'm going to do: predict-yes 1401ENV: Agent did: predict-yes for direction R in state State-A 1402In State-A moving R 1403ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1404predict error 0 1405dir: dir isL 1406/|\179: O: O357 (predict-yes) 1407I see 1 and I'm going to do: predict-yes 1408ENV: Agent did: predict-yes for direction L in state State-B 1409In State-B moving L 1410ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1411predict error 0 1412dir: dir isL 1413-/|180: O: O360 (predict-no) 1414I see 1 and I'm going to do: predict-no 1415ENV: Agent did: predict-no for direction L in state State-A 1416In State-A moving L 1417ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1418predict error 0 1419dir: dir isU 1420\-/181: O: O362 (predict-no) 1421I see 1 and I'm going to do: predict-no 1422ENV: Agent did: predict-no for direction U in state State-A 1423In State-A moving U 1424ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1425predict error 0 1426dir: dir isL 1427|182: O: O363 (predict-yes) 1428I see 1 and I'm going to do: predict-yes 1429ENV: Agent did: predict-yes for direction L in state State-A 1430In State-A moving L 1431ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1432predict error 1 1433dir: dir isU 1434\-183: O: O366 (predict-no) 1435I see 0 and I'm going to do: predict-no 1436ENV: Agent did: predict-no for direction U in state State-A 1437In State-A moving U 1438ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1439predict error 0 1440dir: dir isU 1441/|\-184: O: O367 (predict-yes) 1442I see 1 and I'm going to do: predict-yes 1443ENV: Agent did: predict-yes for direction U in state State-A 1444In State-A moving U 1445ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1446predict error 1 1447dir: dir isR 1448/|\185: O: O370 (predict-no) 1449I see 0 and I'm going to do: predict-no 1450ENV: Agent did: predict-no for direction R in state State-A 1451In State-A moving R 1452ENV: (next state, see, prediction correct?) = (State-B, 1, False) 1453predict error 1 1454dir: dir isL 1455-/|186: O: O372 (predict-no) 1456I see 0 and I'm going to do: predict-no 1457ENV: Agent did: predict-no for direction L in state State-B 1458In State-B moving L 1459ENV: (next state, see, prediction correct?) = (State-A, 1, False) 1460predict error 1 1461dir: dir isU 1462\-/187: O: O374 (predict-no) 1463I see 0 and I'm going to do: predict-no 1464ENV: Agent did: predict-no for direction U in state State-A 1465In State-A moving U 1466ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1467predict error 0 1468dir: dir isU 1469|188: O: O376 (predict-no) 1470I see 1 and I'm going to do: predict-no 1471ENV: Agent did: predict-no for direction U in state State-A 1472In State-A moving U 1473ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1474predict error 0 1475dir: dir isU 1476\-189: O: O377 (predict-yes) 1477I see 1 and I'm going to do: predict-yes 1478ENV: Agent did: predict-yes for direction U in state State-A 1479In State-A moving U 1480ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1481predict error 1 1482dir: dir isR 1483/|190: O: O379 (predict-yes) 1484I see 0 and I'm going to do: predict-yes 1485ENV: Agent did: predict-yes for direction R in state State-A 1486In State-A moving R 1487ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1488predict error 0 1489dir: dir isR 1490\-191: O: O382 (predict-no) 1491I see 1 and I'm going to do: predict-no 1492ENV: Agent did: predict-no for direction R in state State-B 1493In State-B moving R 1494ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1495predict error 0 1496dir: dir isR 1497/192: O: O384 (predict-no) 1498I see 1 and I'm going to do: predict-no 1499ENV: Agent did: predict-no for direction R in state State-B 1500In State-B moving R 1501ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1502predict error 0 1503dir: dir isL 1504|193: O: O385 (predict-yes) 1505I see 1 and I'm going to do: predict-yes 1506ENV: Agent did: predict-yes for direction L in state State-B 1507In State-B moving L 1508ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1509predict error 0 1510dir: dir isU 1511\-/194: O: O388 (predict-no) 1512I see 1 and I'm going to do: predict-no 1513ENV: Agent did: predict-no for direction U in state State-A 1514In State-A moving U 1515ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1516predict error 0 1517dir: dir isR 1518|\-195: O: O389 (predict-yes) 1519I see 1 and I'm going to do: predict-yes 1520ENV: Agent did: predict-yes for direction R in state State-A 1521In State-A moving R 1522ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1523predict error 0 1524dir: dir isL 1525/|\196: O: O391 (predict-yes) 1526I see 1 and I'm going to do: predict-yes 1527ENV: Agent did: predict-yes for direction L in state State-B 1528In State-B moving L 1529ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1530predict error 0 1531dir: dir isL 1532-197: O: O394 (predict-no) 1533I see 1 and I'm going to do: predict-no 1534ENV: Agent did: predict-no for direction L in state State-A 1535In State-A moving L 1536ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1537predict error 0 1538dir: dir isR 1539/|\198: O: O395 (predict-yes) 1540I see 1 and I'm going to do: predict-yes 1541ENV: Agent did: predict-yes for direction R in state State-A 1542In State-A moving R 1543ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1544predict error 0 1545dir: dir isL 1546-/|199: O: O397 (predict-yes) 1547I see 1 and I'm going to do: predict-yes 1548ENV: Agent did: predict-yes for direction L in state State-B 1549In State-B moving L 1550ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1551predict error 0 1552dir: dir isR 1553\-/200: O: O399 (predict-yes) 1554I see 1 and I'm going to do: predict-yes 1555ENV: Agent did: predict-yes for direction R in state State-A 1556In State-A moving R 1557ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1558predict error 0 1559dir: dir isL 1560|\-201: O: O401 (predict-yes) 1561I see 1 and I'm going to do: predict-yes 1562ENV: Agent did: predict-yes for direction L in state State-B 1563In State-B moving L 1564ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1565predict error 0 1566dir: dir isU 1567/|202: O: O404 (predict-no) 1568I see 1 and I'm going to do: predict-no 1569ENV: Agent did: predict-no for direction U in state State-A 1570In State-A moving U 1571ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1572predict error 0 1573dir: dir isU 1574\-203: O: O406 (predict-no) 1575I see 1 and I'm going to do: predict-no 1576ENV: Agent did: predict-no for direction U in state State-A 1577In State-A moving U 1578ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1579predict error 0 1580dir: dir isL 1581/|\204: O: O408 (predict-no) 1582I see 1 and I'm going to do: predict-no 1583ENV: Agent did: predict-no for direction L in state State-A 1584In State-A moving L 1585ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1586predict error 0 1587dir: dir isL 1588-205: O: O409 (predict-yes) 1589I see 1 and I'm going to do: predict-yes 1590ENV: Agent did: predict-yes for direction L in state State-A 1591In State-A moving L 1592ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1593predict error 1 1594dir: dir isL 1595/|\206: O: O412 (predict-no) 1596I see 0 and I'm going to do: predict-no 1597ENV: Agent did: predict-no for direction L in state State-A 1598In State-A moving L 1599ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1600predict error 0 1601dir: dir isU 1602-/|207: O: O414 (predict-no) 1603I see 1 and I'm going to do: predict-no 1604ENV: Agent did: predict-no for direction U in state State-A 1605In State-A moving U 1606ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1607predict error 0 1608dir: dir isU 1609\-/208: O: O416 (predict-no) 1610I see 1 and I'm going to do: predict-no 1611ENV: Agent did: predict-no for direction U in state State-A 1612In State-A moving U 1613ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1614predict error 0 1615dir: dir isR 1616|\209: O: O417 (predict-yes) 1617I see 1 and I'm going to do: predict-yes 1618ENV: Agent did: predict-yes for direction R in state State-A 1619In State-A moving R 1620ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1621predict error 0 1622dir: dir isL 1623-/|210: O: O419 (predict-yes) 1624I see 1 and I'm going to do: predict-yes 1625ENV: Agent did: predict-yes for direction L in state State-B 1626In State-B moving L 1627ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1628predict error 0 1629dir: dir isU 1630\-/211: O: O422 (predict-no) 1631I see 1 and I'm going to do: predict-no 1632ENV: Agent did: predict-no for direction U in state State-A 1633In State-A moving U 1634ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1635predict error 0 1636dir: dir isU 1637|212: O: O424 (predict-no) 1638I see 1 and I'm going to do: predict-no 1639ENV: Agent did: predict-no for direction U in state State-A 1640In State-A moving U 1641ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1642predict error 0 1643dir: dir isU 1644\-/213: O: O426 (predict-no) 1645I see 1 and I'm going to do: predict-no 1646ENV: Agent did: predict-no for direction U in state State-A 1647In State-A moving U 1648ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1649predict error 0 1650dir: dir isR 1651|\-214: O: O427 (predict-yes) 1652I see 1 and I'm going to do: predict-yes 1653ENV: Agent did: predict-yes for direction R in state State-A 1654In State-A moving R 1655ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1656predict error 0 1657dir: dir isU 1658/|215: O: O430 (predict-no) 1659I see 1 and I'm going to do: predict-no 1660ENV: Agent did: predict-no for direction U in state State-B 1661In State-B moving U 1662ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1663predict error 0 1664dir: dir isU 1665\216: O: O432 (predict-no) 1666I see 1 and I'm going to do: predict-no 1667ENV: Agent did: predict-no for direction U in state State-B 1668In State-B moving U 1669ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1670predict error 0 1671dir: dir isR 1672-/|217: O: O434 (predict-no) 1673I see 1 and I'm going to do: predict-no 1674ENV: Agent did: predict-no for direction R in state State-B 1675In State-B moving R 1676ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1677predict error 0 1678dir: dir isU 1679\-/218: O: O436 (predict-no) 1680I see 1 and I'm going to do: predict-no 1681ENV: Agent did: predict-no for direction U in state State-B 1682In State-B moving U 1683ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1684predict error 0 1685dir: dir isL 1686|\-219: O: O437 (predict-yes) 1687I see 1 and I'm going to do: predict-yes 1688ENV: Agent did: predict-yes for direction L in state State-B 1689In State-B moving L 1690ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1691predict error 0 1692dir: dir isU 1693/|220: O: O439 (predict-yes) 1694I see 1 and I'm going to do: predict-yes 1695ENV: Agent did: predict-yes for direction U in state State-A 1696In State-A moving U 1697ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1698predict error 1 1699dir: dir isL 1700\-/|221: O: O442 (predict-no) 1701I see 0 and I'm going to do: predict-no 1702ENV: Agent did: predict-no for direction L in state State-A 1703In State-A moving L 1704ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1705predict error 0 1706dir: dir isL 1707\222: O: O444 (predict-no) 1708I see 1 and I'm going to do: predict-no 1709ENV: Agent did: predict-no for direction L in state State-A 1710In State-A moving L 1711ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1712predict error 0 1713dir: dir isU 1714-/|223: O: O445 (predict-yes) 1715I see 1 and I'm going to do: predict-yes 1716ENV: Agent did: predict-yes for direction U in state State-A 1717In State-A moving U 1718ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1719predict error 1 1720dir: dir isL 1721\-/|sleeping... 1722\224: O: O448 (predict-no) 1723I see 0 and I'm going to do: predict-no 1724ENV: Agent did: predict-no for direction L in state State-A 1725In State-A moving L 1726ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1727predict error 0 1728dir: dir isU 1729-/|225: O: O450 (predict-no) 1730I see 1 and I'm going to do: predict-no 1731ENV: Agent did: predict-no for direction U in state State-A 1732In State-A moving U 1733ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1734predict error 0 1735dir: dir isR 1736\-/226: O: O451 (predict-yes) 1737I see 1 and I'm going to do: predict-yes 1738ENV: Agent did: predict-yes for direction R in state State-A 1739In State-A moving R 1740ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1741predict error 0 1742dir: dir isU 1743|\-/227: O: O454 (predict-no) 1744I see 1 and I'm going to do: predict-no 1745ENV: Agent did: predict-no for direction U in state State-B 1746In State-B moving U 1747ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1748predict error 0 1749dir: dir isR 1750|\-/228: O: O455 (predict-yes) 1751I see 1 and I'm going to do: predict-yes 1752ENV: Agent did: predict-yes for direction R in state State-B 1753In State-B moving R 1754ENV: (next state, see, prediction correct?) = (State-B, 0, False) 1755predict error 1 1756dir: dir isR 1757|\-229: O: O458 (predict-no) 1758I see 0 and I'm going to do: predict-no 1759ENV: Agent did: predict-no for direction R in state State-B 1760In State-B moving R 1761ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1762predict error 0 1763dir: dir isL 1764/|\230: O: O459 (predict-yes) 1765I see 1 and I'm going to do: predict-yes 1766ENV: Agent did: predict-yes for direction L in state State-B 1767In State-B moving L 1768ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1769predict error 0 1770dir: dir isU 1771-/231: O: O461 (predict-yes) 1772I see 1 and I'm going to do: predict-yes 1773ENV: Agent did: predict-yes for direction U in state State-A 1774In State-A moving U 1775ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1776predict error 1 1777dir: dir isR 1778|232: O: O463 (predict-yes) 1779I see 0 and I'm going to do: predict-yes 1780ENV: Agent did: predict-yes for direction R in state State-A 1781In State-A moving R 1782ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1783predict error 0 1784dir: dir isU 1785\-/233: O: O466 (predict-no) 1786I see 1 and I'm going to do: predict-no 1787ENV: Agent did: predict-no for direction U in state State-B 1788In State-B moving U 1789ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1790predict error 0 1791dir: dir isU 1792|\-234: O: O468 (predict-no) 1793I see 1 and I'm going to do: predict-no 1794ENV: Agent did: predict-no for direction U in state State-B 1795In State-B moving U 1796ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1797predict error 0 1798dir: dir isL 1799/|235: O: O469 (predict-yes) 1800I see 1 and I'm going to do: predict-yes 1801ENV: Agent did: predict-yes for direction L in state State-B 1802In State-B moving L 1803ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1804predict error 0 1805dir: dir isR 1806\-236: O: O471 (predict-yes) 1807I see 1 and I'm going to do: predict-yes 1808ENV: Agent did: predict-yes for direction R in state State-A 1809In State-A moving R 1810ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1811predict error 0 1812dir: dir isL 1813/|\237: O: O473 (predict-yes) 1814I see 1 and I'm going to do: predict-yes 1815ENV: Agent did: predict-yes for direction L in state State-B 1816In State-B moving L 1817ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1818predict error 0 1819dir: dir isL 1820-/238: O: O475 (predict-yes) 1821I see 1 and I'm going to do: predict-yes 1822ENV: Agent did: predict-yes for direction L in state State-A 1823In State-A moving L 1824ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1825predict error 1 1826dir: dir isL 1827|239: O: O478 (predict-no) 1828I see 0 and I'm going to do: predict-no 1829ENV: Agent did: predict-no for direction L in state State-A 1830In State-A moving L 1831ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1832predict error 0 1833dir: dir isU 1834\-240: O: O480 (predict-no) 1835I see 1 and I'm going to do: predict-no 1836ENV: Agent did: predict-no for direction U in state State-A 1837In State-A moving U 1838ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1839predict error 0 1840dir: dir isU 1841/|\241: O: O482 (predict-no) 1842I see 1 and I'm going to do: predict-no 1843ENV: Agent did: predict-no for direction U in state State-A 1844In State-A moving U 1845ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1846predict error 0 1847dir: dir isU 1848-242: O: O484 (predict-no) 1849I see 1 and I'm going to do: predict-no 1850ENV: Agent did: predict-no for direction U in state State-A 1851In State-A moving U 1852ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1853predict error 0 1854dir: dir isR 1855/|\243: O: O485 (predict-yes) 1856I see 1 and I'm going to do: predict-yes 1857ENV: Agent did: predict-yes for direction R in state State-A 1858In State-A moving R 1859ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1860predict error 0 1861dir: dir isR 1862-/|244: O: O487 (predict-yes) 1863I see 1 and I'm going to do: predict-yes 1864ENV: Agent did: predict-yes for direction R in state State-B 1865In State-B moving R 1866ENV: (next state, see, prediction correct?) = (State-B, 0, False) 1867predict error 1 1868dir: dir isU 1869\245: O: O490 (predict-no) 1870I see 0 and I'm going to do: predict-no 1871ENV: Agent did: predict-no for direction U in state State-B 1872In State-B moving U 1873ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1874predict error 0 1875dir: dir isR 1876-/|246: O: O492 (predict-no) 1877I see 1 and I'm going to do: predict-no 1878ENV: Agent did: predict-no for direction R in state State-B 1879In State-B moving R 1880ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1881predict error 0 1882dir: dir isR 1883\-/247: O: O494 (predict-no) 1884I see 1 and I'm going to do: predict-no 1885ENV: Agent did: predict-no for direction R in state State-B 1886In State-B moving R 1887ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1888predict error 0 1889dir: dir isL 1890|\248: O: O495 (predict-yes) 1891I see 1 and I'm going to do: predict-yes 1892ENV: Agent did: predict-yes for direction L in state State-B 1893In State-B moving L 1894ENV: (next state, see, prediction correct?) = (State-A, 1, True) 1895predict error 0 1896dir: dir isL 1897-/|\249: O: O498 (predict-no) 1898I see 1 and I'm going to do: predict-no 1899ENV: Agent did: predict-no for direction L in state State-A 1900In State-A moving L 1901ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1902predict error 0 1903dir: dir isL 1904-/|250: O: O500 (predict-no) 1905I see 1 and I'm going to do: predict-no 1906ENV: Agent did: predict-no for direction L in state State-A 1907In State-A moving L 1908ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1909predict error 0 1910dir: dir isU 1911\-251: O: O502 (predict-no) 1912I see 1 and I'm going to do: predict-no 1913ENV: Agent did: predict-no for direction U in state State-A 1914In State-A moving U 1915ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1916predict error 0 1917dir: dir isR 1918/252: O: O503 (predict-yes) 1919I see 1 and I'm going to do: predict-yes 1920ENV: Agent did: predict-yes for direction R in state State-A 1921In State-A moving R 1922ENV: (next state, see, prediction correct?) = (State-B, 1, True) 1923predict error 0 1924dir: dir isU 1925|\253: O: O506 (predict-no) 1926I see 1 and I'm going to do: predict-no 1927ENV: Agent did: predict-no for direction U in state State-B 1928In State-B moving U 1929ENV: (next state, see, prediction correct?) = (State-B, 0, True) 1930predict error 0 1931dir: dir isR 1932-254: O: O507 (predict-yes) 1933I see 1 and I'm going to do: predict-yes 1934ENV: Agent did: predict-yes for direction R in state State-B 1935In State-B moving R 1936ENV: (next state, see, prediction correct?) = (State-B, 0, False) 1937predict error 1 1938dir: dir isL 1939/|255: O: O510 (predict-no) 1940I see 0 and I'm going to do: predict-no 1941ENV: Agent did: predict-no for direction L in state State-B 1942In State-B moving L 1943ENV: (next state, see, prediction correct?) = (State-A, 1, False) 1944predict error 1 1945dir: dir isU 1946\-/256: O: O511 (predict-yes) 1947I see 0 and I'm going to do: predict-yes 1948ENV: Agent did: predict-yes for direction U in state State-A 1949In State-A moving U 1950ENV: (next state, see, prediction correct?) = (State-A, 0, False) 1951predict error 1 1952dir: dir isU 1953|\-257: O: O514 (predict-no) 1954I see 0 and I'm going to do: predict-no 1955ENV: Agent did: predict-no for direction U in state State-A 1956In State-A moving U 1957ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1958predict error 0 1959dir: dir isL 1960/|258: O: O516 (predict-no) 1961I see 1 and I'm going to do: predict-no 1962ENV: Agent did: predict-no for direction L in state State-A 1963In State-A moving L 1964ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1965predict error 0 1966dir: dir isU 1967\-/259: O: O518 (predict-no) 1968I see 1 and I'm going to do: predict-no 1969ENV: Agent did: predict-no for direction U in state State-A 1970In State-A moving U 1971ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1972predict error 0 1973dir: dir isL 1974|\-260: O: O520 (predict-no) 1975I see 1 and I'm going to do: predict-no 1976ENV: Agent did: predict-no for direction L in state State-A 1977In State-A moving L 1978ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1979predict error 0 1980dir: dir isL 1981/|261: O: O522 (predict-no) 1982I see 1 and I'm going to do: predict-no 1983ENV: Agent did: predict-no for direction L in state State-A 1984In State-A moving L 1985ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1986predict error 0 1987dir: dir isU 1988\262: O: O524 (predict-no) 1989I see 1 and I'm going to do: predict-no 1990ENV: Agent did: predict-no for direction U in state State-A 1991In State-A moving U 1992ENV: (next state, see, prediction correct?) = (State-A, 0, True) 1993predict error 0 1994dir: dir isL 1995-/|263: O: O526 (predict-no) 1996I see 1 and I'm going to do: predict-no 1997ENV: Agent did: predict-no for direction L in state State-A 1998In State-A moving L 1999ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2000predict error 0 2001dir: dir isL 2002\-/264: O: O528 (predict-no) 2003I see 1 and I'm going to do: predict-no 2004ENV: Agent did: predict-no for direction L in state State-A 2005In State-A moving L 2006ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2007predict error 0 2008dir: dir isU 2009|\-265: O: O530 (predict-no) 2010I see 1 and I'm going to do: predict-no 2011ENV: Agent did: predict-no for direction U in state State-A 2012In State-A moving U 2013ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2014predict error 0 2015dir: dir isR 2016/|266: O: O532 (predict-no) 2017I see 1 and I'm going to do: predict-no 2018ENV: Agent did: predict-no for direction R in state State-A 2019In State-A moving R 2020ENV: (next state, see, prediction correct?) = (State-B, 1, False) 2021predict error 1 2022dir: dir isL 2023\-/267: O: O534 (predict-no) 2024I see 0 and I'm going to do: predict-no 2025ENV: Agent did: predict-no for direction L in state State-B 2026In State-B moving L 2027ENV: (next state, see, prediction correct?) = (State-A, 1, False) 2028predict error 1 2029dir: dir isL 2030|\-268: O: O536 (predict-no) 2031I see 0 and I'm going to do: predict-no 2032ENV: Agent did: predict-no for direction L in state State-A 2033In State-A moving L 2034ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2035predict error 0 2036dir: dir isL 2037/269: O: O538 (predict-no) 2038I see 1 and I'm going to do: predict-no 2039ENV: Agent did: predict-no for direction L in state State-A 2040In State-A moving L 2041ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2042predict error 0 2043dir: dir isU 2044|\270: O: O540 (predict-no) 2045I see 1 and I'm going to do: predict-no 2046ENV: Agent did: predict-no for direction U in state State-A 2047In State-A moving U 2048ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2049predict error 0 2050dir: dir isL 2051-/271: O: O542 (predict-no) 2052I see 1 and I'm going to do: predict-no 2053ENV: Agent did: predict-no for direction L in state State-A 2054In State-A moving L 2055ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2056predict error 0 2057dir: dir isU 2058|272: O: O544 (predict-no) 2059I see 1 and I'm going to do: predict-no 2060ENV: Agent did: predict-no for direction U in state State-A 2061In State-A moving U 2062ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2063predict error 0 2064dir: dir isR 2065\-/273: O: O545 (predict-yes) 2066I see 1 and I'm going to do: predict-yes 2067ENV: Agent did: predict-yes for direction R in state State-A 2068In State-A moving R 2069ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2070predict error 0 2071dir: dir isU 2072|274: O: O548 (predict-no) 2073I see 1 and I'm going to do: predict-no 2074ENV: Agent did: predict-no for direction U in state State-B 2075In State-B moving U 2076ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2077predict error 0 2078dir: dir isU 2079\-275: O: O550 (predict-no) 2080I see 1 and I'm going to do: predict-no 2081ENV: Agent did: predict-no for direction U in state State-B 2082In State-B moving U 2083ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2084predict error 0 2085dir: dir isL 2086/|276: O: O551 (predict-yes) 2087I see 1 and I'm going to do: predict-yes 2088ENV: Agent did: predict-yes for direction L in state State-B 2089In State-B moving L 2090ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2091predict error 0 2092dir: dir isL 2093\-/277: O: O554 (predict-no) 2094I see 1 and I'm going to do: predict-no 2095ENV: Agent did: predict-no for direction L in state State-A 2096In State-A moving L 2097ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2098predict error 0 2099dir: dir isR 2100|\278: O: O555 (predict-yes) 2101I see 1 and I'm going to do: predict-yes 2102ENV: Agent did: predict-yes for direction R in state State-A 2103In State-A moving R 2104ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2105predict error 0 2106dir: dir isL 2107-/279: O: O557 (predict-yes) 2108I see 1 and I'm going to do: predict-yes 2109ENV: Agent did: predict-yes for direction L in state State-B 2110In State-B moving L 2111ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2112predict error 0 2113dir: dir isR 2114|\-280: O: O559 (predict-yes) 2115I see 1 and I'm going to do: predict-yes 2116ENV: Agent did: predict-yes for direction R in state State-A 2117In State-A moving R 2118ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2119predict error 0 2120dir: dir isL 2121/|281: O: O561 (predict-yes) 2122I see 1 and I'm going to do: predict-yes 2123ENV: Agent did: predict-yes for direction L in state State-B 2124In State-B moving L 2125ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2126predict error 0 2127dir: dir isL 2128\282: O: O563 (predict-yes) 2129I see 1 and I'm going to do: predict-yes 2130ENV: Agent did: predict-yes for direction L in state State-A 2131In State-A moving L 2132ENV: (next state, see, prediction correct?) = (State-A, 0, False) 2133predict error 1 2134dir: dir isU 2135-/|283: O: O566 (predict-no) 2136I see 0 and I'm going to do: predict-no 2137ENV: Agent did: predict-no for direction U in state State-A 2138In State-A moving U 2139ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2140predict error 0 2141dir: dir isL 2142\-284: O: O568 (predict-no) 2143I see 1 and I'm going to do: predict-no 2144ENV: Agent did: predict-no for direction L in state State-A 2145In State-A moving L 2146ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2147predict error 0 2148dir: dir isR 2149/|285: O: O569 (predict-yes) 2150I see 1 and I'm going to do: predict-yes 2151ENV: Agent did: predict-yes for direction R in state State-A 2152In State-A moving R 2153ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2154predict error 0 2155dir: dir isR 2156\-/|286: O: O572 (predict-no) 2157I see 1 and I'm going to do: predict-no 2158ENV: Agent did: predict-no for direction R in state State-B 2159In State-B moving R 2160ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2161predict error 0 2162dir: dir isL 2163\-/287: O: O574 (predict-no) 2164I see 1 and I'm going to do: predict-no 2165ENV: Agent did: predict-no for direction L in state State-B 2166In State-B moving L 2167ENV: (next state, see, prediction correct?) = (State-A, 1, False) 2168predict error 1 2169dir: dir isL 2170|\-288: O: O576 (predict-no) 2171I see 0 and I'm going to do: predict-no 2172ENV: Agent did: predict-no for direction L in state State-A 2173In State-A moving L 2174ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2175predict error 0 2176dir: dir isU 2177/|\289: O: O578 (predict-no) 2178I see 1 and I'm going to do: predict-no 2179ENV: Agent did: predict-no for direction U in state State-A 2180In State-A moving U 2181ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2182predict error 0 2183dir: dir isU 2184-/|290: O: O580 (predict-no) 2185I see 1 and I'm going to do: predict-no 2186ENV: Agent did: predict-no for direction U in state State-A 2187In State-A moving U 2188ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2189predict error 0 2190dir: dir isU 2191\-/291: O: O582 (predict-no) 2192I see 1 and I'm going to do: predict-no 2193ENV: Agent did: predict-no for direction U in state State-A 2194In State-A moving U 2195ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2196predict error 0 2197dir: dir isL 2198|292: O: O584 (predict-no) 2199I see 1 and I'm going to do: predict-no 2200ENV: Agent did: predict-no for direction L in state State-A 2201In State-A moving L 2202ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2203predict error 0 2204dir: dir isL 2205\-293: O: O586 (predict-no) 2206I see 1 and I'm going to do: predict-no 2207ENV: Agent did: predict-no for direction L in state State-A 2208In State-A moving L 2209ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2210predict error 0 2211dir: dir isR 2212/|\294: O: O587 (predict-yes) 2213I see 1 and I'm going to do: predict-yes 2214ENV: Agent did: predict-yes for direction R in state State-A 2215In State-A moving R 2216ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2217predict error 0 2218dir: dir isU 2219-/|295: O: O590 (predict-no) 2220I see 1 and I'm going to do: predict-no 2221ENV: Agent did: predict-no for direction U in state State-B 2222In State-B moving U 2223ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2224predict error 0 2225dir: dir isR 2226\296: O: O592 (predict-no) 2227I see 1 and I'm going to do: predict-no 2228ENV: Agent did: predict-no for direction R in state State-B 2229In State-B moving R 2230ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2231predict error 0 2232dir: dir isU 2233-/|297: O: O594 (predict-no) 2234I see 1 and I'm going to do: predict-no 2235ENV: Agent did: predict-no for direction U in state State-B 2236In State-B moving U 2237ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2238predict error 0 2239dir: dir isR 2240\-298: O: O596 (predict-no) 2241I see 1 and I'm going to do: predict-no 2242ENV: Agent did: predict-no for direction R in state State-B 2243In State-B moving R 2244ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2245predict error 0 2246dir: dir isL 2247/|\299: O: O597 (predict-yes) 2248I see 1 and I'm going to do: predict-yes 2249ENV: Agent did: predict-yes for direction L in state State-B 2250In State-B moving L 2251ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2252predict error 0 2253dir: dir isR 2254-/|300: O: O599 (predict-yes) 2255I see 1 and I'm going to do: predict-yes 2256ENV: Agent did: predict-yes for direction R in state State-A 2257In State-A moving R 2258ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2259predict error 0 2260dir: dir isL 2261\-/|\-301: O: O601 (predict-yes) 2262I see 1 and I'm going to do: predict-yes 2263ENV: Agent did: predict-yes for direction L in state State-B 2264In State-B moving L 2265ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2266predict error 0 2267dir: dir isL 2268/302: O: O604 (predict-no) 2269I see 1 and I'm going to do: predict-no 2270ENV: Agent did: predict-no for direction L in state State-A 2271In State-A moving L 2272ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2273predict error 0 2274dir: dir isL 2275|\303: O: O606 (predict-no) 2276I see 1 and I'm going to do: predict-no 2277ENV: Agent did: predict-no for direction L in state State-A 2278In State-A moving L 2279ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2280predict error 0 2281dir: dir isL 2282-/|304: O: O608 (predict-no) 2283I see 1 and I'm going to do: predict-no 2284ENV: Agent did: predict-no for direction L in state State-A 2285In State-A moving L 2286ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2287predict error 0 2288dir: dir isU 2289\-/305: O: O610 (predict-no) 2290I see 1 and I'm going to do: predict-no 2291ENV: Agent did: predict-no for direction U in state State-A 2292In State-A moving U 2293ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2294predict error 0 2295dir: dir isR 2296|\-306: O: O611 (predict-yes) 2297I see 1 and I'm going to do: predict-yes 2298ENV: Agent did: predict-yes for direction R in state State-A 2299In State-A moving R 2300ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2301predict error 0 2302dir: dir isR 2303/|\307: O: O614 (predict-no) 2304I see 1 and I'm going to do: predict-no 2305ENV: Agent did: predict-no for direction R in state State-B 2306In State-B moving R 2307ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2308predict error 0 2309dir: dir isR 2310-/|308: O: O616 (predict-no) 2311I see 1 and I'm going to do: predict-no 2312ENV: Agent did: predict-no for direction R in state State-B 2313In State-B moving R 2314ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2315predict error 0 2316dir: dir isU 2317\-/309: O: O618 (predict-no) 2318I see 1 and I'm going to do: predict-no 2319ENV: Agent did: predict-no for direction U in state State-B 2320In State-B moving U 2321ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2322predict error 0 2323dir: dir isR 2324|\-310: O: O620 (predict-no) 2325I see 1 and I'm going to do: predict-no 2326ENV: Agent did: predict-no for direction R in state State-B 2327In State-B moving R 2328ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2329predict error 0 2330dir: dir isL 2331/|\311: O: O621 (predict-yes) 2332I see 1 and I'm going to do: predict-yes 2333ENV: Agent did: predict-yes for direction L in state State-B 2334In State-B moving L 2335ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2336predict error 0 2337dir: dir isL 2338-312: O: O624 (predict-no) 2339I see 1 and I'm going to do: predict-no 2340ENV: Agent did: predict-no for direction L in state State-A 2341In State-A moving L 2342ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2343predict error 0 2344dir: dir isL 2345/|\313: O: O626 (predict-no) 2346I see 1 and I'm going to do: predict-no 2347ENV: Agent did: predict-no for direction L in state State-A 2348In State-A moving L 2349ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2350predict error 0 2351dir: dir isU 2352-/314: O: O628 (predict-no) 2353I see 1 and I'm going to do: predict-no 2354ENV: Agent did: predict-no for direction U in state State-A 2355In State-A moving U 2356ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2357predict error 0 2358dir: dir isU 2359|\315: O: O630 (predict-no) 2360I see 1 and I'm going to do: predict-no 2361ENV: Agent did: predict-no for direction U in state State-A 2362In State-A moving U 2363ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2364predict error 0 2365dir: dir isL 2366-/316: O: O632 (predict-no) 2367I see 1 and I'm going to do: predict-no 2368ENV: Agent did: predict-no for direction L in state State-A 2369In State-A moving L 2370ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2371predict error 0 2372dir: dir isR 2373|\-317: O: O634 (predict-no) 2374I see 1 and I'm going to do: predict-no 2375ENV: Agent did: predict-no for direction R in state State-A 2376In State-A moving R 2377ENV: (next state, see, prediction correct?) = (State-B, 1, False) 2378predict error 1 2379dir: dir isR 2380/|318: O: O636 (predict-no) 2381I see 0 and I'm going to do: predict-no 2382ENV: Agent did: predict-no for direction R in state State-B 2383In State-B moving R 2384ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2385predict error 0 2386dir: dir isR 2387\-/319: O: O638 (predict-no) 2388I see 1 and I'm going to do: predict-no 2389ENV: Agent did: predict-no for direction R in state State-B 2390In State-B moving R 2391ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2392predict error 0 2393dir: dir isR 2394|\-320: O: O640 (predict-no) 2395I see 1 and I'm going to do: predict-no 2396ENV: Agent did: predict-no for direction R in state State-B 2397In State-B moving R 2398ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2399predict error 0 2400dir: dir isL 2401/|321: O: O641 (predict-yes) 2402I see 1 and I'm going to do: predict-yes 2403ENV: Agent did: predict-yes for direction L in state State-B 2404In State-B moving L 2405ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2406predict error 0 2407dir: dir isL 2408\322: O: O643 (predict-yes) 2409I see 1 and I'm going to do: predict-yes 2410ENV: Agent did: predict-yes for direction L in state State-A 2411In State-A moving L 2412ENV: (next state, see, prediction correct?) = (State-A, 0, False) 2413predict error 1 2414dir: dir isL 2415-/|323: O: O645 (predict-yes) 2416I see 0 and I'm going to do: predict-yes 2417ENV: Agent did: predict-yes for direction L in state State-A 2418In State-A moving L 2419ENV: (next state, see, prediction correct?) = (State-A, 0, False) 2420predict error 1 2421dir: dir isL 2422\-/324: O: O648 (predict-no) 2423I see 0 and I'm going to do: predict-no 2424ENV: Agent did: predict-no for direction L in state State-A 2425In State-A moving L 2426ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2427predict error 0 2428dir: dir isR 2429|\325: O: O649 (predict-yes) 2430I see 1 and I'm going to do: predict-yes 2431ENV: Agent did: predict-yes for direction R in state State-A 2432In State-A moving R 2433ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2434predict error 0 2435dir: dir isL 2436-/|326: O: O651 (predict-yes) 2437I see 1 and I'm going to do: predict-yes 2438ENV: Agent did: predict-yes for direction L in state State-B 2439In State-B moving L 2440ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2441predict error 0 2442dir: dir isL 2443\-/327: O: O654 (predict-no) 2444I see 1 and I'm going to do: predict-no 2445ENV: Agent did: predict-no for direction L in state State-A 2446In State-A moving L 2447ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2448predict error 0 2449dir: dir isR 2450|\-328: O: O655 (predict-yes) 2451I see 1 and I'm going to do: predict-yes 2452ENV: Agent did: predict-yes for direction R in state State-A 2453In State-A moving R 2454ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2455predict error 0 2456dir: dir isL 2457/|\329: O: O657 (predict-yes) 2458I see 1 and I'm going to do: predict-yes 2459ENV: Agent did: predict-yes for direction L in state State-B 2460In State-B moving L 2461ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2462predict error 0 2463dir: dir isU 2464-/|330: O: O660 (predict-no) 2465I see 1 and I'm going to do: predict-no 2466ENV: Agent did: predict-no for direction U in state State-A 2467In State-A moving U 2468ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2469predict error 0 2470dir: dir isR 2471\-331: O: O661 (predict-yes) 2472I see 1 and I'm going to do: predict-yes 2473ENV: Agent did: predict-yes for direction R in state State-A 2474In State-A moving R 2475ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2476predict error 0 2477dir: dir isU 2478/332: O: O663 (predict-yes) 2479I see 1 and I'm going to do: predict-yes 2480ENV: Agent did: predict-yes for direction U in state State-B 2481In State-B moving U 2482ENV: (next state, see, prediction correct?) = (State-B, 0, False) 2483predict error 1 2484dir: dir isL 2485|\-333: O: O665 (predict-yes) 2486I see 0 and I'm going to do: predict-yes 2487ENV: Agent did: predict-yes for direction L in state State-B 2488In State-B moving L 2489ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2490predict error 0 2491dir: dir isR 2492/|334: O: O667 (predict-yes) 2493I see 1 and I'm going to do: predict-yes 2494ENV: Agent did: predict-yes for direction R in state State-A 2495In State-A moving R 2496ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2497predict error 0 2498dir: dir isU 2499\-/335: O: O670 (predict-no) 2500I see 1 and I'm going to do: predict-no 2501ENV: Agent did: predict-no for direction U in state State-B 2502In State-B moving U 2503ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2504predict error 0 2505dir: dir isL 2506|\-336: O: O671 (predict-yes) 2507I see 1 and I'm going to do: predict-yes 2508ENV: Agent did: predict-yes for direction L in state State-B 2509In State-B moving L 2510ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2511predict error 0 2512dir: dir isU 2513/|\337: O: O673 (predict-yes) 2514I see 1 and I'm going to do: predict-yes 2515ENV: Agent did: predict-yes for direction U in state State-A 2516In State-A moving U 2517ENV: (next state, see, prediction correct?) = (State-A, 0, False) 2518predict error 1 2519dir: dir isL 2520-/338: O: O676 (predict-no) 2521I see 0 and I'm going to do: predict-no 2522ENV: Agent did: predict-no for direction L in state State-A 2523In State-A moving L 2524ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2525predict error 0 2526dir: dir isU 2527|\339: O: O678 (predict-no) 2528I see 1 and I'm going to do: predict-no 2529ENV: Agent did: predict-no for direction U in state State-A 2530In State-A moving U 2531ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2532predict error 0 2533dir: dir isU 2534-340: O: O680 (predict-no) 2535I see 1 and I'm going to do: predict-no 2536ENV: Agent did: predict-no for direction U in state State-A 2537In State-A moving U 2538ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2539predict error 0 2540dir: dir isU 2541/|341: O: O682 (predict-no) 2542I see 1 and I'm going to do: predict-no 2543ENV: Agent did: predict-no for direction U in state State-A 2544In State-A moving U 2545ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2546predict error 0 2547dir: dir isL 2548\342: O: O684 (predict-no) 2549I see 1 and I'm going to do: predict-no 2550ENV: Agent did: predict-no for direction L in state State-A 2551In State-A moving L 2552ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2553predict error 0 2554dir: dir isL 2555-/|343: O: O686 (predict-no) 2556I see 1 and I'm going to do: predict-no 2557ENV: Agent did: predict-no for direction L in state State-A 2558In State-A moving L 2559ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2560predict error 0 2561dir: dir isR 2562\-/344: O: O687 (predict-yes) 2563I see 1 and I'm going to do: predict-yes 2564ENV: Agent did: predict-yes for direction R in state State-A 2565In State-A moving R 2566ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2567predict error 0 2568dir: dir isU 2569|\-345: O: O689 (predict-yes) 2570I see 1 and I'm going to do: predict-yes 2571ENV: Agent did: predict-yes for direction U in state State-B 2572In State-B moving U 2573ENV: (next state, see, prediction correct?) = (State-B, 0, False) 2574predict error 1 2575dir: dir isL 2576/|\-sleeping... 2577/346: O: O691 (predict-yes) 2578I see 0 and I'm going to do: predict-yes 2579ENV: Agent did: predict-yes for direction L in state State-B 2580In State-B moving L 2581ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2582predict error 0 2583dir: dir isU 2584|\-347: O: O693 (predict-yes) 2585I see 1 and I'm going to do: predict-yes 2586ENV: Agent did: predict-yes for direction U in state State-A 2587In State-A moving U 2588ENV: (next state, see, prediction correct?) = (State-A, 0, False) 2589predict error 1 2590dir: dir isL 2591/|\348: O: O696 (predict-no) 2592I see 0 and I'm going to do: predict-no 2593ENV: Agent did: predict-no for direction L in state State-A 2594In State-A moving L 2595ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2596predict error 0 2597dir: dir isU 2598-/|349: O: O698 (predict-no) 2599I see 1 and I'm going to do: predict-no 2600ENV: Agent did: predict-no for direction U in state State-A 2601In State-A moving U 2602ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2603predict error 0 2604dir: dir isL 2605\-/350: O: O700 (predict-no) 2606I see 1 and I'm going to do: predict-no 2607ENV: Agent did: predict-no for direction L in state State-A 2608In State-A moving L 2609ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2610predict error 0 2611dir: dir isL 2612|\-351: O: O702 (predict-no) 2613I see 1 and I'm going to do: predict-no 2614ENV: Agent did: predict-no for direction L in state State-A 2615In State-A moving L 2616ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2617predict error 0 2618dir: dir isU 2619/352: O: O704 (predict-no) 2620I see 1 and I'm going to do: predict-no 2621ENV: Agent did: predict-no for direction U in state State-A 2622In State-A moving U 2623ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2624predict error 0 2625dir: dir isU 2626|\353: O: O706 (predict-no) 2627I see 1 and I'm going to do: predict-no 2628ENV: Agent did: predict-no for direction U in state State-A 2629In State-A moving U 2630ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2631predict error 0 2632dir: dir isU 2633-/|354: O: O708 (predict-no) 2634I see 1 and I'm going to do: predict-no 2635ENV: Agent did: predict-no for direction U in state State-A 2636In State-A moving U 2637ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2638predict error 0 2639dir: dir isU 2640\-/355: O: O710 (predict-no) 2641I see 1 and I'm going to do: predict-no 2642ENV: Agent did: predict-no for direction U in state State-A 2643In State-A moving U 2644ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2645predict error 0 2646dir: dir isU 2647|\-356: O: O712 (predict-no) 2648I see 1 and I'm going to do: predict-no 2649ENV: Agent did: predict-no for direction U in state State-A 2650In State-A moving U 2651ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2652predict error 0 2653dir: dir isU 2654/|\357: O: O714 (predict-no) 2655I see 1 and I'm going to do: predict-no 2656ENV: Agent did: predict-no for direction U in state State-A 2657In State-A moving U 2658ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2659predict error 0 2660dir: dir isL 2661-/|358: O: O716 (predict-no) 2662I see 1 and I'm going to do: predict-no 2663ENV: Agent did: predict-no for direction L in state State-A 2664In State-A moving L 2665ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2666predict error 0 2667dir: dir isR 2668\-/359: O: O718 (predict-no) 2669I see 1 and I'm going to do: predict-no 2670ENV: Agent did: predict-no for direction R in state State-A 2671In State-A moving R 2672ENV: (next state, see, prediction correct?) = (State-B, 1, False) 2673predict error 1 2674dir: dir isL 2675|\360: O: O719 (predict-yes) 2676I see 0 and I'm going to do: predict-yes 2677ENV: Agent did: predict-yes for direction L in state State-B 2678In State-B moving L 2679ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2680predict error 0 2681dir: dir isU 2682-/|361: O: O722 (predict-no) 2683I see 1 and I'm going to do: predict-no 2684ENV: Agent did: predict-no for direction U in state State-A 2685In State-A moving U 2686ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2687predict error 0 2688dir: dir isU 2689\362: O: O724 (predict-no) 2690I see 1 and I'm going to do: predict-no 2691ENV: Agent did: predict-no for direction U in state State-A 2692In State-A moving U 2693ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2694predict error 0 2695dir: dir isL 2696-/|363: O: O726 (predict-no) 2697I see 1 and I'm going to do: predict-no 2698ENV: Agent did: predict-no for direction L in state State-A 2699In State-A moving L 2700ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2701predict error 0 2702dir: dir isL 2703\-/364: O: O728 (predict-no) 2704I see 1 and I'm going to do: predict-no 2705ENV: Agent did: predict-no for direction L in state State-A 2706In State-A moving L 2707ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2708predict error 0 2709dir: dir isU 2710|\365: O: O730 (predict-no) 2711I see 1 and I'm going to do: predict-no 2712ENV: Agent did: predict-no for direction U in state State-A 2713In State-A moving U 2714ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2715predict error 0 2716dir: dir isU 2717-/|366: O: O732 (predict-no) 2718I see 1 and I'm going to do: predict-no 2719ENV: Agent did: predict-no for direction U in state State-A 2720In State-A moving U 2721ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2722predict error 0 2723dir: dir isR 2724\-/367: O: O733 (predict-yes) 2725I see 1 and I'm going to do: predict-yes 2726ENV: Agent did: predict-yes for direction R in state State-A 2727In State-A moving R 2728ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2729predict error 0 2730dir: dir isR 2731|\368: O: O735 (predict-yes) 2732I see 1 and I'm going to do: predict-yes 2733ENV: Agent did: predict-yes for direction R in state State-B 2734In State-B moving R 2735ENV: (next state, see, prediction correct?) = (State-B, 0, False) 2736predict error 1 2737dir: dir isU 2738-/|369: O: O738 (predict-no) 2739I see 0 and I'm going to do: predict-no 2740ENV: Agent did: predict-no for direction U in state State-B 2741In State-B moving U 2742ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2743predict error 0 2744dir: dir isR 2745\-/370: O: O740 (predict-no) 2746I see 1 and I'm going to do: predict-no 2747ENV: Agent did: predict-no for direction R in state State-B 2748In State-B moving R 2749ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2750predict error 0 2751dir: dir isR 2752|\371: O: O742 (predict-no) 2753I see 1 and I'm going to do: predict-no 2754ENV: Agent did: predict-no for direction R in state State-B 2755In State-B moving R 2756ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2757predict error 0 2758dir: dir isR 2759-372: O: O744 (predict-no) 2760I see 1 and I'm going to do: predict-no 2761ENV: Agent did: predict-no for direction R in state State-B 2762In State-B moving R 2763ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2764predict error 0 2765dir: dir isL 2766/|\373: O: O745 (predict-yes) 2767I see 1 and I'm going to do: predict-yes 2768ENV: Agent did: predict-yes for direction L in state State-B 2769In State-B moving L 2770ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2771predict error 0 2772dir: dir isL 2773-/374: O: O748 (predict-no) 2774I see 1 and I'm going to do: predict-no 2775ENV: Agent did: predict-no for direction L in state State-A 2776In State-A moving L 2777ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2778predict error 0 2779dir: dir isR 2780|\-375: O: O749 (predict-yes) 2781I see 1 and I'm going to do: predict-yes 2782ENV: Agent did: predict-yes for direction R in state State-A 2783In State-A moving R 2784ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2785predict error 0 2786dir: dir isR 2787/|\376: O: O752 (predict-no) 2788I see 1 and I'm going to do: predict-no 2789ENV: Agent did: predict-no for direction R in state State-B 2790In State-B moving R 2791ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2792predict error 0 2793dir: dir isR 2794-/|377: O: O754 (predict-no) 2795I see 1 and I'm going to do: predict-no 2796ENV: Agent did: predict-no for direction R in state State-B 2797In State-B moving R 2798ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2799predict error 0 2800dir: dir isL 2801\-378: O: O755 (predict-yes) 2802I see 1 and I'm going to do: predict-yes 2803ENV: Agent did: predict-yes for direction L in state State-B 2804In State-B moving L 2805ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2806predict error 0 2807dir: dir isR 2808/|\379: O: O757 (predict-yes) 2809I see 1 and I'm going to do: predict-yes 2810ENV: Agent did: predict-yes for direction R in state State-A 2811In State-A moving R 2812ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2813predict error 0 2814dir: dir isL 2815-/|380: O: O759 (predict-yes) 2816I see 1 and I'm going to do: predict-yes 2817ENV: Agent did: predict-yes for direction L in state State-B 2818In State-B moving L 2819ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2820predict error 0 2821dir: dir isL 2822\-/381: O: O762 (predict-no) 2823I see 1 and I'm going to do: predict-no 2824ENV: Agent did: predict-no for direction L in state State-A 2825In State-A moving L 2826ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2827predict error 0 2828dir: dir isL 2829|382: O: O764 (predict-no) 2830I see 1 and I'm going to do: predict-no 2831ENV: Agent did: predict-no for direction L in state State-A 2832In State-A moving L 2833ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2834predict error 0 2835dir: dir isU 2836\-/383: O: O766 (predict-no) 2837I see 1 and I'm going to do: predict-no 2838ENV: Agent did: predict-no for direction U in state State-A 2839In State-A moving U 2840ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2841predict error 0 2842dir: dir isR 2843|\384: O: O767 (predict-yes) 2844I see 1 and I'm going to do: predict-yes 2845ENV: Agent did: predict-yes for direction R in state State-A 2846In State-A moving R 2847ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2848predict error 0 2849dir: dir isR 2850-/|385: O: O770 (predict-no) 2851I see 1 and I'm going to do: predict-no 2852ENV: Agent did: predict-no for direction R in state State-B 2853In State-B moving R 2854ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2855predict error 0 2856dir: dir isR 2857\-386: O: O772 (predict-no) 2858I see 1 and I'm going to do: predict-no 2859ENV: Agent did: predict-no for direction R in state State-B 2860In State-B moving R 2861ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2862predict error 0 2863dir: dir isL 2864/|\387: O: O773 (predict-yes) 2865I see 1 and I'm going to do: predict-yes 2866ENV: Agent did: predict-yes for direction L in state State-B 2867In State-B moving L 2868ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2869predict error 0 2870dir: dir isL 2871-/|388: O: O776 (predict-no) 2872I see 1 and I'm going to do: predict-no 2873ENV: Agent did: predict-no for direction L in state State-A 2874In State-A moving L 2875ENV: (next state, see, prediction correct?) = (State-A, 0, True) 2876predict error 0 2877dir: dir isR 2878\-389: O: O777 (predict-yes) 2879I see 1 and I'm going to do: predict-yes 2880ENV: Agent did: predict-yes for direction R in state State-A 2881In State-A moving R 2882ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2883predict error 0 2884dir: dir isR 2885/|\390: O: O779 (predict-yes) 2886I see 1 and I'm going to do: predict-yes 2887ENV: Agent did: predict-yes for direction R in state State-B 2888In State-B moving R 2889ENV: (next state, see, prediction correct?) = (State-B, 0, False) 2890predict error 1 2891dir: dir isR 2892-/|391: O: O782 (predict-no) 2893I see 0 and I'm going to do: predict-no 2894ENV: Agent did: predict-no for direction R in state State-B 2895In State-B moving R 2896ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2897predict error 0 2898dir: dir isR 2899\392: O: O784 (predict-no) 2900I see 1 and I'm going to do: predict-no 2901ENV: Agent did: predict-no for direction R in state State-B 2902In State-B moving R 2903ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2904predict error 0 2905dir: dir isU 2906-/|393: O: O786 (predict-no) 2907I see 1 and I'm going to do: predict-no 2908ENV: Agent did: predict-no for direction U in state State-B 2909In State-B moving U 2910ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2911predict error 0 2912dir: dir isU 2913\-/394: O: O788 (predict-no) 2914I see 1 and I'm going to do: predict-no 2915ENV: Agent did: predict-no for direction U in state State-B 2916In State-B moving U 2917ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2918predict error 0 2919dir: dir isL 2920|\395: O: O789 (predict-yes) 2921I see 1 and I'm going to do: predict-yes 2922ENV: Agent did: predict-yes for direction L in state State-B 2923In State-B moving L 2924ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2925predict error 0 2926dir: dir isR 2927-/|396: O: O791 (predict-yes) 2928I see 1 and I'm going to do: predict-yes 2929ENV: Agent did: predict-yes for direction R in state State-A 2930In State-A moving R 2931ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2932predict error 0 2933dir: dir isR 2934\-397: O: O794 (predict-no) 2935I see 1 and I'm going to do: predict-no 2936ENV: Agent did: predict-no for direction R in state State-B 2937In State-B moving R 2938ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2939predict error 0 2940dir: dir isL 2941/|\398: O: O795 (predict-yes) 2942I see 1 and I'm going to do: predict-yes 2943ENV: Agent did: predict-yes for direction L in state State-B 2944In State-B moving L 2945ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2946predict error 0 2947dir: dir isR 2948-/|399: O: O797 (predict-yes) 2949I see 1 and I'm going to do: predict-yes 2950ENV: Agent did: predict-yes for direction R in state State-A 2951In State-A moving R 2952ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2953predict error 0 2954dir: dir isR 2955\-/400: O: O800 (predict-no) 2956I see 1 and I'm going to do: predict-no 2957ENV: Agent did: predict-no for direction R in state State-B 2958In State-B moving R 2959ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2960predict error 0 2961dir: dir isU 2962|\-401: O: O802 (predict-no) 2963I see 1 and I'm going to do: predict-no 2964ENV: Agent did: predict-no for direction U in state State-B 2965In State-B moving U 2966ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2967predict error 0 2968dir: dir isU 2969/402: O: O804 (predict-no) 2970I see 1 and I'm going to do: predict-no 2971ENV: Agent did: predict-no for direction U in state State-B 2972In State-B moving U 2973ENV: (next state, see, prediction correct?) = (State-B, 0, True) 2974predict error 0 2975dir: dir isL 2976|\403: O: O805 (predict-yes) 2977I see 1 and I'm going to do: predict-yes 2978ENV: Agent did: predict-yes for direction L in state State-B 2979In State-B moving L 2980ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2981predict error 0 2982dir: dir isR 2983-/404: O: O807 (predict-yes) 2984I see 1 and I'm going to do: predict-yes 2985ENV: Agent did: predict-yes for direction R in state State-A 2986In State-A moving R 2987ENV: (next state, see, prediction correct?) = (State-B, 1, True) 2988predict error 0 2989dir: dir isL 2990|\-405: O: O809 (predict-yes) 2991I see 1 and I'm going to do: predict-yes 2992ENV: Agent did: predict-yes for direction L in state State-B 2993In State-B moving L 2994ENV: (next state, see, prediction correct?) = (State-A, 1, True) 2995predict error 0 2996dir: dir isL 2997/|406: O: O812 (predict-no) 2998I see 1 and I'm going to do: predict-no 2999ENV: Agent did: predict-no for direction L in state State-A 3000In State-A moving L 3001ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3002predict error 0 3003dir: dir isR 3004\-407: O: O813 (predict-yes) 3005I see 1 and I'm going to do: predict-yes 3006ENV: Agent did: predict-yes for direction R in state State-A 3007In State-A moving R 3008ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3009predict error 0 3010dir: dir isU 3011/|\408: O: O816 (predict-no) 3012I see 1 and I'm going to do: predict-no 3013ENV: Agent did: predict-no for direction U in state State-B 3014In State-B moving U 3015ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3016predict error 0 3017dir: dir isL 3018-/409: O: O817 (predict-yes) 3019I see 1 and I'm going to do: predict-yes 3020ENV: Agent did: predict-yes for direction L in state State-B 3021In State-B moving L 3022ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3023predict error 0 3024dir: dir isU 3025|\-410: O: O820 (predict-no) 3026I see 1 and I'm going to do: predict-no 3027ENV: Agent did: predict-no for direction U in state State-A 3028In State-A moving U 3029ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3030predict error 0 3031dir: dir isU 3032/|\411: O: O822 (predict-no) 3033I see 1 and I'm going to do: predict-no 3034ENV: Agent did: predict-no for direction U in state State-A 3035In State-A moving U 3036ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3037predict error 0 3038dir: dir isL 3039-412: O: O824 (predict-no) 3040I see 1 and I'm going to do: predict-no 3041ENV: Agent did: predict-no for direction L in state State-A 3042In State-A moving L 3043ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3044predict error 0 3045dir: dir isU 3046/|413: O: O826 (predict-no) 3047I see 1 and I'm going to do: predict-no 3048ENV: Agent did: predict-no for direction U in state State-A 3049In State-A moving U 3050ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3051predict error 0 3052dir: dir isU 3053\-/414: O: O828 (predict-no) 3054I see 1 and I'm going to do: predict-no 3055ENV: Agent did: predict-no for direction U in state State-A 3056In State-A moving U 3057ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3058predict error 0 3059dir: dir isR 3060|\-415: O: O830 (predict-no) 3061I see 1 and I'm going to do: predict-no 3062ENV: Agent did: predict-no for direction R in state State-A 3063In State-A moving R 3064ENV: (next state, see, prediction correct?) = (State-B, 1, False) 3065predict error 1 3066dir: dir isU 3067/|\416: O: O831 (predict-yes) 3068I see 0 and I'm going to do: predict-yes 3069ENV: Agent did: predict-yes for direction U in state State-B 3070In State-B moving U 3071ENV: (next state, see, prediction correct?) = (State-B, 0, False) 3072predict error 1 3073dir: dir isU 3074-/417: O: O834 (predict-no) 3075I see 0 and I'm going to do: predict-no 3076ENV: Agent did: predict-no for direction U in state State-B 3077In State-B moving U 3078ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3079predict error 0 3080dir: dir isR 3081|\-418: O: O836 (predict-no) 3082I see 1 and I'm going to do: predict-no 3083ENV: Agent did: predict-no for direction R in state State-B 3084In State-B moving R 3085ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3086predict error 0 3087dir: dir isU 3088/|419: O: O838 (predict-no) 3089I see 1 and I'm going to do: predict-no 3090ENV: Agent did: predict-no for direction U in state State-B 3091In State-B moving U 3092ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3093predict error 0 3094dir: dir isU 3095\-420: O: O840 (predict-no) 3096I see 1 and I'm going to do: predict-no 3097ENV: Agent did: predict-no for direction U in state State-B 3098In State-B moving U 3099ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3100predict error 0 3101dir: dir isU 3102/421: O: O841 (predict-yes) 3103I see 1 and I'm going to do: predict-yes 3104ENV: Agent did: predict-yes for direction U in state State-B 3105In State-B moving U 3106ENV: (next state, see, prediction correct?) = (State-B, 0, False) 3107predict error 1 3108dir: dir isR 3109|422: O: O844 (predict-no) 3110I see 0 and I'm going to do: predict-no 3111ENV: Agent did: predict-no for direction R in state State-B 3112In State-B moving R 3113ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3114predict error 0 3115dir: dir isL 3116\-/423: O: O845 (predict-yes) 3117I see 1 and I'm going to do: predict-yes 3118ENV: Agent did: predict-yes for direction L in state State-B 3119In State-B moving L 3120ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3121predict error 0 3122dir: dir isL 3123|\-424: O: O848 (predict-no) 3124I see 1 and I'm going to do: predict-no 3125ENV: Agent did: predict-no for direction L in state State-A 3126In State-A moving L 3127ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3128predict error 0 3129dir: dir isL 3130/|\425: O: O850 (predict-no) 3131I see 1 and I'm going to do: predict-no 3132ENV: Agent did: predict-no for direction L in state State-A 3133In State-A moving L 3134ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3135predict error 0 3136dir: dir isR 3137-/|426: O: O851 (predict-yes) 3138I see 1 and I'm going to do: predict-yes 3139ENV: Agent did: predict-yes for direction R in state State-A 3140In State-A moving R 3141ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3142predict error 0 3143dir: dir isU 3144\-/427: O: O854 (predict-no) 3145I see 1 and I'm going to do: predict-no 3146ENV: Agent did: predict-no for direction U in state State-B 3147In State-B moving U 3148ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3149predict error 0 3150dir: dir isL 3151|\-428: O: O855 (predict-yes) 3152I see 1 and I'm going to do: predict-yes 3153ENV: Agent did: predict-yes for direction L in state State-B 3154In State-B moving L 3155ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3156predict error 0 3157dir: dir isU 3158/|\429: O: O858 (predict-no) 3159I see 1 and I'm going to do: predict-no 3160ENV: Agent did: predict-no for direction U in state State-A 3161In State-A moving U 3162ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3163predict error 0 3164dir: dir isU 3165-/|430: O: O860 (predict-no) 3166I see 1 and I'm going to do: predict-no 3167ENV: Agent did: predict-no for direction U in state State-A 3168In State-A moving U 3169ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3170predict error 0 3171dir: dir isR 3172\-/431: O: O861 (predict-yes) 3173I see 1 and I'm going to do: predict-yes 3174ENV: Agent did: predict-yes for direction R in state State-A 3175In State-A moving R 3176ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3177predict error 0 3178dir: dir isR 3179|432: O: O864 (predict-no) 3180I see 1 and I'm going to do: predict-no 3181ENV: Agent did: predict-no for direction R in state State-B 3182In State-B moving R 3183ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3184predict error 0 3185dir: dir isL 3186\-433: O: O865 (predict-yes) 3187I see 1 and I'm going to do: predict-yes 3188ENV: Agent did: predict-yes for direction L in state State-B 3189In State-B moving L 3190ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3191predict error 0 3192dir: dir isU 3193/|\434: O: O868 (predict-no) 3194I see 1 and I'm going to do: predict-no 3195ENV: Agent did: predict-no for direction U in state State-A 3196In State-A moving U 3197ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3198predict error 0 3199dir: dir isL 3200-435: O: O870 (predict-no) 3201I see 1 and I'm going to do: predict-no 3202ENV: Agent did: predict-no for direction L in state State-A 3203In State-A moving L 3204ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3205predict error 0 3206dir: dir isU 3207/|\436: O: O872 (predict-no) 3208I see 1 and I'm going to do: predict-no 3209ENV: Agent did: predict-no for direction U in state State-A 3210In State-A moving U 3211ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3212predict error 0 3213dir: dir isU 3214-/|437: O: O874 (predict-no) 3215I see 1 and I'm going to do: predict-no 3216ENV: Agent did: predict-no for direction U in state State-A 3217In State-A moving U 3218ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3219predict error 0 3220dir: dir isR 3221\-/438: O: O875 (predict-yes) 3222I see 1 and I'm going to do: predict-yes 3223ENV: Agent did: predict-yes for direction R in state State-A 3224In State-A moving R 3225ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3226predict error 0 3227dir: dir isL 3228|439: O: O877 (predict-yes) 3229I see 1 and I'm going to do: predict-yes 3230ENV: Agent did: predict-yes for direction L in state State-B 3231In State-B moving L 3232ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3233predict error 0 3234dir: dir isU 3235\-440: O: O880 (predict-no) 3236I see 1 and I'm going to do: predict-no 3237ENV: Agent did: predict-no for direction U in state State-A 3238In State-A moving U 3239ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3240predict error 0 3241dir: dir isU 3242/|441: O: O882 (predict-no) 3243I see 1 and I'm going to do: predict-no 3244ENV: Agent did: predict-no for direction U in state State-A 3245In State-A moving U 3246ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3247predict error 0 3248dir: dir isL 3249\442: O: O884 (predict-no) 3250I see 1 and I'm going to do: predict-no 3251ENV: Agent did: predict-no for direction L in state State-A 3252In State-A moving L 3253ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3254predict error 0 3255dir: dir isU 3256-/443: O: O886 (predict-no) 3257I see 1 and I'm going to do: predict-no 3258ENV: Agent did: predict-no for direction U in state State-A 3259In State-A moving U 3260ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3261predict error 0 3262dir: dir isU 3263|\444: O: O888 (predict-no) 3264I see 1 and I'm going to do: predict-no 3265ENV: Agent did: predict-no for direction U in state State-A 3266In State-A moving U 3267ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3268predict error 0 3269dir: dir isR 3270-/|445: O: O890 (predict-no) 3271I see 1 and I'm going to do: predict-no 3272ENV: Agent did: predict-no for direction R in state State-A 3273In State-A moving R 3274ENV: (next state, see, prediction correct?) = (State-B, 1, False) 3275predict error 1 3276dir: dir isU 3277\-/446: O: O892 (predict-no) 3278I see 0 and I'm going to do: predict-no 3279ENV: Agent did: predict-no for direction U in state State-B 3280In State-B moving U 3281ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3282predict error 0 3283dir: dir isR 3284|\-447: O: O894 (predict-no) 3285I see 1 and I'm going to do: predict-no 3286ENV: Agent did: predict-no for direction R in state State-B 3287In State-B moving R 3288ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3289predict error 0 3290dir: dir isU 3291/|448: O: O895 (predict-yes) 3292I see 1 and I'm going to do: predict-yes 3293ENV: Agent did: predict-yes for direction U in state State-B 3294In State-B moving U 3295ENV: (next state, see, prediction correct?) = (State-B, 0, False) 3296predict error 1 3297dir: dir isU 3298\-449: O: O898 (predict-no) 3299I see 0 and I'm going to do: predict-no 3300ENV: Agent did: predict-no for direction U in state State-B 3301In State-B moving U 3302ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3303predict error 0 3304dir: dir isR 3305/|450: O: O900 (predict-no) 3306I see 1 and I'm going to do: predict-no 3307ENV: Agent did: predict-no for direction R in state State-B 3308In State-B moving R 3309ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3310predict error 0 3311dir: dir isU 3312\-/|451: O: O902 (predict-no) 3313I see 1 and I'm going to do: predict-no 3314ENV: Agent did: predict-no for direction U in state State-B 3315In State-B moving U 3316ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3317predict error 0 3318dir: dir isR 3319\452: O: O904 (predict-no) 3320I see 1 and I'm going to do: predict-no 3321ENV: Agent did: predict-no for direction R in state State-B 3322In State-B moving R 3323ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3324predict error 0 3325dir: dir isL 3326-/|453: O: O905 (predict-yes) 3327I see 1 and I'm going to do: predict-yes 3328ENV: Agent did: predict-yes for direction L in state State-B 3329In State-B moving L 3330ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3331predict error 0 3332dir: dir isL 3333\-/454: O: O908 (predict-no) 3334I see 1 and I'm going to do: predict-no 3335ENV: Agent did: predict-no for direction L in state State-A 3336In State-A moving L 3337ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3338predict error 0 3339dir: dir isL 3340|\-455: O: O909 (predict-yes) 3341I see 1 and I'm going to do: predict-yes 3342ENV: Agent did: predict-yes for direction L in state State-A 3343In State-A moving L 3344ENV: (next state, see, prediction correct?) = (State-A, 0, False) 3345predict error 1 3346dir: dir isU 3347/|456: O: O912 (predict-no) 3348I see 0 and I'm going to do: predict-no 3349ENV: Agent did: predict-no for direction U in state State-A 3350In State-A moving U 3351ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3352predict error 0 3353dir: dir isU 3354\-457: O: O914 (predict-no) 3355I see 1 and I'm going to do: predict-no 3356ENV: Agent did: predict-no for direction U in state State-A 3357In State-A moving U 3358ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3359predict error 0 3360dir: dir isL 3361/|\458: O: O916 (predict-no) 3362I see 1 and I'm going to do: predict-no 3363ENV: Agent did: predict-no for direction L in state State-A 3364In State-A moving L 3365ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3366predict error 0 3367dir: dir isR 3368-/|459: O: O917 (predict-yes) 3369I see 1 and I'm going to do: predict-yes 3370ENV: Agent did: predict-yes for direction R in state State-A 3371In State-A moving R 3372ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3373predict error 0 3374dir: dir isR 3375\-/460: O: O920 (predict-no) 3376I see 1 and I'm going to do: predict-no 3377ENV: Agent did: predict-no for direction R in state State-B 3378In State-B moving R 3379ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3380predict error 0 3381dir: dir isL 3382|\-461: O: O921 (predict-yes) 3383I see 1 and I'm going to do: predict-yes 3384ENV: Agent did: predict-yes for direction L in state State-B 3385In State-B moving L 3386ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3387predict error 0 3388dir: dir isL 3389/462: O: O924 (predict-no) 3390I see 1 and I'm going to do: predict-no 3391ENV: Agent did: predict-no for direction L in state State-A 3392In State-A moving L 3393ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3394predict error 0 3395dir: dir isL 3396|\-463: O: O926 (predict-no) 3397I see 1 and I'm going to do: predict-no 3398ENV: Agent did: predict-no for direction L in state State-A 3399In State-A moving L 3400ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3401predict error 0 3402dir: dir isU 3403/|\464: O: O928 (predict-no) 3404I see 1 and I'm going to do: predict-no 3405ENV: Agent did: predict-no for direction U in state State-A 3406In State-A moving U 3407ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3408predict error 0 3409dir: dir isL 3410-/|465: O: O930 (predict-no) 3411I see 1 and I'm going to do: predict-no 3412ENV: Agent did: predict-no for direction L in state State-A 3413In State-A moving L 3414ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3415predict error 0 3416dir: dir isL 3417\-/466: O: O932 (predict-no) 3418I see 1 and I'm going to do: predict-no 3419ENV: Agent did: predict-no for direction L in state State-A 3420In State-A moving L 3421ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3422predict error 0 3423dir: dir isR 3424|\-467: O: O933 (predict-yes) 3425I see 1 and I'm going to do: predict-yes 3426ENV: Agent did: predict-yes for direction R in state State-A 3427In State-A moving R 3428ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3429predict error 0 3430dir: dir isL 3431/|468: O: O935 (predict-yes) 3432I see 1 and I'm going to do: predict-yes 3433ENV: Agent did: predict-yes for direction L in state State-B 3434In State-B moving L 3435ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3436predict error 0 3437dir: dir isR 3438\469: O: O938 (predict-no) 3439I see 1 and I'm going to do: predict-no 3440ENV: Agent did: predict-no for direction R in state State-A 3441In State-A moving R 3442ENV: (next state, see, prediction correct?) = (State-B, 1, False) 3443predict error 1 3444dir: dir isR 3445-/470: O: O940 (predict-no) 3446I see 0 and I'm going to do: predict-no 3447ENV: Agent did: predict-no for direction R in state State-B 3448In State-B moving R 3449ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3450predict error 0 3451dir: dir isU 3452|\-471: O: O942 (predict-no) 3453I see 1 and I'm going to do: predict-no 3454ENV: Agent did: predict-no for direction U in state State-B 3455In State-B moving U 3456ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3457predict error 0 3458dir: dir isL 3459/472: O: O943 (predict-yes) 3460I see 1 and I'm going to do: predict-yes 3461ENV: Agent did: predict-yes for direction L in state State-B 3462In State-B moving L 3463ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3464predict error 0 3465dir: dir isL 3466|\473: O: O945 (predict-yes) 3467I see 1 and I'm going to do: predict-yes 3468ENV: Agent did: predict-yes for direction L in state State-A 3469In State-A moving L 3470ENV: (next state, see, prediction correct?) = (State-A, 0, False) 3471predict error 1 3472dir: dir isR 3473-/|474: O: O947 (predict-yes) 3474I see 0 and I'm going to do: predict-yes 3475ENV: Agent did: predict-yes for direction R in state State-A 3476In State-A moving R 3477ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3478predict error 0 3479dir: dir isL 3480\-/475: O: O949 (predict-yes) 3481I see 1 and I'm going to do: predict-yes 3482ENV: Agent did: predict-yes for direction L in state State-B 3483In State-B moving L 3484ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3485predict error 0 3486dir: dir isR 3487|\-476: O: O952 (predict-no) 3488I see 1 and I'm going to do: predict-no 3489ENV: Agent did: predict-no for direction R in state State-A 3490In State-A moving R 3491ENV: (next state, see, prediction correct?) = (State-B, 1, False) 3492predict error 1 3493dir: dir isL 3494/|\477: O: O953 (predict-yes) 3495I see 0 and I'm going to do: predict-yes 3496ENV: Agent did: predict-yes for direction L in state State-B 3497In State-B moving L 3498ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3499predict error 0 3500dir: dir isU 3501-/|478: O: O956 (predict-no) 3502I see 1 and I'm going to do: predict-no 3503ENV: Agent did: predict-no for direction U in state State-A 3504In State-A moving U 3505ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3506predict error 0 3507dir: dir isU 3508\-/479: O: O958 (predict-no) 3509I see 1 and I'm going to do: predict-no 3510ENV: Agent did: predict-no for direction U in state State-A 3511In State-A moving U 3512ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3513predict error 0 3514dir: dir isU 3515|\480: O: O960 (predict-no) 3516I see 1 and I'm going to do: predict-no 3517ENV: Agent did: predict-no for direction U in state State-A 3518In State-A moving U 3519ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3520predict error 0 3521dir: dir isU 3522-/|481: O: O962 (predict-no) 3523I see 1 and I'm going to do: predict-no 3524ENV: Agent did: predict-no for direction U in state State-A 3525In State-A moving U 3526ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3527predict error 0 3528dir: dir isR 3529\482: O: O963 (predict-yes) 3530I see 1 and I'm going to do: predict-yes 3531ENV: Agent did: predict-yes for direction R in state State-A 3532In State-A moving R 3533ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3534predict error 0 3535dir: dir isR 3536-/|483: O: O966 (predict-no) 3537I see 1 and I'm going to do: predict-no 3538ENV: Agent did: predict-no for direction R in state State-B 3539In State-B moving R 3540ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3541predict error 0 3542dir: dir isU 3543\-/484: O: O968 (predict-no) 3544I see 1 and I'm going to do: predict-no 3545ENV: Agent did: predict-no for direction U in state State-B 3546In State-B moving U 3547ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3548predict error 0 3549dir: dir isU 3550|\-485: O: O970 (predict-no) 3551I see 1 and I'm going to do: predict-no 3552ENV: Agent did: predict-no for direction U in state State-B 3553In State-B moving U 3554ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3555predict error 0 3556dir: dir isR 3557/|\486: O: O972 (predict-no) 3558I see 1 and I'm going to do: predict-no 3559ENV: Agent did: predict-no for direction R in state State-B 3560In State-B moving R 3561ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3562predict error 0 3563dir: dir isR 3564-/|\sleeping... 3565-487: O: O974 (predict-no) 3566I see 1 and I'm going to do: predict-no 3567ENV: Agent did: predict-no for direction R in state State-B 3568In State-B moving R 3569ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3570predict error 0 3571dir: dir isL 3572/|488: O: O975 (predict-yes) 3573I see 1 and I'm going to do: predict-yes 3574ENV: Agent did: predict-yes for direction L in state State-B 3575In State-B moving L 3576ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3577predict error 0 3578dir: dir isL 3579\-489: O: O978 (predict-no) 3580I see 1 and I'm going to do: predict-no 3581ENV: Agent did: predict-no for direction L in state State-A 3582In State-A moving L 3583ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3584predict error 0 3585dir: dir isU 3586/|490: O: O980 (predict-no) 3587I see 1 and I'm going to do: predict-no 3588ENV: Agent did: predict-no for direction U in state State-A 3589In State-A moving U 3590ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3591predict error 0 3592dir: dir isL 3593\-/491: O: O982 (predict-no) 3594I see 1 and I'm going to do: predict-no 3595ENV: Agent did: predict-no for direction L in state State-A 3596In State-A moving L 3597ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3598predict error 0 3599dir: dir isU 3600|492: O: O984 (predict-no) 3601I see 1 and I'm going to do: predict-no 3602ENV: Agent did: predict-no for direction U in state State-A 3603In State-A moving U 3604ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3605predict error 0 3606dir: dir isR 3607\-/493: O: O985 (predict-yes) 3608I see 1 and I'm going to do: predict-yes 3609ENV: Agent did: predict-yes for direction R in state State-A 3610In State-A moving R 3611ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3612predict error 0 3613dir: dir isU 3614|\494: O: O988 (predict-no) 3615I see 1 and I'm going to do: predict-no 3616ENV: Agent did: predict-no for direction U in state State-B 3617In State-B moving U 3618ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3619predict error 0 3620dir: dir isU 3621-/|495: O: O990 (predict-no) 3622I see 1 and I'm going to do: predict-no 3623ENV: Agent did: predict-no for direction U in state State-B 3624In State-B moving U 3625ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3626predict error 0 3627dir: dir isU 3628\-/496: O: O992 (predict-no) 3629I see 1 and I'm going to do: predict-no 3630ENV: Agent did: predict-no for direction U in state State-B 3631In State-B moving U 3632ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3633predict error 0 3634dir: dir isL 3635|\-497: O: O993 (predict-yes) 3636I see 1 and I'm going to do: predict-yes 3637ENV: Agent did: predict-yes for direction L in state State-B 3638In State-B moving L 3639ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3640predict error 0 3641dir: dir isR 3642/|498: O: O995 (predict-yes) 3643I see 1 and I'm going to do: predict-yes 3644ENV: Agent did: predict-yes for direction R in state State-A 3645In State-A moving R 3646ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3647predict error 0 3648dir: dir isR 3649\-/499: O: O998 (predict-no) 3650I see 1 and I'm going to do: predict-no 3651ENV: Agent did: predict-no for direction R in state State-B 3652In State-B moving R 3653ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3654predict error 0 3655dir: dir isL 3656|\-500: O: O999 (predict-yes) 3657I see 1 and I'm going to do: predict-yes 3658ENV: Agent did: predict-yes for direction L in state State-B 3659In State-B moving L 3660ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3661predict error 0 3662dir: dir isR 3663/|\-/501: O: O1001 (predict-yes) 3664I see 1 and I'm going to do: predict-yes 3665ENV: Agent did: predict-yes for direction R in state State-A 3666In State-A moving R 3667ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3668predict error 0 3669dir: dir isR 3670|502: O: O1004 (predict-no) 3671I see 1 and I'm going to do: predict-no 3672ENV: Agent did: predict-no for direction R in state State-B 3673In State-B moving R 3674ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3675predict error 0 3676dir: dir isR 3677\-/503: O: O1006 (predict-no) 3678I see 1 and I'm going to do: predict-no 3679ENV: Agent did: predict-no for direction R in state State-B 3680In State-B moving R 3681ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3682predict error 0 3683dir: dir isL 3684|\504: O: O1007 (predict-yes) 3685I see 1 and I'm going to do: predict-yes 3686ENV: Agent did: predict-yes for direction L in state State-B 3687In State-B moving L 3688ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3689predict error 0 3690dir: dir isR 3691-505: O: O1009 (predict-yes) 3692I see 1 and I'm going to do: predict-yes 3693ENV: Agent did: predict-yes for direction R in state State-A 3694In State-A moving R 3695ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3696predict error 0 3697dir: dir isR 3698/|\506: O: O1012 (predict-no) 3699I see 1 and I'm going to do: predict-no 3700ENV: Agent did: predict-no for direction R in state State-B 3701In State-B moving R 3702ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3703predict error 0 3704dir: dir isL 3705-/507: O: O1013 (predict-yes) 3706I see 1 and I'm going to do: predict-yes 3707ENV: Agent did: predict-yes for direction L in state State-B 3708In State-B moving L 3709ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3710predict error 0 3711dir: dir isR 3712|\508: O: O1015 (predict-yes) 3713I see 1 and I'm going to do: predict-yes 3714ENV: Agent did: predict-yes for direction R in state State-A 3715In State-A moving R 3716ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3717predict error 0 3718dir: dir isU 3719-/|509: O: O1018 (predict-no) 3720I see 1 and I'm going to do: predict-no 3721ENV: Agent did: predict-no for direction U in state State-B 3722In State-B moving U 3723ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3724predict error 0 3725dir: dir isU 3726\-/510: O: O1020 (predict-no) 3727I see 1 and I'm going to do: predict-no 3728ENV: Agent did: predict-no for direction U in state State-B 3729In State-B moving U 3730ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3731predict error 0 3732dir: dir isR 3733|\-511: O: O1022 (predict-no) 3734I see 1 and I'm going to do: predict-no 3735ENV: Agent did: predict-no for direction R in state State-B 3736In State-B moving R 3737ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3738predict error 0 3739dir: dir isR 3740/512: O: O1023 (predict-yes) 3741I see 1 and I'm going to do: predict-yes 3742ENV: Agent did: predict-yes for direction R in state State-B 3743In State-B moving R 3744ENV: (next state, see, prediction correct?) = (State-B, 0, False) 3745predict error 1 3746dir: dir isR 3747|\513: O: O1026 (predict-no) 3748I see 0 and I'm going to do: predict-no 3749ENV: Agent did: predict-no for direction R in state State-B 3750In State-B moving R 3751ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3752predict error 0 3753dir: dir isL 3754-514: O: O1027 (predict-yes) 3755I see 1 and I'm going to do: predict-yes 3756ENV: Agent did: predict-yes for direction L in state State-B 3757In State-B moving L 3758ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3759predict error 0 3760dir: dir isL 3761/|\515: O: O1030 (predict-no) 3762I see 1 and I'm going to do: predict-no 3763ENV: Agent did: predict-no for direction L in state State-A 3764In State-A moving L 3765ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3766predict error 0 3767dir: dir isL 3768-/|516: O: O1032 (predict-no) 3769I see 1 and I'm going to do: predict-no 3770ENV: Agent did: predict-no for direction L in state State-A 3771In State-A moving L 3772ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3773predict error 0 3774dir: dir isR 3775\-517: O: O1034 (predict-no) 3776I see 1 and I'm going to do: predict-no 3777ENV: Agent did: predict-no for direction R in state State-A 3778In State-A moving R 3779ENV: (next state, see, prediction correct?) = (State-B, 1, False) 3780predict error 1 3781dir: dir isU 3782/|\518: O: O1036 (predict-no) 3783I see 0 and I'm going to do: predict-no 3784ENV: Agent did: predict-no for direction U in state State-B 3785In State-B moving U 3786ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3787predict error 0 3788dir: dir isU 3789-/519: O: O1038 (predict-no) 3790I see 1 and I'm going to do: predict-no 3791ENV: Agent did: predict-no for direction U in state State-B 3792In State-B moving U 3793ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3794predict error 0 3795dir: dir isR 3796|\-520: O: O1040 (predict-no) 3797I see 1 and I'm going to do: predict-no 3798ENV: Agent did: predict-no for direction R in state State-B 3799In State-B moving R 3800ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3801predict error 0 3802dir: dir isU 3803/|\521: O: O1042 (predict-no) 3804I see 1 and I'm going to do: predict-no 3805ENV: Agent did: predict-no for direction U in state State-B 3806In State-B moving U 3807ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3808predict error 0 3809dir: dir isR 3810-522: O: O1044 (predict-no) 3811I see 1 and I'm going to do: predict-no 3812ENV: Agent did: predict-no for direction R in state State-B 3813In State-B moving R 3814ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3815predict error 0 3816dir: dir isU 3817/|\523: O: O1046 (predict-no) 3818I see 1 and I'm going to do: predict-no 3819ENV: Agent did: predict-no for direction U in state State-B 3820In State-B moving U 3821ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3822predict error 0 3823dir: dir isR 3824-/|524: O: O1048 (predict-no) 3825I see 1 and I'm going to do: predict-no 3826ENV: Agent did: predict-no for direction R in state State-B 3827In State-B moving R 3828ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3829predict error 0 3830dir: dir isU 3831\-/525: O: O1050 (predict-no) 3832I see 1 and I'm going to do: predict-no 3833ENV: Agent did: predict-no for direction U in state State-B 3834In State-B moving U 3835ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3836predict error 0 3837dir: dir isU 3838|\-526: O: O1052 (predict-no) 3839I see 1 and I'm going to do: predict-no 3840ENV: Agent did: predict-no for direction U in state State-B 3841In State-B moving U 3842ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3843predict error 0 3844dir: dir isL 3845/|\527: O: O1053 (predict-yes) 3846I see 1 and I'm going to do: predict-yes 3847ENV: Agent did: predict-yes for direction L in state State-B 3848In State-B moving L 3849ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3850predict error 0 3851dir: dir isL 3852-/528: O: O1056 (predict-no) 3853I see 1 and I'm going to do: predict-no 3854ENV: Agent did: predict-no for direction L in state State-A 3855In State-A moving L 3856ENV: (next state, see, prediction correct?) = (State-A, 0, True) 3857predict error 0 3858dir: dir isR 3859|\-529: O: O1057 (predict-yes) 3860I see 1 and I'm going to do: predict-yes 3861ENV: Agent did: predict-yes for direction R in state State-A 3862In State-A moving R 3863ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3864predict error 0 3865dir: dir isR 3866/|\530: O: O1060 (predict-no) 3867I see 1 and I'm going to do: predict-no 3868ENV: Agent did: predict-no for direction R in state State-B 3869In State-B moving R 3870ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3871predict error 0 3872dir: dir isR 3873-/|531: O: O1062 (predict-no) 3874I see 1 and I'm going to do: predict-no 3875ENV: Agent did: predict-no for direction R in state State-B 3876In State-B moving R 3877ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3878predict error 0 3879dir: dir isL 3880\532: O: O1063 (predict-yes) 3881I see 1 and I'm going to do: predict-yes 3882ENV: Agent did: predict-yes for direction L in state State-B 3883In State-B moving L 3884ENV: (next state, see, prediction correct?) = (State-A, 1, True) 3885predict error 0 3886dir: dir isR 3887-/533: O: O1065 (predict-yes) 3888I see 1 and I'm going to do: predict-yes 3889ENV: Agent did: predict-yes for direction R in state State-A 3890In State-A moving R 3891ENV: (next state, see, prediction correct?) = (State-B, 1, True) 3892predict error 0 3893dir: dir isR 3894|\-534: O: O1068 (predict-no) 3895I see 1 and I'm going to do: predict-no 3896ENV: Agent did: predict-no for direction R in state State-B 3897In State-B moving R 3898ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3899predict error 0 3900dir: dir isR 3901/|\535: O: O1070 (predict-no) 3902I see 1 and I'm going to do: predict-no 3903ENV: Agent did: predict-no for direction R in state State-B 3904In State-B moving R 3905ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3906predict error 0 3907dir: dir isU 3908-/|536: O: O1072 (predict-no) 3909I see 1 and I'm going to do: predict-no 3910ENV: Agent did: predict-no for direction U in state State-B 3911In State-B moving U 3912ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3913predict error 0 3914dir: dir isR 3915\-537: O: O1074 (predict-no) 3916I see 1 and I'm going to do: predict-no 3917ENV: Agent did: predict-no for direction R in state State-B 3918In State-B moving R 3919ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3920predict error 0 3921dir: dir isU 3922/|\538: O: O1076 (predict-no) 3923I see 1 and I'm going to do: predict-no 3924ENV: Agent did: predict-no for direction U in state State-B 3925In State-B moving U 3926ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3927predict error 0 3928dir: dir isU 3929-/|\539: O: O1078 (predict-no) 3930I see 1 and I'm going to do: predict-no 3931ENV: Agent did: predict-no for direction U in state State-B 3932In State-B moving U 3933ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3934predict error 0 3935dir: dir isU 3936-/|540: O: O1080 (predict-no) 3937I see 1 and I'm going to do: predict-no 3938ENV: Agent did: predict-no for direction U in state State-B 3939In State-B moving U 3940ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3941predict error 0 3942dir: dir isR 3943\-541: O: O1082 (predict-no) 3944I see 1 and I'm going to do: predict-no 3945ENV: Agent did: predict-no for direction R in state State-B 3946In State-B moving R 3947ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3948predict error 0 3949dir: dir isU 3950/542: O: O1083 (predict-yes) 3951I see 1 and I'm going to do: predict-yes 3952ENV: Agent did: predict-yes for direction U in state State-B 3953In State-B moving U 3954ENV: (next state, see, prediction correct?) = (State-B, 0, False) 3955predict error 1 3956dir: dir isR 3957|\-/543: O: O1086 (predict-no) 3958I see 0 and I'm going to do: predict-no 3959ENV: Agent did: predict-no for direction R in state State-B 3960In State-B moving R 3961ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3962predict error 0 3963dir: dir isR 3964|\-544: O: O1088 (predict-no) 3965I see 1 and I'm going to do: predict-no 3966ENV: Agent did: predict-no for direction R in state State-B 3967In State-B moving R 3968ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3969predict error 0 3970dir: dir isR 3971/|545: O: O1090 (predict-no) 3972I see 1 and I'm going to do: predict-no 3973ENV: Agent did: predict-no for direction R in state State-B 3974In State-B moving R 3975ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3976predict error 0 3977dir: dir isR 3978\-/546: O: O1092 (predict-no) 3979I see 1 and I'm going to do: predict-no 3980ENV: Agent did: predict-no for direction R in state State-B 3981In State-B moving R 3982ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3983predict error 0 3984dir: dir isR 3985|\547: O: O1094 (predict-no) 3986I see 1 and I'm going to do: predict-no 3987ENV: Agent did: predict-no for direction R in state State-B 3988In State-B moving R 3989ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3990predict error 0 3991dir: dir isR 3992-/|548: O: O1096 (predict-no) 3993I see 1 and I'm going to do: predict-no 3994ENV: Agent did: predict-no for direction R in state State-B 3995In State-B moving R 3996ENV: (next state, see, prediction correct?) = (State-B, 0, True) 3997predict error 0 3998dir: dir isU 3999\-/549: O: O1098 (predict-no) 4000I see 1 and I'm going to do: predict-no 4001ENV: Agent did: predict-no for direction U in state State-B 4002In State-B moving U 4003ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4004predict error 0 4005dir: dir isU 4006|\550: O: O1099 (predict-yes) 4007I see 1 and I'm going to do: predict-yes 4008ENV: Agent did: predict-yes for direction U in state State-B 4009In State-B moving U 4010ENV: (next state, see, prediction correct?) = (State-B, 0, False) 4011predict error 1 4012dir: dir isU 4013-/|551: O: O1102 (predict-no) 4014I see 0 and I'm going to do: predict-no 4015ENV: Agent did: predict-no for direction U in state State-B 4016In State-B moving U 4017ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4018predict error 0 4019dir: dir isU 4020\552: O: O1104 (predict-no) 4021I see 1 and I'm going to do: predict-no 4022ENV: Agent did: predict-no for direction U in state State-B 4023In State-B moving U 4024ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4025predict error 0 4026dir: dir isU 4027-/|553: O: O1105 (predict-yes) 4028I see 1 and I'm going to do: predict-yes 4029ENV: Agent did: predict-yes for direction U in state State-B 4030In State-B moving U 4031ENV: (next state, see, prediction correct?) = (State-B, 0, False) 4032predict error 1 4033dir: dir isR 4034\-/554: O: O1108 (predict-no) 4035I see 0 and I'm going to do: predict-no 4036ENV: Agent did: predict-no for direction R in state State-B 4037In State-B moving R 4038ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4039predict error 0 4040dir: dir isR 4041|\-555: O: O1110 (predict-no) 4042I see 1 and I'm going to do: predict-no 4043ENV: Agent did: predict-no for direction R in state State-B 4044In State-B moving R 4045ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4046predict error 0 4047dir: dir isL 4048/|\556: O: O1111 (predict-yes) 4049I see 1 and I'm going to do: predict-yes 4050ENV: Agent did: predict-yes for direction L in state State-B 4051In State-B moving L 4052ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4053predict error 0 4054dir: dir isU 4055-/557: O: O1114 (predict-no) 4056I see 1 and I'm going to do: predict-no 4057ENV: Agent did: predict-no for direction U in state State-A 4058In State-A moving U 4059ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4060predict error 0 4061dir: dir isU 4062|\-558: O: O1116 (predict-no) 4063I see 1 and I'm going to do: predict-no 4064ENV: Agent did: predict-no for direction U in state State-A 4065In State-A moving U 4066ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4067predict error 0 4068dir: dir isR 4069/|\559: O: O1117 (predict-yes) 4070I see 1 and I'm going to do: predict-yes 4071ENV: Agent did: predict-yes for direction R in state State-A 4072In State-A moving R 4073ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4074predict error 0 4075dir: dir isL 4076-/|560: O: O1119 (predict-yes) 4077I see 1 and I'm going to do: predict-yes 4078ENV: Agent did: predict-yes for direction L in state State-B 4079In State-B moving L 4080ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4081predict error 0 4082dir: dir isU 4083\-/561: O: O1122 (predict-no) 4084I see 1 and I'm going to do: predict-no 4085ENV: Agent did: predict-no for direction U in state State-A 4086In State-A moving U 4087ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4088predict error 0 4089dir: dir isR 4090|562: O: O1124 (predict-no) 4091I see 1 and I'm going to do: predict-no 4092ENV: Agent did: predict-no for direction R in state State-A 4093In State-A moving R 4094ENV: (next state, see, prediction correct?) = (State-B, 1, False) 4095predict error 1 4096dir: dir isR 4097\-/563: O: O1126 (predict-no) 4098I see 0 and I'm going to do: predict-no 4099ENV: Agent did: predict-no for direction R in state State-B 4100In State-B moving R 4101ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4102predict error 0 4103dir: dir isL 4104|\-564: O: O1127 (predict-yes) 4105I see 1 and I'm going to do: predict-yes 4106ENV: Agent did: predict-yes for direction L in state State-B 4107In State-B moving L 4108ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4109predict error 0 4110dir: dir isR 4111/|\565: O: O1129 (predict-yes) 4112I see 1 and I'm going to do: predict-yes 4113ENV: Agent did: predict-yes for direction R in state State-A 4114In State-A moving R 4115ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4116predict error 0 4117dir: dir isU 4118-/566: O: O1132 (predict-no) 4119I see 1 and I'm going to do: predict-no 4120ENV: Agent did: predict-no for direction U in state State-B 4121In State-B moving U 4122ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4123predict error 0 4124dir: dir isR 4125|\-567: O: O1134 (predict-no) 4126I see 1 and I'm going to do: predict-no 4127ENV: Agent did: predict-no for direction R in state State-B 4128In State-B moving R 4129ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4130predict error 0 4131dir: dir isR 4132/|\568: O: O1136 (predict-no) 4133I see 1 and I'm going to do: predict-no 4134ENV: Agent did: predict-no for direction R in state State-B 4135In State-B moving R 4136ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4137predict error 0 4138dir: dir isR 4139-569: O: O1138 (predict-no) 4140I see 1 and I'm going to do: predict-no 4141ENV: Agent did: predict-no for direction R in state State-B 4142In State-B moving R 4143ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4144predict error 0 4145dir: dir isL 4146/|\570: O: O1139 (predict-yes) 4147I see 1 and I'm going to do: predict-yes 4148ENV: Agent did: predict-yes for direction L in state State-B 4149In State-B moving L 4150ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4151predict error 0 4152dir: dir isR 4153-/571: O: O1141 (predict-yes) 4154I see 1 and I'm going to do: predict-yes 4155ENV: Agent did: predict-yes for direction R in state State-A 4156In State-A moving R 4157ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4158predict error 0 4159dir: dir isU 4160|572: O: O1144 (predict-no) 4161I see 1 and I'm going to do: predict-no 4162ENV: Agent did: predict-no for direction U in state State-B 4163In State-B moving U 4164ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4165predict error 0 4166dir: dir isU 4167\-/573: O: O1146 (predict-no) 4168I see 1 and I'm going to do: predict-no 4169ENV: Agent did: predict-no for direction U in state State-B 4170In State-B moving U 4171ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4172predict error 0 4173dir: dir isR 4174|\-574: O: O1148 (predict-no) 4175I see 1 and I'm going to do: predict-no 4176ENV: Agent did: predict-no for direction R in state State-B 4177In State-B moving R 4178ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4179predict error 0 4180dir: dir isU 4181/|\575: O: O1150 (predict-no) 4182I see 1 and I'm going to do: predict-no 4183ENV: Agent did: predict-no for direction U in state State-B 4184In State-B moving U 4185ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4186predict error 0 4187dir: dir isR 4188-/|576: O: O1152 (predict-no) 4189I see 1 and I'm going to do: predict-no 4190ENV: Agent did: predict-no for direction R in state State-B 4191In State-B moving R 4192ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4193predict error 0 4194dir: dir isL 4195\-/577: O: O1153 (predict-yes) 4196I see 1 and I'm going to do: predict-yes 4197ENV: Agent did: predict-yes for direction L in state State-B 4198In State-B moving L 4199ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4200predict error 0 4201dir: dir isL 4202|\-578: O: O1156 (predict-no) 4203I see 1 and I'm going to do: predict-no 4204ENV: Agent did: predict-no for direction L in state State-A 4205In State-A moving L 4206ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4207predict error 0 4208dir: dir isU 4209/|\579: O: O1158 (predict-no) 4210I see 1 and I'm going to do: predict-no 4211ENV: Agent did: predict-no for direction U in state State-A 4212In State-A moving U 4213ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4214predict error 0 4215dir: dir isL 4216-/|580: O: O1160 (predict-no) 4217I see 1 and I'm going to do: predict-no 4218ENV: Agent did: predict-no for direction L in state State-A 4219In State-A moving L 4220ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4221predict error 0 4222dir: dir isL 4223\-/|581: O: O1162 (predict-no) 4224I see 1 and I'm going to do: predict-no 4225ENV: Agent did: predict-no for direction L in state State-A 4226In State-A moving L 4227ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4228predict error 0 4229dir: dir isU 4230\582: O: O1164 (predict-no) 4231I see 1 and I'm going to do: predict-no 4232ENV: Agent did: predict-no for direction U in state State-A 4233In State-A moving U 4234ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4235predict error 0 4236dir: dir isR 4237-/583: O: O1165 (predict-yes) 4238I see 1 and I'm going to do: predict-yes 4239ENV: Agent did: predict-yes for direction R in state State-A 4240In State-A moving R 4241ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4242predict error 0 4243dir: dir isR 4244|\-584: O: O1168 (predict-no) 4245I see 1 and I'm going to do: predict-no 4246ENV: Agent did: predict-no for direction R in state State-B 4247In State-B moving R 4248ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4249predict error 0 4250dir: dir isR 4251/|585: O: O1170 (predict-no) 4252I see 1 and I'm going to do: predict-no 4253ENV: Agent did: predict-no for direction R in state State-B 4254In State-B moving R 4255ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4256predict error 0 4257dir: dir isU 4258\-586: O: O1172 (predict-no) 4259I see 1 and I'm going to do: predict-no 4260ENV: Agent did: predict-no for direction U in state State-B 4261In State-B moving U 4262ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4263predict error 0 4264dir: dir isL 4265/587: O: O1173 (predict-yes) 4266I see 1 and I'm going to do: predict-yes 4267ENV: Agent did: predict-yes for direction L in state State-B 4268In State-B moving L 4269ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4270predict error 0 4271dir: dir isR 4272|588: O: O1175 (predict-yes) 4273I see 1 and I'm going to do: predict-yes 4274ENV: Agent did: predict-yes for direction R in state State-A 4275In State-A moving R 4276ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4277predict error 0 4278dir: dir isU 4279\-/589: O: O1178 (predict-no) 4280I see 1 and I'm going to do: predict-no 4281ENV: Agent did: predict-no for direction U in state State-B 4282In State-B moving U 4283ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4284predict error 0 4285dir: dir isU 4286|\-590: O: O1180 (predict-no) 4287I see 1 and I'm going to do: predict-no 4288ENV: Agent did: predict-no for direction U in state State-B 4289In State-B moving U 4290ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4291predict error 0 4292dir: dir isL 4293/|\591: O: O1181 (predict-yes) 4294I see 1 and I'm going to do: predict-yes 4295ENV: Agent did: predict-yes for direction L in state State-B 4296In State-B moving L 4297ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4298predict error 0 4299dir: dir isR 4300-592: O: O1183 (predict-yes) 4301I see 1 and I'm going to do: predict-yes 4302ENV: Agent did: predict-yes for direction R in state State-A 4303In State-A moving R 4304ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4305predict error 0 4306dir: dir isL 4307/|\593: O: O1185 (predict-yes) 4308I see 1 and I'm going to do: predict-yes 4309ENV: Agent did: predict-yes for direction L in state State-B 4310In State-B moving L 4311ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4312predict error 0 4313dir: dir isR 4314-/|594: O: O1187 (predict-yes) 4315I see 1 and I'm going to do: predict-yes 4316ENV: Agent did: predict-yes for direction R in state State-A 4317In State-A moving R 4318ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4319predict error 0 4320dir: dir isL 4321\-/595: O: O1189 (predict-yes) 4322I see 1 and I'm going to do: predict-yes 4323ENV: Agent did: predict-yes for direction L in state State-B 4324In State-B moving L 4325ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4326predict error 0 4327dir: dir isU 4328|\-596: O: O1192 (predict-no) 4329I see 1 and I'm going to do: predict-no 4330ENV: Agent did: predict-no for direction U in state State-A 4331In State-A moving U 4332ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4333predict error 0 4334dir: dir isU 4335/|\597: O: O1194 (predict-no) 4336I see 1 and I'm going to do: predict-no 4337ENV: Agent did: predict-no for direction U in state State-A 4338In State-A moving U 4339ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4340predict error 0 4341dir: dir isL 4342-/598: O: O1196 (predict-no) 4343I see 1 and I'm going to do: predict-no 4344ENV: Agent did: predict-no for direction L in state State-A 4345In State-A moving L 4346ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4347predict error 0 4348dir: dir isL 4349|\599: O: O1198 (predict-no) 4350I see 1 and I'm going to do: predict-no 4351ENV: Agent did: predict-no for direction L in state State-A 4352In State-A moving L 4353ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4354predict error 0 4355dir: dir isU 4356-/|600: O: O1200 (predict-no) 4357I see 1 and I'm going to do: predict-no 4358ENV: Agent did: predict-no for direction U in state State-A 4359In State-A moving U 4360ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4361predict error 0 4362dir: dir isU 4363\-/601: O: O1202 (predict-no) 4364I see 1 and I'm going to do: predict-no 4365ENV: Agent did: predict-no for direction U in state State-A 4366In State-A moving U 4367ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4368predict error 0 4369dir: dir isU 4370|602: O: O1204 (predict-no) 4371I see 1 and I'm going to do: predict-no 4372ENV: Agent did: predict-no for direction U in state State-A 4373In State-A moving U 4374ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4375predict error 0 4376dir: dir isL 4377\-/603: O: O1206 (predict-no) 4378I see 1 and I'm going to do: predict-no 4379ENV: Agent did: predict-no for direction L in state State-A 4380In State-A moving L 4381ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4382predict error 0 4383dir: dir isU 4384|604: O: O1208 (predict-no) 4385I see 1 and I'm going to do: predict-no 4386ENV: Agent did: predict-no for direction U in state State-A 4387In State-A moving U 4388ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4389predict error 0 4390dir: dir isR 4391\-605: O: O1209 (predict-yes) 4392I see 1 and I'm going to do: predict-yes 4393ENV: Agent did: predict-yes for direction R in state State-A 4394In State-A moving R 4395ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4396predict error 0 4397dir: dir isL 4398/606: O: O1211 (predict-yes) 4399I see 1 and I'm going to do: predict-yes 4400ENV: Agent did: predict-yes for direction L in state State-B 4401In State-B moving L 4402ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4403predict error 0 4404dir: dir isR 4405|\-607: O: O1213 (predict-yes) 4406I see 1 and I'm going to do: predict-yes 4407ENV: Agent did: predict-yes for direction R in state State-A 4408In State-A moving R 4409ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4410predict error 0 4411dir: dir isU 4412/|\608: O: O1216 (predict-no) 4413I see 1 and I'm going to do: predict-no 4414ENV: Agent did: predict-no for direction U in state State-B 4415In State-B moving U 4416ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4417predict error 0 4418dir: dir isU 4419-/|609: O: O1218 (predict-no) 4420I see 1 and I'm going to do: predict-no 4421ENV: Agent did: predict-no for direction U in state State-B 4422In State-B moving U 4423ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4424predict error 0 4425dir: dir isL 4426\610: O: O1219 (predict-yes) 4427I see 1 and I'm going to do: predict-yes 4428ENV: Agent did: predict-yes for direction L in state State-B 4429In State-B moving L 4430ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4431predict error 0 4432dir: dir isR 4433-/|611: O: O1221 (predict-yes) 4434I see 1 and I'm going to do: predict-yes 4435ENV: Agent did: predict-yes for direction R in state State-A 4436In State-A moving R 4437ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4438predict error 0 4439dir: dir isL 4440\612: O: O1224 (predict-no) 4441I see 1 and I'm going to do: predict-no 4442ENV: Agent did: predict-no for direction L in state State-B 4443In State-B moving L 4444ENV: (next state, see, prediction correct?) = (State-A, 1, False) 4445predict error 1 4446dir: dir isU 4447-/|613: O: O1226 (predict-no) 4448I see 0 and I'm going to do: predict-no 4449ENV: Agent did: predict-no for direction U in state State-A 4450In State-A moving U 4451ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4452predict error 0 4453dir: dir isR 4454\-/614: O: O1227 (predict-yes) 4455I see 1 and I'm going to do: predict-yes 4456ENV: Agent did: predict-yes for direction R in state State-A 4457In State-A moving R 4458ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4459predict error 0 4460dir: dir isU 4461|\615: O: O1230 (predict-no) 4462I see 1 and I'm going to do: predict-no 4463ENV: Agent did: predict-no for direction U in state State-B 4464In State-B moving U 4465ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4466predict error 0 4467dir: dir isU 4468-/|616: O: O1232 (predict-no) 4469I see 1 and I'm going to do: predict-no 4470ENV: Agent did: predict-no for direction U in state State-B 4471In State-B moving U 4472ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4473predict error 0 4474dir: dir isR 4475\-/617: O: O1233 (predict-yes) 4476I see 1 and I'm going to do: predict-yes 4477ENV: Agent did: predict-yes for direction R in state State-B 4478In State-B moving R 4479ENV: (next state, see, prediction correct?) = (State-B, 0, False) 4480predict error 1 4481dir: dir isL 4482|\-618: O: O1235 (predict-yes) 4483I see 0 and I'm going to do: predict-yes 4484ENV: Agent did: predict-yes for direction L in state State-B 4485In State-B moving L 4486ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4487predict error 0 4488dir: dir isR 4489/|\619: O: O1237 (predict-yes) 4490I see 1 and I'm going to do: predict-yes 4491ENV: Agent did: predict-yes for direction R in state State-A 4492In State-A moving R 4493ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4494predict error 0 4495dir: dir isL 4496-/|620: O: O1239 (predict-yes) 4497I see 1 and I'm going to do: predict-yes 4498ENV: Agent did: predict-yes for direction L in state State-B 4499In State-B moving L 4500ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4501predict error 0 4502dir: dir isL 4503\621: O: O1242 (predict-no) 4504I see 1 and I'm going to do: predict-no 4505ENV: Agent did: predict-no for direction L in state State-A 4506In State-A moving L 4507ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4508predict error 0 4509dir: dir isU 4510-622: O: O1244 (predict-no) 4511I see 1 and I'm going to do: predict-no 4512ENV: Agent did: predict-no for direction U in state State-A 4513In State-A moving U 4514ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4515predict error 0 4516dir: dir isR 4517/|\623: O: O1245 (predict-yes) 4518I see 1 and I'm going to do: predict-yes 4519ENV: Agent did: predict-yes for direction R in state State-A 4520In State-A moving R 4521ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4522predict error 0 4523dir: dir isU 4524-/|624: O: O1248 (predict-no) 4525I see 1 and I'm going to do: predict-no 4526ENV: Agent did: predict-no for direction U in state State-B 4527In State-B moving U 4528ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4529predict error 0 4530dir: dir isL 4531\-/625: O: O1249 (predict-yes) 4532I see 1 and I'm going to do: predict-yes 4533ENV: Agent did: predict-yes for direction L in state State-B 4534In State-B moving L 4535ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4536predict error 0 4537dir: dir isU 4538|626: O: O1252 (predict-no) 4539I see 1 and I'm going to do: predict-no 4540ENV: Agent did: predict-no for direction U in state State-A 4541In State-A moving U 4542ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4543predict error 0 4544dir: dir isU 4545\-627: O: O1254 (predict-no) 4546I see 1 and I'm going to do: predict-no 4547ENV: Agent did: predict-no for direction U in state State-A 4548In State-A moving U 4549ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4550predict error 0 4551dir: dir isL 4552/|\628: O: O1256 (predict-no) 4553I see 1 and I'm going to do: predict-no 4554ENV: Agent did: predict-no for direction L in state State-A 4555In State-A moving L 4556ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4557predict error 0 4558dir: dir isL 4559-/|629: O: O1258 (predict-no) 4560I see 1 and I'm going to do: predict-no 4561ENV: Agent did: predict-no for direction L in state State-A 4562In State-A moving L 4563ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4564predict error 0 4565dir: dir isR 4566\-/630: O: O1259 (predict-yes) 4567I see 1 and I'm going to do: predict-yes 4568ENV: Agent did: predict-yes for direction R in state State-A 4569In State-A moving R 4570ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4571predict error 0 4572dir: dir isR 4573|\631: O: O1262 (predict-no) 4574I see 1 and I'm going to do: predict-no 4575ENV: Agent did: predict-no for direction R in state State-B 4576In State-B moving R 4577ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4578predict error 0 4579dir: dir isL 4580-632: O: O1263 (predict-yes) 4581I see 1 and I'm going to do: predict-yes 4582ENV: Agent did: predict-yes for direction L in state State-B 4583In State-B moving L 4584ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4585predict error 0 4586dir: dir isL 4587/|633: O: O1266 (predict-no) 4588I see 1 and I'm going to do: predict-no 4589ENV: Agent did: predict-no for direction L in state State-A 4590In State-A moving L 4591ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4592predict error 0 4593dir: dir isL 4594\-/634: O: O1268 (predict-no) 4595I see 1 and I'm going to do: predict-no 4596ENV: Agent did: predict-no for direction L in state State-A 4597In State-A moving L 4598ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4599predict error 0 4600dir: dir isR 4601|\-635: O: O1269 (predict-yes) 4602I see 1 and I'm going to do: predict-yes 4603ENV: Agent did: predict-yes for direction R in state State-A 4604In State-A moving R 4605ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4606predict error 0 4607dir: dir isU 4608/|\636: O: O1272 (predict-no) 4609I see 1 and I'm going to do: predict-no 4610ENV: Agent did: predict-no for direction U in state State-B 4611In State-B moving U 4612ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4613predict error 0 4614dir: dir isL 4615-/|637: O: O1273 (predict-yes) 4616I see 1 and I'm going to do: predict-yes 4617ENV: Agent did: predict-yes for direction L in state State-B 4618In State-B moving L 4619ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4620predict error 0 4621dir: dir isL 4622\-/638: O: O1276 (predict-no) 4623I see 1 and I'm going to do: predict-no 4624ENV: Agent did: predict-no for direction L in state State-A 4625In State-A moving L 4626ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4627predict error 0 4628dir: dir isU 4629|\-639: O: O1278 (predict-no) 4630I see 1 and I'm going to do: predict-no 4631ENV: Agent did: predict-no for direction U in state State-A 4632In State-A moving U 4633ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4634predict error 0 4635dir: dir isU 4636/|\640: O: O1280 (predict-no) 4637I see 1 and I'm going to do: predict-no 4638ENV: Agent did: predict-no for direction U in state State-A 4639In State-A moving U 4640ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4641predict error 0 4642dir: dir isU 4643-/|641: O: O1282 (predict-no) 4644I see 1 and I'm going to do: predict-no 4645ENV: Agent did: predict-no for direction U in state State-A 4646In State-A moving U 4647ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4648predict error 0 4649dir: dir isR 4650\642: O: O1283 (predict-yes) 4651I see 1 and I'm going to do: predict-yes 4652ENV: Agent did: predict-yes for direction R in state State-A 4653In State-A moving R 4654ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4655predict error 0 4656dir: dir isR 4657-/643: O: O1286 (predict-no) 4658I see 1 and I'm going to do: predict-no 4659ENV: Agent did: predict-no for direction R in state State-B 4660In State-B moving R 4661ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4662predict error 0 4663dir: dir isU 4664|\644: O: O1288 (predict-no) 4665I see 1 and I'm going to do: predict-no 4666ENV: Agent did: predict-no for direction U in state State-B 4667In State-B moving U 4668ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4669predict error 0 4670dir: dir isL 4671-/645: O: O1289 (predict-yes) 4672I see 1 and I'm going to do: predict-yes 4673ENV: Agent did: predict-yes for direction L in state State-B 4674In State-B moving L 4675ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4676predict error 0 4677dir: dir isU 4678|\-646: O: O1292 (predict-no) 4679I see 1 and I'm going to do: predict-no 4680ENV: Agent did: predict-no for direction U in state State-A 4681In State-A moving U 4682ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4683predict error 0 4684dir: dir isL 4685/647: O: O1294 (predict-no) 4686I see 1 and I'm going to do: predict-no 4687ENV: Agent did: predict-no for direction L in state State-A 4688In State-A moving L 4689ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4690predict error 0 4691dir: dir isR 4692|\648: O: O1295 (predict-yes) 4693I see 1 and I'm going to do: predict-yes 4694ENV: Agent did: predict-yes for direction R in state State-A 4695In State-A moving R 4696ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4697predict error 0 4698dir: dir isR 4699-649: O: O1298 (predict-no) 4700I see 1 and I'm going to do: predict-no 4701ENV: Agent did: predict-no for direction R in state State-B 4702In State-B moving R 4703ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4704predict error 0 4705dir: dir isR 4706/|\650: O: O1300 (predict-no) 4707I see 1 and I'm going to do: predict-no 4708ENV: Agent did: predict-no for direction R in state State-B 4709In State-B moving R 4710ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4711predict error 0 4712dir: dir isL 4713-/|651: O: O1301 (predict-yes) 4714I see 1 and I'm going to do: predict-yes 4715ENV: Agent did: predict-yes for direction L in state State-B 4716In State-B moving L 4717ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4718predict error 0 4719dir: dir isL 4720\652: O: O1304 (predict-no) 4721I see 1 and I'm going to do: predict-no 4722ENV: Agent did: predict-no for direction L in state State-A 4723In State-A moving L 4724ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4725predict error 0 4726dir: dir isU 4727-/|\653: O: O1306 (predict-no) 4728I see 1 and I'm going to do: predict-no 4729ENV: Agent did: predict-no for direction U in state State-A 4730In State-A moving U 4731ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4732predict error 0 4733dir: dir isR 4734-/|654: O: O1308 (predict-no) 4735I see 1 and I'm going to do: predict-no 4736ENV: Agent did: predict-no for direction R in state State-A 4737In State-A moving R 4738ENV: (next state, see, prediction correct?) = (State-B, 1, False) 4739predict error 1 4740dir: dir isR 4741\-/655: O: O1310 (predict-no) 4742I see 0 and I'm going to do: predict-no 4743ENV: Agent did: predict-no for direction R in state State-B 4744In State-B moving R 4745ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4746predict error 0 4747dir: dir isL 4748|\-656: O: O1311 (predict-yes) 4749I see 1 and I'm going to do: predict-yes 4750ENV: Agent did: predict-yes for direction L in state State-B 4751In State-B moving L 4752ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4753predict error 0 4754dir: dir isU 4755/|\657: O: O1314 (predict-no) 4756I see 1 and I'm going to do: predict-no 4757ENV: Agent did: predict-no for direction U in state State-A 4758In State-A moving U 4759ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4760predict error 0 4761dir: dir isL 4762-/658: O: O1316 (predict-no) 4763I see 1 and I'm going to do: predict-no 4764ENV: Agent did: predict-no for direction L in state State-A 4765In State-A moving L 4766ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4767predict error 0 4768dir: dir isR 4769|\-659: O: O1317 (predict-yes) 4770I see 1 and I'm going to do: predict-yes 4771ENV: Agent did: predict-yes for direction R in state State-A 4772In State-A moving R 4773ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4774predict error 0 4775dir: dir isU 4776/|\660: O: O1320 (predict-no) 4777I see 1 and I'm going to do: predict-no 4778ENV: Agent did: predict-no for direction U in state State-B 4779In State-B moving U 4780ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4781predict error 0 4782dir: dir isU 4783-/661: O: O1322 (predict-no) 4784I see 1 and I'm going to do: predict-no 4785ENV: Agent did: predict-no for direction U in state State-B 4786In State-B moving U 4787ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4788predict error 0 4789dir: dir isL 4790|662: O: O1323 (predict-yes) 4791I see 1 and I'm going to do: predict-yes 4792ENV: Agent did: predict-yes for direction L in state State-B 4793In State-B moving L 4794ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4795predict error 0 4796dir: dir isU 4797\-/663: O: O1326 (predict-no) 4798I see 1 and I'm going to do: predict-no 4799ENV: Agent did: predict-no for direction U in state State-A 4800In State-A moving U 4801ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4802predict error 0 4803dir: dir isU 4804|\664: O: O1328 (predict-no) 4805I see 1 and I'm going to do: predict-no 4806ENV: Agent did: predict-no for direction U in state State-A 4807In State-A moving U 4808ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4809predict error 0 4810dir: dir isL 4811-665: O: O1330 (predict-no) 4812I see 1 and I'm going to do: predict-no 4813ENV: Agent did: predict-no for direction L in state State-A 4814In State-A moving L 4815ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4816predict error 0 4817dir: dir isR 4818/|\666: O: O1331 (predict-yes) 4819I see 1 and I'm going to do: predict-yes 4820ENV: Agent did: predict-yes for direction R in state State-A 4821In State-A moving R 4822ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4823predict error 0 4824dir: dir isR 4825-667: O: O1334 (predict-no) 4826I see 1 and I'm going to do: predict-no 4827ENV: Agent did: predict-no for direction R in state State-B 4828In State-B moving R 4829ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4830predict error 0 4831dir: dir isU 4832/|668: O: O1336 (predict-no) 4833I see 1 and I'm going to do: predict-no 4834ENV: Agent did: predict-no for direction U in state State-B 4835In State-B moving U 4836ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4837predict error 0 4838dir: dir isR 4839\-/669: O: O1338 (predict-no) 4840I see 1 and I'm going to do: predict-no 4841ENV: Agent did: predict-no for direction R in state State-B 4842In State-B moving R 4843ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4844predict error 0 4845dir: dir isU 4846|\-670: O: O1340 (predict-no) 4847I see 1 and I'm going to do: predict-no 4848ENV: Agent did: predict-no for direction U in state State-B 4849In State-B moving U 4850ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4851predict error 0 4852dir: dir isU 4853/|\671: O: O1341 (predict-yes) 4854I see 1 and I'm going to do: predict-yes 4855ENV: Agent did: predict-yes for direction U in state State-B 4856In State-B moving U 4857ENV: (next state, see, prediction correct?) = (State-B, 0, False) 4858predict error 1 4859dir: dir isL 4860-672: O: O1343 (predict-yes) 4861I see 0 and I'm going to do: predict-yes 4862ENV: Agent did: predict-yes for direction L in state State-B 4863In State-B moving L 4864ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4865predict error 0 4866dir: dir isU 4867/|673: O: O1346 (predict-no) 4868I see 1 and I'm going to do: predict-no 4869ENV: Agent did: predict-no for direction U in state State-A 4870In State-A moving U 4871ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4872predict error 0 4873dir: dir isL 4874\-/674: O: O1348 (predict-no) 4875I see 1 and I'm going to do: predict-no 4876ENV: Agent did: predict-no for direction L in state State-A 4877In State-A moving L 4878ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4879predict error 0 4880dir: dir isL 4881|\-675: O: O1350 (predict-no) 4882I see 1 and I'm going to do: predict-no 4883ENV: Agent did: predict-no for direction L in state State-A 4884In State-A moving L 4885ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4886predict error 0 4887dir: dir isR 4888/676: O: O1351 (predict-yes) 4889I see 1 and I'm going to do: predict-yes 4890ENV: Agent did: predict-yes for direction R in state State-A 4891In State-A moving R 4892ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4893predict error 0 4894dir: dir isL 4895|\-677: O: O1353 (predict-yes) 4896I see 1 and I'm going to do: predict-yes 4897ENV: Agent did: predict-yes for direction L in state State-B 4898In State-B moving L 4899ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4900predict error 0 4901dir: dir isR 4902/|678: O: O1355 (predict-yes) 4903I see 1 and I'm going to do: predict-yes 4904ENV: Agent did: predict-yes for direction R in state State-A 4905In State-A moving R 4906ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4907predict error 0 4908dir: dir isL 4909\-/679: O: O1357 (predict-yes) 4910I see 1 and I'm going to do: predict-yes 4911ENV: Agent did: predict-yes for direction L in state State-B 4912In State-B moving L 4913ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4914predict error 0 4915dir: dir isR 4916|680: O: O1359 (predict-yes) 4917I see 1 and I'm going to do: predict-yes 4918ENV: Agent did: predict-yes for direction R in state State-A 4919In State-A moving R 4920ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4921predict error 0 4922dir: dir isU 4923\-/681: O: O1362 (predict-no) 4924I see 1 and I'm going to do: predict-no 4925ENV: Agent did: predict-no for direction U in state State-B 4926In State-B moving U 4927ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4928predict error 0 4929dir: dir isU 4930|682: O: O1364 (predict-no) 4931I see 1 and I'm going to do: predict-no 4932ENV: Agent did: predict-no for direction U in state State-B 4933In State-B moving U 4934ENV: (next state, see, prediction correct?) = (State-B, 0, True) 4935predict error 0 4936dir: dir isL 4937\-/683: O: O1365 (predict-yes) 4938I see 1 and I'm going to do: predict-yes 4939ENV: Agent did: predict-yes for direction L in state State-B 4940In State-B moving L 4941ENV: (next state, see, prediction correct?) = (State-A, 1, True) 4942predict error 0 4943dir: dir isL 4944|\-684: O: O1368 (predict-no) 4945I see 1 and I'm going to do: predict-no 4946ENV: Agent did: predict-no for direction L in state State-A 4947In State-A moving L 4948ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4949predict error 0 4950dir: dir isU 4951/|\685: O: O1370 (predict-no) 4952I see 1 and I'm going to do: predict-no 4953ENV: Agent did: predict-no for direction U in state State-A 4954In State-A moving U 4955ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4956predict error 0 4957dir: dir isL 4958-/686: O: O1372 (predict-no) 4959I see 1 and I'm going to do: predict-no 4960ENV: Agent did: predict-no for direction L in state State-A 4961In State-A moving L 4962ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4963predict error 0 4964dir: dir isL 4965|\-687: O: O1374 (predict-no) 4966I see 1 and I'm going to do: predict-no 4967ENV: Agent did: predict-no for direction L in state State-A 4968In State-A moving L 4969ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4970predict error 0 4971dir: dir isL 4972/688: O: O1376 (predict-no) 4973I see 1 and I'm going to do: predict-no 4974ENV: Agent did: predict-no for direction L in state State-A 4975In State-A moving L 4976ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4977predict error 0 4978dir: dir isL 4979|\-689: O: O1378 (predict-no) 4980I see 1 and I'm going to do: predict-no 4981ENV: Agent did: predict-no for direction L in state State-A 4982In State-A moving L 4983ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4984predict error 0 4985dir: dir isL 4986/|\690: O: O1380 (predict-no) 4987I see 1 and I'm going to do: predict-no 4988ENV: Agent did: predict-no for direction L in state State-A 4989In State-A moving L 4990ENV: (next state, see, prediction correct?) = (State-A, 0, True) 4991predict error 0 4992dir: dir isR 4993-/|691: O: O1381 (predict-yes) 4994I see 1 and I'm going to do: predict-yes 4995ENV: Agent did: predict-yes for direction R in state State-A 4996In State-A moving R 4997ENV: (next state, see, prediction correct?) = (State-B, 1, True) 4998predict error 0 4999dir: dir isU 5000\692: O: O1384 (predict-no) 5001I see 1 and I'm going to do: predict-no 5002ENV: Agent did: predict-no for direction U in state State-B 5003In State-B moving U 5004ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5005predict error 0 5006dir: dir isU 5007-/|\693: O: O1386 (predict-no) 5008I see 1 and I'm going to do: predict-no 5009ENV: Agent did: predict-no for direction U in state State-B 5010In State-B moving U 5011ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5012predict error 0 5013dir: dir isU 5014-/|694: O: O1388 (predict-no) 5015I see 1 and I'm going to do: predict-no 5016ENV: Agent did: predict-no for direction U in state State-B 5017In State-B moving U 5018ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5019predict error 0 5020dir: dir isR 5021\-695: O: O1390 (predict-no) 5022I see 1 and I'm going to do: predict-no 5023ENV: Agent did: predict-no for direction R in state State-B 5024In State-B moving R 5025ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5026predict error 0 5027dir: dir isR 5028/|\696: O: O1392 (predict-no) 5029I see 1 and I'm going to do: predict-no 5030ENV: Agent did: predict-no for direction R in state State-B 5031In State-B moving R 5032ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5033predict error 0 5034dir: dir isR 5035-/697: O: O1394 (predict-no) 5036I see 1 and I'm going to do: predict-no 5037ENV: Agent did: predict-no for direction R in state State-B 5038In State-B moving R 5039ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5040predict error 0 5041dir: dir isU 5042|\-698: O: O1396 (predict-no) 5043I see 1 and I'm going to do: predict-no 5044ENV: Agent did: predict-no for direction U in state State-B 5045In State-B moving U 5046ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5047predict error 0 5048dir: dir isR 5049/|\699: O: O1398 (predict-no) 5050I see 1 and I'm going to do: predict-no 5051ENV: Agent did: predict-no for direction R in state State-B 5052In State-B moving R 5053ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5054predict error 0 5055dir: dir isL 5056-/|700: O: O1399 (predict-yes) 5057I see 1 and I'm going to do: predict-yes 5058ENV: Agent did: predict-yes for direction L in state State-B 5059In State-B moving L 5060ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5061predict error 0 5062dir: dir isL 5063\-701: O: O1402 (predict-no) 5064I see 1 and I'm going to do: predict-no 5065ENV: Agent did: predict-no for direction L in state State-A 5066In State-A moving L 5067ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5068predict error 0 5069dir: dir isU 5070/702: O: O1404 (predict-no) 5071I see 1 and I'm going to do: predict-no 5072ENV: Agent did: predict-no for direction U in state State-A 5073In State-A moving U 5074ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5075predict error 0 5076dir: dir isR 5077|\703: O: O1405 (predict-yes) 5078I see 1 and I'm going to do: predict-yes 5079ENV: Agent did: predict-yes for direction R in state State-A 5080In State-A moving R 5081ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5082predict error 0 5083dir: dir isR 5084-/|704: O: O1408 (predict-no) 5085I see 1 and I'm going to do: predict-no 5086ENV: Agent did: predict-no for direction R in state State-B 5087In State-B moving R 5088ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5089predict error 0 5090dir: dir isR 5091\-/705: O: O1409 (predict-yes) 5092I see 1 and I'm going to do: predict-yes 5093ENV: Agent did: predict-yes for direction R in state State-B 5094In State-B moving R 5095ENV: (next state, see, prediction correct?) = (State-B, 0, False) 5096predict error 1 5097dir: dir isR 5098|\-706: O: O1412 (predict-no) 5099I see 0 and I'm going to do: predict-no 5100ENV: Agent did: predict-no for direction R in state State-B 5101In State-B moving R 5102ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5103predict error 0 5104dir: dir isR 5105/|\707: O: O1414 (predict-no) 5106I see 1 and I'm going to do: predict-no 5107ENV: Agent did: predict-no for direction R in state State-B 5108In State-B moving R 5109ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5110predict error 0 5111dir: dir isL 5112-708: O: O1415 (predict-yes) 5113I see 1 and I'm going to do: predict-yes 5114ENV: Agent did: predict-yes for direction L in state State-B 5115In State-B moving L 5116ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5117predict error 0 5118dir: dir isR 5119/|\709: O: O1417 (predict-yes) 5120I see 1 and I'm going to do: predict-yes 5121ENV: Agent did: predict-yes for direction R in state State-A 5122In State-A moving R 5123ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5124predict error 0 5125dir: dir isR 5126-710: O: O1420 (predict-no) 5127I see 1 and I'm going to do: predict-no 5128ENV: Agent did: predict-no for direction R in state State-B 5129In State-B moving R 5130ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5131predict error 0 5132dir: dir isL 5133/|\711: O: O1421 (predict-yes) 5134I see 1 and I'm going to do: predict-yes 5135ENV: Agent did: predict-yes for direction L in state State-B 5136In State-B moving L 5137ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5138predict error 0 5139dir: dir isU 5140-712: O: O1424 (predict-no) 5141I see 1 and I'm going to do: predict-no 5142ENV: Agent did: predict-no for direction U in state State-A 5143In State-A moving U 5144ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5145predict error 0 5146dir: dir isR 5147/|713: O: O1425 (predict-yes) 5148I see 1 and I'm going to do: predict-yes 5149ENV: Agent did: predict-yes for direction R in state State-A 5150In State-A moving R 5151ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5152predict error 0 5153dir: dir isR 5154\-714: O: O1428 (predict-no) 5155I see 1 and I'm going to do: predict-no 5156ENV: Agent did: predict-no for direction R in state State-B 5157In State-B moving R 5158ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5159predict error 0 5160dir: dir isU 5161/|\715: O: O1430 (predict-no) 5162I see 1 and I'm going to do: predict-no 5163ENV: Agent did: predict-no for direction U in state State-B 5164In State-B moving U 5165ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5166predict error 0 5167dir: dir isU 5168-/|\716: O: O1432 (predict-no) 5169I see 1 and I'm going to do: predict-no 5170ENV: Agent did: predict-no for direction U in state State-B 5171In State-B moving U 5172ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5173predict error 0 5174dir: dir isU 5175-/|\717: O: O1434 (predict-no) 5176I see 1 and I'm going to do: predict-no 5177ENV: Agent did: predict-no for direction U in state State-B 5178In State-B moving U 5179ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5180predict error 0 5181dir: dir isU 5182-/|718: O: O1436 (predict-no) 5183I see 1 and I'm going to do: predict-no 5184ENV: Agent did: predict-no for direction U in state State-B 5185In State-B moving U 5186ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5187predict error 0 5188dir: dir isL 5189\-719: O: O1437 (predict-yes) 5190I see 1 and I'm going to do: predict-yes 5191ENV: Agent did: predict-yes for direction L in state State-B 5192In State-B moving L 5193ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5194predict error 0 5195dir: dir isU 5196/|720: O: O1440 (predict-no) 5197I see 1 and I'm going to do: predict-no 5198ENV: Agent did: predict-no for direction U in state State-A 5199In State-A moving U 5200ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5201predict error 0 5202dir: dir isL 5203\-721: O: O1442 (predict-no) 5204I see 1 and I'm going to do: predict-no 5205ENV: Agent did: predict-no for direction L in state State-A 5206In State-A moving L 5207ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5208predict error 0 5209dir: dir isU 5210/722: O: O1444 (predict-no) 5211I see 1 and I'm going to do: predict-no 5212ENV: Agent did: predict-no for direction U in state State-A 5213In State-A moving U 5214ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5215predict error 0 5216dir: dir isU 5217|\-723: O: O1446 (predict-no) 5218I see 1 and I'm going to do: predict-no 5219ENV: Agent did: predict-no for direction U in state State-A 5220In State-A moving U 5221ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5222predict error 0 5223dir: dir isU 5224/|\724: O: O1448 (predict-no) 5225I see 1 and I'm going to do: predict-no 5226ENV: Agent did: predict-no for direction U in state State-A 5227In State-A moving U 5228ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5229predict error 0 5230dir: dir isL 5231-/|725: O: O1450 (predict-no) 5232I see 1 and I'm going to do: predict-no 5233ENV: Agent did: predict-no for direction L in state State-A 5234In State-A moving L 5235ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5236predict error 0 5237dir: dir isL 5238\-/|726: O: O1452 (predict-no) 5239I see 1 and I'm going to do: predict-no 5240ENV: Agent did: predict-no for direction L in state State-A 5241In State-A moving L 5242ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5243predict error 0 5244dir: dir isU 5245\-/727: O: O1454 (predict-no) 5246I see 1 and I'm going to do: predict-no 5247ENV: Agent did: predict-no for direction U in state State-A 5248In State-A moving U 5249ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5250predict error 0 5251dir: dir isR 5252|\-728: O: O1455 (predict-yes) 5253I see 1 and I'm going to do: predict-yes 5254ENV: Agent did: predict-yes for direction R in state State-A 5255In State-A moving R 5256ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5257predict error 0 5258dir: dir isR 5259/|\729: O: O1458 (predict-no) 5260I see 1 and I'm going to do: predict-no 5261ENV: Agent did: predict-no for direction R in state State-B 5262In State-B moving R 5263ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5264predict error 0 5265dir: dir isU 5266-/730: O: O1460 (predict-no) 5267I see 1 and I'm going to do: predict-no 5268ENV: Agent did: predict-no for direction U in state State-B 5269In State-B moving U 5270ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5271predict error 0 5272dir: dir isL 5273|\-731: O: O1461 (predict-yes) 5274I see 1 and I'm going to do: predict-yes 5275ENV: Agent did: predict-yes for direction L in state State-B 5276In State-B moving L 5277ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5278predict error 0 5279dir: dir isR 5280/732: O: O1463 (predict-yes) 5281I see 1 and I'm going to do: predict-yes 5282ENV: Agent did: predict-yes for direction R in state State-A 5283In State-A moving R 5284ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5285predict error 0 5286dir: dir isR 5287|\733: O: O1466 (predict-no) 5288I see 1 and I'm going to do: predict-no 5289ENV: Agent did: predict-no for direction R in state State-B 5290In State-B moving R 5291ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5292predict error 0 5293dir: dir isL 5294-/|734: O: O1467 (predict-yes) 5295I see 1 and I'm going to do: predict-yes 5296ENV: Agent did: predict-yes for direction L in state State-B 5297In State-B moving L 5298ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5299predict error 0 5300dir: dir isR 5301\-/735: O: O1469 (predict-yes) 5302I see 1 and I'm going to do: predict-yes 5303ENV: Agent did: predict-yes for direction R in state State-A 5304In State-A moving R 5305ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5306predict error 0 5307dir: dir isU 5308|\-/736: O: O1472 (predict-no) 5309I see 1 and I'm going to do: predict-no 5310ENV: Agent did: predict-no for direction U in state State-B 5311In State-B moving U 5312ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5313predict error 0 5314dir: dir isU 5315|\737: O: O1474 (predict-no) 5316I see 1 and I'm going to do: predict-no 5317ENV: Agent did: predict-no for direction U in state State-B 5318In State-B moving U 5319ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5320predict error 0 5321dir: dir isL 5322-/738: O: O1475 (predict-yes) 5323I see 1 and I'm going to do: predict-yes 5324ENV: Agent did: predict-yes for direction L in state State-B 5325In State-B moving L 5326ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5327predict error 0 5328dir: dir isR 5329|\-739: O: O1477 (predict-yes) 5330I see 1 and I'm going to do: predict-yes 5331ENV: Agent did: predict-yes for direction R in state State-A 5332In State-A moving R 5333ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5334predict error 0 5335dir: dir isL 5336/|\740: O: O1479 (predict-yes) 5337I see 1 and I'm going to do: predict-yes 5338ENV: Agent did: predict-yes for direction L in state State-B 5339In State-B moving L 5340ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5341predict error 0 5342dir: dir isU 5343-/741: O: O1482 (predict-no) 5344I see 1 and I'm going to do: predict-no 5345ENV: Agent did: predict-no for direction U in state State-A 5346In State-A moving U 5347ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5348predict error 0 5349dir: dir isL 5350|742: O: O1484 (predict-no) 5351I see 1 and I'm going to do: predict-no 5352ENV: Agent did: predict-no for direction L in state State-A 5353In State-A moving L 5354ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5355predict error 0 5356dir: dir isL 5357\-743: O: O1486 (predict-no) 5358I see 1 and I'm going to do: predict-no 5359ENV: Agent did: predict-no for direction L in state State-A 5360In State-A moving L 5361ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5362predict error 0 5363dir: dir isR 5364/|\744: O: O1487 (predict-yes) 5365I see 1 and I'm going to do: predict-yes 5366ENV: Agent did: predict-yes for direction R in state State-A 5367In State-A moving R 5368ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5369predict error 0 5370dir: dir isU 5371-/|745: O: O1490 (predict-no) 5372I see 1 and I'm going to do: predict-no 5373ENV: Agent did: predict-no for direction U in state State-B 5374In State-B moving U 5375ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5376predict error 0 5377dir: dir isL 5378\-746: O: O1491 (predict-yes) 5379I see 1 and I'm going to do: predict-yes 5380ENV: Agent did: predict-yes for direction L in state State-B 5381In State-B moving L 5382ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5383predict error 0 5384dir: dir isL 5385/|\747: O: O1494 (predict-no) 5386I see 1 and I'm going to do: predict-no 5387ENV: Agent did: predict-no for direction L in state State-A 5388In State-A moving L 5389ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5390predict error 0 5391dir: dir isU 5392-/|748: O: O1496 (predict-no) 5393I see 1 and I'm going to do: predict-no 5394ENV: Agent did: predict-no for direction U in state State-A 5395In State-A moving U 5396ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5397predict error 0 5398dir: dir isU 5399\-/749: O: O1498 (predict-no) 5400I see 1 and I'm going to do: predict-no 5401ENV: Agent did: predict-no for direction U in state State-A 5402In State-A moving U 5403ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5404predict error 0 5405dir: dir isU 5406|\-750: O: O1500 (predict-no) 5407I see 1 and I'm going to do: predict-no 5408ENV: Agent did: predict-no for direction U in state State-A 5409In State-A moving U 5410ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5411predict error 0 5412dir: dir isL 5413/|\751: O: O1502 (predict-no) 5414I see 1 and I'm going to do: predict-no 5415ENV: Agent did: predict-no for direction L in state State-A 5416In State-A moving L 5417ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5418predict error 0 5419dir: dir isR 5420-752: O: O1503 (predict-yes) 5421I see 1 and I'm going to do: predict-yes 5422ENV: Agent did: predict-yes for direction R in state State-A 5423In State-A moving R 5424ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5425predict error 0 5426dir: dir isL 5427/|753: O: O1505 (predict-yes) 5428I see 1 and I'm going to do: predict-yes 5429ENV: Agent did: predict-yes for direction L in state State-B 5430In State-B moving L 5431ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5432predict error 0 5433dir: dir isR 5434\-/754: O: O1507 (predict-yes) 5435I see 1 and I'm going to do: predict-yes 5436ENV: Agent did: predict-yes for direction R in state State-A 5437In State-A moving R 5438ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5439predict error 0 5440dir: dir isL 5441|\-755: O: O1509 (predict-yes) 5442I see 1 and I'm going to do: predict-yes 5443ENV: Agent did: predict-yes for direction L in state State-B 5444In State-B moving L 5445ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5446predict error 0 5447dir: dir isR 5448/|\756: O: O1511 (predict-yes) 5449I see 1 and I'm going to do: predict-yes 5450ENV: Agent did: predict-yes for direction R in state State-A 5451In State-A moving R 5452ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5453predict error 0 5454dir: dir isU 5455-/|757: O: O1514 (predict-no) 5456I see 1 and I'm going to do: predict-no 5457ENV: Agent did: predict-no for direction U in state State-B 5458In State-B moving U 5459ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5460predict error 0 5461dir: dir isU 5462\-/758: O: O1516 (predict-no) 5463I see 1 and I'm going to do: predict-no 5464ENV: Agent did: predict-no for direction U in state State-B 5465In State-B moving U 5466ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5467predict error 0 5468dir: dir isR 5469|\-759: O: O1518 (predict-no) 5470I see 1 and I'm going to do: predict-no 5471ENV: Agent did: predict-no for direction R in state State-B 5472In State-B moving R 5473ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5474predict error 0 5475dir: dir isL 5476/|\760: O: O1519 (predict-yes) 5477I see 1 and I'm going to do: predict-yes 5478ENV: Agent did: predict-yes for direction L in state State-B 5479In State-B moving L 5480ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5481predict error 0 5482dir: dir isR 5483-/|761: O: O1521 (predict-yes) 5484I see 1 and I'm going to do: predict-yes 5485ENV: Agent did: predict-yes for direction R in state State-A 5486In State-A moving R 5487ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5488predict error 0 5489dir: dir isR 5490\762: O: O1524 (predict-no) 5491I see 1 and I'm going to do: predict-no 5492ENV: Agent did: predict-no for direction R in state State-B 5493In State-B moving R 5494ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5495predict error 0 5496dir: dir isU 5497-/|763: O: O1526 (predict-no) 5498I see 1 and I'm going to do: predict-no 5499ENV: Agent did: predict-no for direction U in state State-B 5500In State-B moving U 5501ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5502predict error 0 5503dir: dir isU 5504\-/764: O: O1528 (predict-no) 5505I see 1 and I'm going to do: predict-no 5506ENV: Agent did: predict-no for direction U in state State-B 5507In State-B moving U 5508ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5509predict error 0 5510dir: dir isU 5511|\-765: O: O1530 (predict-no) 5512I see 1 and I'm going to do: predict-no 5513ENV: Agent did: predict-no for direction U in state State-B 5514In State-B moving U 5515ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5516predict error 0 5517dir: dir isU 5518/766: O: O1532 (predict-no) 5519I see 1 and I'm going to do: predict-no 5520ENV: Agent did: predict-no for direction U in state State-B 5521In State-B moving U 5522ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5523predict error 0 5524dir: dir isR 5525|767: O: O1534 (predict-no) 5526I see 1 and I'm going to do: predict-no 5527ENV: Agent did: predict-no for direction R in state State-B 5528In State-B moving R 5529ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5530predict error 0 5531dir: dir isU 5532\-/768: O: O1536 (predict-no) 5533I see 1 and I'm going to do: predict-no 5534ENV: Agent did: predict-no for direction U in state State-B 5535In State-B moving U 5536ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5537predict error 0 5538dir: dir isU 5539|\-769: O: O1538 (predict-no) 5540I see 1 and I'm going to do: predict-no 5541ENV: Agent did: predict-no for direction U in state State-B 5542In State-B moving U 5543ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5544predict error 0 5545dir: dir isL 5546/|770: O: O1539 (predict-yes) 5547I see 1 and I'm going to do: predict-yes 5548ENV: Agent did: predict-yes for direction L in state State-B 5549In State-B moving L 5550ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5551predict error 0 5552dir: dir isL 5553\771: O: O1542 (predict-no) 5554I see 1 and I'm going to do: predict-no 5555ENV: Agent did: predict-no for direction L in state State-A 5556In State-A moving L 5557ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5558predict error 0 5559dir: dir isR 5560-772: O: O1543 (predict-yes) 5561I see 1 and I'm going to do: predict-yes 5562ENV: Agent did: predict-yes for direction R in state State-A 5563In State-A moving R 5564ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5565predict error 0 5566dir: dir isR 5567/|773: O: O1546 (predict-no) 5568I see 1 and I'm going to do: predict-no 5569ENV: Agent did: predict-no for direction R in state State-B 5570In State-B moving R 5571ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5572predict error 0 5573dir: dir isL 5574\-/|774: O: O1547 (predict-yes) 5575I see 1 and I'm going to do: predict-yes 5576ENV: Agent did: predict-yes for direction L in state State-B 5577In State-B moving L 5578ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5579predict error 0 5580dir: dir isR 5581\-/775: O: O1549 (predict-yes) 5582I see 1 and I'm going to do: predict-yes 5583ENV: Agent did: predict-yes for direction R in state State-A 5584In State-A moving R 5585ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5586predict error 0 5587dir: dir isR 5588|\-776: O: O1552 (predict-no) 5589I see 1 and I'm going to do: predict-no 5590ENV: Agent did: predict-no for direction R in state State-B 5591In State-B moving R 5592ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5593predict error 0 5594dir: dir isL 5595/|\777: O: O1553 (predict-yes) 5596I see 1 and I'm going to do: predict-yes 5597ENV: Agent did: predict-yes for direction L in state State-B 5598In State-B moving L 5599ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5600predict error 0 5601dir: dir isU 5602-/778: O: O1556 (predict-no) 5603I see 1 and I'm going to do: predict-no 5604ENV: Agent did: predict-no for direction U in state State-A 5605In State-A moving U 5606ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5607predict error 0 5608dir: dir isR 5609|\-779: O: O1557 (predict-yes) 5610I see 1 and I'm going to do: predict-yes 5611ENV: Agent did: predict-yes for direction R in state State-A 5612In State-A moving R 5613ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5614predict error 0 5615dir: dir isL 5616/|\780: O: O1559 (predict-yes) 5617I see 1 and I'm going to do: predict-yes 5618ENV: Agent did: predict-yes for direction L in state State-B 5619In State-B moving L 5620ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5621predict error 0 5622dir: dir isL 5623-/|781: O: O1562 (predict-no) 5624I see 1 and I'm going to do: predict-no 5625ENV: Agent did: predict-no for direction L in state State-A 5626In State-A moving L 5627ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5628predict error 0 5629dir: dir isR 5630\782: O: O1563 (predict-yes) 5631I see 1 and I'm going to do: predict-yes 5632ENV: Agent did: predict-yes for direction R in state State-A 5633In State-A moving R 5634ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5635predict error 0 5636dir: dir isL 5637-/783: O: O1565 (predict-yes) 5638I see 1 and I'm going to do: predict-yes 5639ENV: Agent did: predict-yes for direction L in state State-B 5640In State-B moving L 5641ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5642predict error 0 5643dir: dir isU 5644|\-784: O: O1568 (predict-no) 5645I see 1 and I'm going to do: predict-no 5646ENV: Agent did: predict-no for direction U in state State-A 5647In State-A moving U 5648ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5649predict error 0 5650dir: dir isR 5651/|785: O: O1569 (predict-yes) 5652I see 1 and I'm going to do: predict-yes 5653ENV: Agent did: predict-yes for direction R in state State-A 5654In State-A moving R 5655ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5656predict error 0 5657dir: dir isR 5658\786: O: O1572 (predict-no) 5659I see 1 and I'm going to do: predict-no 5660ENV: Agent did: predict-no for direction R in state State-B 5661In State-B moving R 5662ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5663predict error 0 5664dir: dir isL 5665-/787: O: O1573 (predict-yes) 5666I see 1 and I'm going to do: predict-yes 5667ENV: Agent did: predict-yes for direction L in state State-B 5668In State-B moving L 5669ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5670predict error 0 5671dir: dir isU 5672|\-788: O: O1576 (predict-no) 5673I see 1 and I'm going to do: predict-no 5674ENV: Agent did: predict-no for direction U in state State-A 5675In State-A moving U 5676ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5677predict error 0 5678dir: dir isL 5679/|\789: O: O1578 (predict-no) 5680I see 1 and I'm going to do: predict-no 5681ENV: Agent did: predict-no for direction L in state State-A 5682In State-A moving L 5683ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5684predict error 0 5685dir: dir isL 5686-/790: O: O1580 (predict-no) 5687I see 1 and I'm going to do: predict-no 5688ENV: Agent did: predict-no for direction L in state State-A 5689In State-A moving L 5690ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5691predict error 0 5692dir: dir isL 5693|\-791: O: O1582 (predict-no) 5694I see 1 and I'm going to do: predict-no 5695ENV: Agent did: predict-no for direction L in state State-A 5696In State-A moving L 5697ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5698predict error 0 5699dir: dir isU 5700/792: O: O1584 (predict-no) 5701I see 1 and I'm going to do: predict-no 5702ENV: Agent did: predict-no for direction U in state State-A 5703In State-A moving U 5704ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5705predict error 0 5706dir: dir isR 5707|\-793: O: O1585 (predict-yes) 5708I see 1 and I'm going to do: predict-yes 5709ENV: Agent did: predict-yes for direction R in state State-A 5710In State-A moving R 5711ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5712predict error 0 5713dir: dir isU 5714/|794: O: O1588 (predict-no) 5715I see 1 and I'm going to do: predict-no 5716ENV: Agent did: predict-no for direction U in state State-B 5717In State-B moving U 5718ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5719predict error 0 5720dir: dir isU 5721\-/795: O: O1590 (predict-no) 5722I see 1 and I'm going to do: predict-no 5723ENV: Agent did: predict-no for direction U in state State-B 5724In State-B moving U 5725ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5726predict error 0 5727dir: dir isU 5728|\-796: O: O1592 (predict-no) 5729I see 1 and I'm going to do: predict-no 5730ENV: Agent did: predict-no for direction U in state State-B 5731In State-B moving U 5732ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5733predict error 0 5734dir: dir isU 5735/|\797: O: O1594 (predict-no) 5736I see 1 and I'm going to do: predict-no 5737ENV: Agent did: predict-no for direction U in state State-B 5738In State-B moving U 5739ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5740predict error 0 5741dir: dir isU 5742-798: O: O1596 (predict-no) 5743I see 1 and I'm going to do: predict-no 5744ENV: Agent did: predict-no for direction U in state State-B 5745In State-B moving U 5746ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5747predict error 0 5748dir: dir isU 5749/|\799: O: O1598 (predict-no) 5750I see 1 and I'm going to do: predict-no 5751ENV: Agent did: predict-no for direction U in state State-B 5752In State-B moving U 5753ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5754predict error 0 5755dir: dir isU 5756-/|800: O: O1600 (predict-no) 5757I see 1 and I'm going to do: predict-no 5758ENV: Agent did: predict-no for direction U in state State-B 5759In State-B moving U 5760ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5761predict error 0 5762dir: dir isL 5763\-/801: O: O1601 (predict-yes) 5764I see 1 and I'm going to do: predict-yes 5765ENV: Agent did: predict-yes for direction L in state State-B 5766In State-B moving L 5767ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5768predict error 0 5769dir: dir isR 5770|802: O: O1603 (predict-yes) 5771I see 1 and I'm going to do: predict-yes 5772ENV: Agent did: predict-yes for direction R in state State-A 5773In State-A moving R 5774ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5775predict error 0 5776dir: dir isR 5777\-/803: O: O1606 (predict-no) 5778I see 1 and I'm going to do: predict-no 5779ENV: Agent did: predict-no for direction R in state State-B 5780In State-B moving R 5781ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5782predict error 0 5783dir: dir isU 5784|\-804: O: O1608 (predict-no) 5785I see 1 and I'm going to do: predict-no 5786ENV: Agent did: predict-no for direction U in state State-B 5787In State-B moving U 5788ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5789predict error 0 5790dir: dir isU 5791/|805: O: O1610 (predict-no) 5792I see 1 and I'm going to do: predict-no 5793ENV: Agent did: predict-no for direction U in state State-B 5794In State-B moving U 5795ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5796predict error 0 5797dir: dir isU 5798\-/806: O: O1612 (predict-no) 5799I see 1 and I'm going to do: predict-no 5800ENV: Agent did: predict-no for direction U in state State-B 5801In State-B moving U 5802ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5803predict error 0 5804dir: dir isU 5805|\-807: O: O1614 (predict-no) 5806I see 1 and I'm going to do: predict-no 5807ENV: Agent did: predict-no for direction U in state State-B 5808In State-B moving U 5809ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5810predict error 0 5811dir: dir isR 5812/|\808: O: O1616 (predict-no) 5813I see 1 and I'm going to do: predict-no 5814ENV: Agent did: predict-no for direction R in state State-B 5815In State-B moving R 5816ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5817predict error 0 5818dir: dir isU 5819-/|809: O: O1618 (predict-no) 5820I see 1 and I'm going to do: predict-no 5821ENV: Agent did: predict-no for direction U in state State-B 5822In State-B moving U 5823ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5824predict error 0 5825dir: dir isR 5826\-/810: O: O1620 (predict-no) 5827I see 1 and I'm going to do: predict-no 5828ENV: Agent did: predict-no for direction R in state State-B 5829In State-B moving R 5830ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5831predict error 0 5832dir: dir isR 5833|\-811: O: O1622 (predict-no) 5834I see 1 and I'm going to do: predict-no 5835ENV: Agent did: predict-no for direction R in state State-B 5836In State-B moving R 5837ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5838predict error 0 5839dir: dir isR 5840/812: O: O1624 (predict-no) 5841I see 1 and I'm going to do: predict-no 5842ENV: Agent did: predict-no for direction R in state State-B 5843In State-B moving R 5844ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5845predict error 0 5846dir: dir isU 5847|\-813: O: O1626 (predict-no) 5848I see 1 and I'm going to do: predict-no 5849ENV: Agent did: predict-no for direction U in state State-B 5850In State-B moving U 5851ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5852predict error 0 5853dir: dir isR 5854/|\814: O: O1628 (predict-no) 5855I see 1 and I'm going to do: predict-no 5856ENV: Agent did: predict-no for direction R in state State-B 5857In State-B moving R 5858ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5859predict error 0 5860dir: dir isL 5861-/|815: O: O1629 (predict-yes) 5862I see 1 and I'm going to do: predict-yes 5863ENV: Agent did: predict-yes for direction L in state State-B 5864In State-B moving L 5865ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5866predict error 0 5867dir: dir isL 5868\-/816: O: O1632 (predict-no) 5869I see 1 and I'm going to do: predict-no 5870ENV: Agent did: predict-no for direction L in state State-A 5871In State-A moving L 5872ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5873predict error 0 5874dir: dir isU 5875|\817: O: O1634 (predict-no) 5876I see 1 and I'm going to do: predict-no 5877ENV: Agent did: predict-no for direction U in state State-A 5878In State-A moving U 5879ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5880predict error 0 5881dir: dir isR 5882-/|818: O: O1635 (predict-yes) 5883I see 1 and I'm going to do: predict-yes 5884ENV: Agent did: predict-yes for direction R in state State-A 5885In State-A moving R 5886ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5887predict error 0 5888dir: dir isU 5889\-/819: O: O1638 (predict-no) 5890I see 1 and I'm going to do: predict-no 5891ENV: Agent did: predict-no for direction U in state State-B 5892In State-B moving U 5893ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5894predict error 0 5895dir: dir isL 5896|\-820: O: O1639 (predict-yes) 5897I see 1 and I'm going to do: predict-yes 5898ENV: Agent did: predict-yes for direction L in state State-B 5899In State-B moving L 5900ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5901predict error 0 5902dir: dir isR 5903/|\821: O: O1641 (predict-yes) 5904I see 1 and I'm going to do: predict-yes 5905ENV: Agent did: predict-yes for direction R in state State-A 5906In State-A moving R 5907ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5908predict error 0 5909dir: dir isU 5910-822: O: O1644 (predict-no) 5911I see 1 and I'm going to do: predict-no 5912ENV: Agent did: predict-no for direction U in state State-B 5913In State-B moving U 5914ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5915predict error 0 5916dir: dir isL 5917/|\823: O: O1645 (predict-yes) 5918I see 1 and I'm going to do: predict-yes 5919ENV: Agent did: predict-yes for direction L in state State-B 5920In State-B moving L 5921ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5922predict error 0 5923dir: dir isL 5924-824: O: O1648 (predict-no) 5925I see 1 and I'm going to do: predict-no 5926ENV: Agent did: predict-no for direction L in state State-A 5927In State-A moving L 5928ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5929predict error 0 5930dir: dir isR 5931/|\825: O: O1649 (predict-yes) 5932I see 1 and I'm going to do: predict-yes 5933ENV: Agent did: predict-yes for direction R in state State-A 5934In State-A moving R 5935ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5936predict error 0 5937dir: dir isL 5938-/|826: O: O1651 (predict-yes) 5939I see 1 and I'm going to do: predict-yes 5940ENV: Agent did: predict-yes for direction L in state State-B 5941In State-B moving L 5942ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5943predict error 0 5944dir: dir isL 5945\-/827: O: O1654 (predict-no) 5946I see 1 and I'm going to do: predict-no 5947ENV: Agent did: predict-no for direction L in state State-A 5948In State-A moving L 5949ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5950predict error 0 5951dir: dir isL 5952|\-828: O: O1656 (predict-no) 5953I see 1 and I'm going to do: predict-no 5954ENV: Agent did: predict-no for direction L in state State-A 5955In State-A moving L 5956ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5957predict error 0 5958dir: dir isR 5959/|\829: O: O1657 (predict-yes) 5960I see 1 and I'm going to do: predict-yes 5961ENV: Agent did: predict-yes for direction R in state State-A 5962In State-A moving R 5963ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5964predict error 0 5965dir: dir isR 5966-/|830: O: O1660 (predict-no) 5967I see 1 and I'm going to do: predict-no 5968ENV: Agent did: predict-no for direction R in state State-B 5969In State-B moving R 5970ENV: (next state, see, prediction correct?) = (State-B, 0, True) 5971predict error 0 5972dir: dir isL 5973\-/831: O: O1661 (predict-yes) 5974I see 1 and I'm going to do: predict-yes 5975ENV: Agent did: predict-yes for direction L in state State-B 5976In State-B moving L 5977ENV: (next state, see, prediction correct?) = (State-A, 1, True) 5978predict error 0 5979dir: dir isL 5980|832: O: O1664 (predict-no) 5981I see 1 and I'm going to do: predict-no 5982ENV: Agent did: predict-no for direction L in state State-A 5983In State-A moving L 5984ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5985predict error 0 5986dir: dir isU 5987\-/833: O: O1666 (predict-no) 5988I see 1 and I'm going to do: predict-no 5989ENV: Agent did: predict-no for direction U in state State-A 5990In State-A moving U 5991ENV: (next state, see, prediction correct?) = (State-A, 0, True) 5992predict error 0 5993dir: dir isR 5994|\-834: O: O1667 (predict-yes) 5995I see 1 and I'm going to do: predict-yes 5996ENV: Agent did: predict-yes for direction R in state State-A 5997In State-A moving R 5998ENV: (next state, see, prediction correct?) = (State-B, 1, True) 5999predict error 0 6000dir: dir isL 6001/|\835: O: O1669 (predict-yes) 6002I see 1 and I'm going to do: predict-yes 6003ENV: Agent did: predict-yes for direction L in state State-B 6004In State-B moving L 6005ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6006predict error 0 6007dir: dir isU 6008-/836: O: O1672 (predict-no) 6009I see 1 and I'm going to do: predict-no 6010ENV: Agent did: predict-no for direction U in state State-A 6011In State-A moving U 6012ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6013predict error 0 6014dir: dir isL 6015|\-837: O: O1674 (predict-no) 6016I see 1 and I'm going to do: predict-no 6017ENV: Agent did: predict-no for direction L in state State-A 6018In State-A moving L 6019ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6020predict error 0 6021dir: dir isR 6022/|\838: O: O1675 (predict-yes) 6023I see 1 and I'm going to do: predict-yes 6024ENV: Agent did: predict-yes for direction R in state State-A 6025In State-A moving R 6026ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6027predict error 0 6028dir: dir isU 6029-/|839: O: O1678 (predict-no) 6030I see 1 and I'm going to do: predict-no 6031ENV: Agent did: predict-no for direction U in state State-B 6032In State-B moving U 6033ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6034predict error 0 6035dir: dir isU 6036\-/840: O: O1680 (predict-no) 6037I see 1 and I'm going to do: predict-no 6038ENV: Agent did: predict-no for direction U in state State-B 6039In State-B moving U 6040ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6041predict error 0 6042dir: dir isL 6043|\-841: O: O1681 (predict-yes) 6044I see 1 and I'm going to do: predict-yes 6045ENV: Agent did: predict-yes for direction L in state State-B 6046In State-B moving L 6047ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6048predict error 0 6049dir: dir isU 6050/842: O: O1684 (predict-no) 6051I see 1 and I'm going to do: predict-no 6052ENV: Agent did: predict-no for direction U in state State-A 6053In State-A moving U 6054ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6055predict error 0 6056dir: dir isR 6057|\843: O: O1685 (predict-yes) 6058I see 1 and I'm going to do: predict-yes 6059ENV: Agent did: predict-yes for direction R in state State-A 6060In State-A moving R 6061ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6062predict error 0 6063dir: dir isU 6064-/844: O: O1688 (predict-no) 6065I see 1 and I'm going to do: predict-no 6066ENV: Agent did: predict-no for direction U in state State-B 6067In State-B moving U 6068ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6069predict error 0 6070dir: dir isU 6071|\-845: O: O1690 (predict-no) 6072I see 1 and I'm going to do: predict-no 6073ENV: Agent did: predict-no for direction U in state State-B 6074In State-B moving U 6075ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6076predict error 0 6077dir: dir isR 6078/|\846: O: O1692 (predict-no) 6079I see 1 and I'm going to do: predict-no 6080ENV: Agent did: predict-no for direction R in state State-B 6081In State-B moving R 6082ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6083predict error 0 6084dir: dir isU 6085-/|847: O: O1694 (predict-no) 6086I see 1 and I'm going to do: predict-no 6087ENV: Agent did: predict-no for direction U in state State-B 6088In State-B moving U 6089ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6090predict error 0 6091dir: dir isR 6092\-/848: O: O1696 (predict-no) 6093I see 1 and I'm going to do: predict-no 6094ENV: Agent did: predict-no for direction R in state State-B 6095In State-B moving R 6096ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6097predict error 0 6098dir: dir isU 6099|849: O: O1698 (predict-no) 6100I see 1 and I'm going to do: predict-no 6101ENV: Agent did: predict-no for direction U in state State-B 6102In State-B moving U 6103ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6104predict error 0 6105dir: dir isU 6106\-/850: O: O1700 (predict-no) 6107I see 1 and I'm going to do: predict-no 6108ENV: Agent did: predict-no for direction U in state State-B 6109In State-B moving U 6110ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6111predict error 0 6112dir: dir isU 6113|\-851: O: O1702 (predict-no) 6114I see 1 and I'm going to do: predict-no 6115ENV: Agent did: predict-no for direction U in state State-B 6116In State-B moving U 6117ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6118predict error 0 6119dir: dir isU 6120/852: O: O1704 (predict-no) 6121I see 1 and I'm going to do: predict-no 6122ENV: Agent did: predict-no for direction U in state State-B 6123In State-B moving U 6124ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6125predict error 0 6126dir: dir isU 6127|\-853: O: O1706 (predict-no) 6128I see 1 and I'm going to do: predict-no 6129ENV: Agent did: predict-no for direction U in state State-B 6130In State-B moving U 6131ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6132predict error 0 6133dir: dir isL 6134/|\854: O: O1707 (predict-yes) 6135I see 1 and I'm going to do: predict-yes 6136ENV: Agent did: predict-yes for direction L in state State-B 6137In State-B moving L 6138ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6139predict error 0 6140dir: dir isL 6141-/|855: O: O1710 (predict-no) 6142I see 1 and I'm going to do: predict-no 6143ENV: Agent did: predict-no for direction L in state State-A 6144In State-A moving L 6145ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6146predict error 0 6147dir: dir isU 6148\-856: O: O1712 (predict-no) 6149I see 1 and I'm going to do: predict-no 6150ENV: Agent did: predict-no for direction U in state State-A 6151In State-A moving U 6152ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6153predict error 0 6154dir: dir isU 6155/|\857: O: O1714 (predict-no) 6156I see 1 and I'm going to do: predict-no 6157ENV: Agent did: predict-no for direction U in state State-A 6158In State-A moving U 6159ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6160predict error 0 6161dir: dir isR 6162-/|858: O: O1715 (predict-yes) 6163I see 1 and I'm going to do: predict-yes 6164ENV: Agent did: predict-yes for direction R in state State-A 6165In State-A moving R 6166ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6167predict error 0 6168dir: dir isR 6169\-/859: O: O1718 (predict-no) 6170I see 1 and I'm going to do: predict-no 6171ENV: Agent did: predict-no for direction R in state State-B 6172In State-B moving R 6173ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6174predict error 0 6175dir: dir isR 6176|860: O: O1720 (predict-no) 6177I see 1 and I'm going to do: predict-no 6178ENV: Agent did: predict-no for direction R in state State-B 6179In State-B moving R 6180ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6181predict error 0 6182dir: dir isU 6183\-861: O: O1722 (predict-no) 6184I see 1 and I'm going to do: predict-no 6185ENV: Agent did: predict-no for direction U in state State-B 6186In State-B moving U 6187ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6188predict error 0 6189dir: dir isU 6190/862: O: O1724 (predict-no) 6191I see 1 and I'm going to do: predict-no 6192ENV: Agent did: predict-no for direction U in state State-B 6193In State-B moving U 6194ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6195predict error 0 6196dir: dir isR 6197|\-/863: O: O1726 (predict-no) 6198I see 1 and I'm going to do: predict-no 6199ENV: Agent did: predict-no for direction R in state State-B 6200In State-B moving R 6201ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6202predict error 0 6203dir: dir isL 6204|\-864: O: O1727 (predict-yes) 6205I see 1 and I'm going to do: predict-yes 6206ENV: Agent did: predict-yes for direction L in state State-B 6207In State-B moving L 6208ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6209predict error 0 6210dir: dir isU 6211/865: O: O1730 (predict-no) 6212I see 1 and I'm going to do: predict-no 6213ENV: Agent did: predict-no for direction U in state State-A 6214In State-A moving U 6215ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6216predict error 0 6217dir: dir isR 6218|\-866: O: O1731 (predict-yes) 6219I see 1 and I'm going to do: predict-yes 6220ENV: Agent did: predict-yes for direction R in state State-A 6221In State-A moving R 6222ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6223predict error 0 6224dir: dir isL 6225/|\867: O: O1733 (predict-yes) 6226I see 1 and I'm going to do: predict-yes 6227ENV: Agent did: predict-yes for direction L in state State-B 6228In State-B moving L 6229ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6230predict error 0 6231dir: dir isL 6232-/|868: O: O1736 (predict-no) 6233I see 1 and I'm going to do: predict-no 6234ENV: Agent did: predict-no for direction L in state State-A 6235In State-A moving L 6236ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6237predict error 0 6238dir: dir isU 6239\-/869: O: O1738 (predict-no) 6240I see 1 and I'm going to do: predict-no 6241ENV: Agent did: predict-no for direction U in state State-A 6242In State-A moving U 6243ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6244predict error 0 6245dir: dir isL 6246|\-870: O: O1740 (predict-no) 6247I see 1 and I'm going to do: predict-no 6248ENV: Agent did: predict-no for direction L in state State-A 6249In State-A moving L 6250ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6251predict error 0 6252dir: dir isL 6253/|\-871: O: O1742 (predict-no) 6254I see 1 and I'm going to do: predict-no 6255ENV: Agent did: predict-no for direction L in state State-A 6256In State-A moving L 6257ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6258predict error 0 6259dir: dir isL 6260/872: O: O1744 (predict-no) 6261I see 1 and I'm going to do: predict-no 6262ENV: Agent did: predict-no for direction L in state State-A 6263In State-A moving L 6264ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6265predict error 0 6266dir: dir isU 6267|\-873: O: O1746 (predict-no) 6268I see 1 and I'm going to do: predict-no 6269ENV: Agent did: predict-no for direction U in state State-A 6270In State-A moving U 6271ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6272predict error 0 6273dir: dir isU 6274/|\874: O: O1748 (predict-no) 6275I see 1 and I'm going to do: predict-no 6276ENV: Agent did: predict-no for direction U in state State-A 6277In State-A moving U 6278ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6279predict error 0 6280dir: dir isU 6281-/875: O: O1750 (predict-no) 6282I see 1 and I'm going to do: predict-no 6283ENV: Agent did: predict-no for direction U in state State-A 6284In State-A moving U 6285ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6286predict error 0 6287dir: dir isR 6288|\876: O: O1751 (predict-yes) 6289I see 1 and I'm going to do: predict-yes 6290ENV: Agent did: predict-yes for direction R in state State-A 6291In State-A moving R 6292ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6293predict error 0 6294dir: dir isR 6295-/|877: O: O1754 (predict-no) 6296I see 1 and I'm going to do: predict-no 6297ENV: Agent did: predict-no for direction R in state State-B 6298In State-B moving R 6299ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6300predict error 0 6301dir: dir isR 6302\878: O: O1756 (predict-no) 6303I see 1 and I'm going to do: predict-no 6304ENV: Agent did: predict-no for direction R in state State-B 6305In State-B moving R 6306ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6307predict error 0 6308dir: dir isR 6309-/|879: O: O1758 (predict-no) 6310I see 1 and I'm going to do: predict-no 6311ENV: Agent did: predict-no for direction R in state State-B 6312In State-B moving R 6313ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6314predict error 0 6315dir: dir isR 6316\-/880: O: O1760 (predict-no) 6317I see 1 and I'm going to do: predict-no 6318ENV: Agent did: predict-no for direction R in state State-B 6319In State-B moving R 6320ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6321predict error 0 6322dir: dir isU 6323|\-881: O: O1762 (predict-no) 6324I see 1 and I'm going to do: predict-no 6325ENV: Agent did: predict-no for direction U in state State-B 6326In State-B moving U 6327ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6328predict error 0 6329dir: dir isU 6330/882: O: O1764 (predict-no) 6331I see 1 and I'm going to do: predict-no 6332ENV: Agent did: predict-no for direction U in state State-B 6333In State-B moving U 6334ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6335predict error 0 6336dir: dir isR 6337|\-883: O: O1766 (predict-no) 6338I see 1 and I'm going to do: predict-no 6339ENV: Agent did: predict-no for direction R in state State-B 6340In State-B moving R 6341ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6342predict error 0 6343dir: dir isR 6344/|\884: O: O1768 (predict-no) 6345I see 1 and I'm going to do: predict-no 6346ENV: Agent did: predict-no for direction R in state State-B 6347In State-B moving R 6348ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6349predict error 0 6350dir: dir isL 6351-/|885: O: O1769 (predict-yes) 6352I see 1 and I'm going to do: predict-yes 6353ENV: Agent did: predict-yes for direction L in state State-B 6354In State-B moving L 6355ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6356predict error 0 6357dir: dir isL 6358\-/886: O: O1772 (predict-no) 6359I see 1 and I'm going to do: predict-no 6360ENV: Agent did: predict-no for direction L in state State-A 6361In State-A moving L 6362ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6363predict error 0 6364dir: dir isR 6365|\887: O: O1773 (predict-yes) 6366I see 1 and I'm going to do: predict-yes 6367ENV: Agent did: predict-yes for direction R in state State-A 6368In State-A moving R 6369ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6370predict error 0 6371dir: dir isR 6372-/|888: O: O1776 (predict-no) 6373I see 1 and I'm going to do: predict-no 6374ENV: Agent did: predict-no for direction R in state State-B 6375In State-B moving R 6376ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6377predict error 0 6378dir: dir isR 6379\-/889: O: O1778 (predict-no) 6380I see 1 and I'm going to do: predict-no 6381ENV: Agent did: predict-no for direction R in state State-B 6382In State-B moving R 6383ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6384predict error 0 6385dir: dir isU 6386|\-890: O: O1780 (predict-no) 6387I see 1 and I'm going to do: predict-no 6388ENV: Agent did: predict-no for direction U in state State-B 6389In State-B moving U 6390ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6391predict error 0 6392dir: dir isL 6393/|891: O: O1781 (predict-yes) 6394I see 1 and I'm going to do: predict-yes 6395ENV: Agent did: predict-yes for direction L in state State-B 6396In State-B moving L 6397ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6398predict error 0 6399dir: dir isR 6400\892: O: O1783 (predict-yes) 6401I see 1 and I'm going to do: predict-yes 6402ENV: Agent did: predict-yes for direction R in state State-A 6403In State-A moving R 6404ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6405predict error 0 6406dir: dir isU 6407-/|893: O: O1786 (predict-no) 6408I see 1 and I'm going to do: predict-no 6409ENV: Agent did: predict-no for direction U in state State-B 6410In State-B moving U 6411ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6412predict error 0 6413dir: dir isU 6414\894: O: O1788 (predict-no) 6415I see 1 and I'm going to do: predict-no 6416ENV: Agent did: predict-no for direction U in state State-B 6417In State-B moving U 6418ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6419predict error 0 6420dir: dir isR 6421-/|895: O: O1790 (predict-no) 6422I see 1 and I'm going to do: predict-no 6423ENV: Agent did: predict-no for direction R in state State-B 6424In State-B moving R 6425ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6426predict error 0 6427dir: dir isR 6428\-/896: O: O1792 (predict-no) 6429I see 1 and I'm going to do: predict-no 6430ENV: Agent did: predict-no for direction R in state State-B 6431In State-B moving R 6432ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6433predict error 0 6434dir: dir isR 6435|\-897: O: O1794 (predict-no) 6436I see 1 and I'm going to do: predict-no 6437ENV: Agent did: predict-no for direction R in state State-B 6438In State-B moving R 6439ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6440predict error 0 6441dir: dir isU 6442/|\898: O: O1796 (predict-no) 6443I see 1 and I'm going to do: predict-no 6444ENV: Agent did: predict-no for direction U in state State-B 6445In State-B moving U 6446ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6447predict error 0 6448dir: dir isU 6449-/|899: O: O1798 (predict-no) 6450I see 1 and I'm going to do: predict-no 6451ENV: Agent did: predict-no for direction U in state State-B 6452In State-B moving U 6453ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6454predict error 0 6455dir: dir isU 6456\-/900: O: O1800 (predict-no) 6457I see 1 and I'm going to do: predict-no 6458ENV: Agent did: predict-no for direction U in state State-B 6459In State-B moving U 6460ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6461predict error 0 6462dir: dir isU 6463|\-901: O: O1802 (predict-no) 6464I see 1 and I'm going to do: predict-no 6465ENV: Agent did: predict-no for direction U in state State-B 6466In State-B moving U 6467ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6468predict error 0 6469dir: dir isU 6470/902: O: O1804 (predict-no) 6471I see 1 and I'm going to do: predict-no 6472ENV: Agent did: predict-no for direction U in state State-B 6473In State-B moving U 6474ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6475predict error 0 6476dir: dir isU 6477|\903: O: O1806 (predict-no) 6478I see 1 and I'm going to do: predict-no 6479ENV: Agent did: predict-no for direction U in state State-B 6480In State-B moving U 6481ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6482predict error 0 6483dir: dir isR 6484-/904: O: O1808 (predict-no) 6485I see 1 and I'm going to do: predict-no 6486ENV: Agent did: predict-no for direction R in state State-B 6487In State-B moving R 6488ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6489predict error 0 6490dir: dir isR 6491|\-905: O: O1810 (predict-no) 6492I see 1 and I'm going to do: predict-no 6493ENV: Agent did: predict-no for direction R in state State-B 6494In State-B moving R 6495ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6496predict error 0 6497dir: dir isU 6498/|\906: O: O1812 (predict-no) 6499I see 1 and I'm going to do: predict-no 6500ENV: Agent did: predict-no for direction U in state State-B 6501In State-B moving U 6502ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6503predict error 0 6504dir: dir isR 6505-/|907: O: O1814 (predict-no) 6506I see 1 and I'm going to do: predict-no 6507ENV: Agent did: predict-no for direction R in state State-B 6508In State-B moving R 6509ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6510predict error 0 6511dir: dir isU 6512\-/908: O: O1816 (predict-no) 6513I see 1 and I'm going to do: predict-no 6514ENV: Agent did: predict-no for direction U in state State-B 6515In State-B moving U 6516ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6517predict error 0 6518dir: dir isR 6519|\909: O: O1818 (predict-no) 6520I see 1 and I'm going to do: predict-no 6521ENV: Agent did: predict-no for direction R in state State-B 6522In State-B moving R 6523ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6524predict error 0 6525dir: dir isR 6526-/|910: O: O1820 (predict-no) 6527I see 1 and I'm going to do: predict-no 6528ENV: Agent did: predict-no for direction R in state State-B 6529In State-B moving R 6530ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6531predict error 0 6532dir: dir isR 6533\-/911: O: O1822 (predict-no) 6534I see 1 and I'm going to do: predict-no 6535ENV: Agent did: predict-no for direction R in state State-B 6536In State-B moving R 6537ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6538predict error 0 6539dir: dir isL 6540|912: O: O1823 (predict-yes) 6541I see 1 and I'm going to do: predict-yes 6542ENV: Agent did: predict-yes for direction L in state State-B 6543In State-B moving L 6544ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6545predict error 0 6546dir: dir isR 6547\913: O: O1825 (predict-yes) 6548I see 1 and I'm going to do: predict-yes 6549ENV: Agent did: predict-yes for direction R in state State-A 6550In State-A moving R 6551ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6552predict error 0 6553dir: dir isR 6554-/|914: O: O1828 (predict-no) 6555I see 1 and I'm going to do: predict-no 6556ENV: Agent did: predict-no for direction R in state State-B 6557In State-B moving R 6558ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6559predict error 0 6560dir: dir isL 6561\-/915: O: O1829 (predict-yes) 6562I see 1 and I'm going to do: predict-yes 6563ENV: Agent did: predict-yes for direction L in state State-B 6564In State-B moving L 6565ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6566predict error 0 6567dir: dir isL 6568|\-916: O: O1832 (predict-no) 6569I see 1 and I'm going to do: predict-no 6570ENV: Agent did: predict-no for direction L in state State-A 6571In State-A moving L 6572ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6573predict error 0 6574dir: dir isL 6575/|\917: O: O1834 (predict-no) 6576I see 1 and I'm going to do: predict-no 6577ENV: Agent did: predict-no for direction L in state State-A 6578In State-A moving L 6579ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6580predict error 0 6581dir: dir isU 6582-/918: O: O1836 (predict-no) 6583I see 1 and I'm going to do: predict-no 6584ENV: Agent did: predict-no for direction U in state State-A 6585In State-A moving U 6586ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6587predict error 0 6588dir: dir isR 6589|\-919: O: O1837 (predict-yes) 6590I see 1 and I'm going to do: predict-yes 6591ENV: Agent did: predict-yes for direction R in state State-A 6592In State-A moving R 6593ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6594predict error 0 6595dir: dir isL 6596/|\920: O: O1839 (predict-yes) 6597I see 1 and I'm going to do: predict-yes 6598ENV: Agent did: predict-yes for direction L in state State-B 6599In State-B moving L 6600ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6601predict error 0 6602dir: dir isU 6603-/|921: O: O1842 (predict-no) 6604I see 1 and I'm going to do: predict-no 6605ENV: Agent did: predict-no for direction U in state State-A 6606In State-A moving U 6607ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6608predict error 0 6609dir: dir isL 6610\922: O: O1844 (predict-no) 6611I see 1 and I'm going to do: predict-no 6612ENV: Agent did: predict-no for direction L in state State-A 6613In State-A moving L 6614ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6615predict error 0 6616dir: dir isR 6617-/923: O: O1845 (predict-yes) 6618I see 1 and I'm going to do: predict-yes 6619ENV: Agent did: predict-yes for direction R in state State-A 6620In State-A moving R 6621ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6622predict error 0 6623dir: dir isU 6624|\-924: O: O1848 (predict-no) 6625I see 1 and I'm going to do: predict-no 6626ENV: Agent did: predict-no for direction U in state State-B 6627In State-B moving U 6628ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6629predict error 0 6630dir: dir isU 6631/|\925: O: O1850 (predict-no) 6632I see 1 and I'm going to do: predict-no 6633ENV: Agent did: predict-no for direction U in state State-B 6634In State-B moving U 6635ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6636predict error 0 6637dir: dir isR 6638-/|926: O: O1852 (predict-no) 6639I see 1 and I'm going to do: predict-no 6640ENV: Agent did: predict-no for direction R in state State-B 6641In State-B moving R 6642ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6643predict error 0 6644dir: dir isU 6645\-/927: O: O1854 (predict-no) 6646I see 1 and I'm going to do: predict-no 6647ENV: Agent did: predict-no for direction U in state State-B 6648In State-B moving U 6649ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6650predict error 0 6651dir: dir isR 6652|\-928: O: O1856 (predict-no) 6653I see 1 and I'm going to do: predict-no 6654ENV: Agent did: predict-no for direction R in state State-B 6655In State-B moving R 6656ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6657predict error 0 6658dir: dir isU 6659/|929: O: O1858 (predict-no) 6660I see 1 and I'm going to do: predict-no 6661ENV: Agent did: predict-no for direction U in state State-B 6662In State-B moving U 6663ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6664predict error 0 6665dir: dir isR 6666\-/930: O: O1860 (predict-no) 6667I see 1 and I'm going to do: predict-no 6668ENV: Agent did: predict-no for direction R in state State-B 6669In State-B moving R 6670ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6671predict error 0 6672dir: dir isU 6673|\931: O: O1862 (predict-no) 6674I see 1 and I'm going to do: predict-no 6675ENV: Agent did: predict-no for direction U in state State-B 6676In State-B moving U 6677ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6678predict error 0 6679dir: dir isU 6680-932: O: O1864 (predict-no) 6681I see 1 and I'm going to do: predict-no 6682ENV: Agent did: predict-no for direction U in state State-B 6683In State-B moving U 6684ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6685predict error 0 6686dir: dir isL 6687/|\933: O: O1865 (predict-yes) 6688I see 1 and I'm going to do: predict-yes 6689ENV: Agent did: predict-yes for direction L in state State-B 6690In State-B moving L 6691ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6692predict error 0 6693dir: dir isL 6694-/|934: O: O1868 (predict-no) 6695I see 1 and I'm going to do: predict-no 6696ENV: Agent did: predict-no for direction L in state State-A 6697In State-A moving L 6698ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6699predict error 0 6700dir: dir isU 6701\-/935: O: O1870 (predict-no) 6702I see 1 and I'm going to do: predict-no 6703ENV: Agent did: predict-no for direction U in state State-A 6704In State-A moving U 6705ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6706predict error 0 6707dir: dir isL 6708|\936: O: O1872 (predict-no) 6709I see 1 and I'm going to do: predict-no 6710ENV: Agent did: predict-no for direction L in state State-A 6711In State-A moving L 6712ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6713predict error 0 6714dir: dir isL 6715-/|937: O: O1874 (predict-no) 6716I see 1 and I'm going to do: predict-no 6717ENV: Agent did: predict-no for direction L in state State-A 6718In State-A moving L 6719ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6720predict error 0 6721dir: dir isL 6722\-/938: O: O1876 (predict-no) 6723I see 1 and I'm going to do: predict-no 6724ENV: Agent did: predict-no for direction L in state State-A 6725In State-A moving L 6726ENV: (next state, see, prediction correct?) = (State-A, 0, True) 6727predict error 0 6728dir: dir isR 6729|939: O: O1877 (predict-yes) 6730I see 1 and I'm going to do: predict-yes 6731ENV: Agent did: predict-yes for direction R in state State-A 6732In State-A moving R 6733ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6734predict error 0 6735dir: dir isU 6736\-/940: O: O1880 (predict-no) 6737I see 1 and I'm going to do: predict-no 6738ENV: Agent did: predict-no for direction U in state State-B 6739In State-B moving U 6740ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6741predict error 0 6742dir: dir isR 6743|941: O: O1882 (predict-no) 6744I see 1 and I'm going to do: predict-no 6745ENV: Agent did: predict-no for direction R in state State-B 6746In State-B moving R 6747ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6748predict error 0 6749dir: dir isU 6750\942: O: O1884 (predict-no) 6751I see 1 and I'm going to do: predict-no 6752ENV: Agent did: predict-no for direction U in state State-B 6753In State-B moving U 6754ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6755predict error 0 6756dir: dir isU 6757-/|943: O: O1886 (predict-no) 6758I see 1 and I'm going to do: predict-no 6759ENV: Agent did: predict-no for direction U in state State-B 6760In State-B moving U 6761ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6762predict error 0 6763dir: dir isL 6764\944: O: O1887 (predict-yes) 6765I see 1 and I'm going to do: predict-yes 6766ENV: Agent did: predict-yes for direction L in state State-B 6767In State-B moving L 6768ENV: (next state, see, prediction correct?) = (State-A, 1, True) 6769predict error 0 6770dir: dir isR 6771-/|945: O: O1889 (predict-yes) 6772I see 1 and I'm going to do: predict-yes 6773ENV: Agent did: predict-yes for direction R in state State-A 6774In State-A moving R 6775ENV: (next state, see, prediction correct?) = (State-B, 1, True) 6776predict error 0 6777dir: dir isU 6778\-946: O: O1892 (predict-no) 6779I see 1 and I'm going to do: predict-no 6780ENV: Agent did: predict-no for direction U in state State-B 6781In State-B moving U 6782ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6783predict error 0 6784dir: dir isR 6785/|\947: O: O1894 (predict-no) 6786I see 1 and I'm going to do: predict-no 6787ENV: Agent did: predict-no for direction R in state State-B 6788In State-B moving R 6789ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6790predict error 0 6791dir: dir isR 6792-/|948: O: O1896 (predict-no) 6793I see 1 and I'm going to do: predict-no 6794ENV: Agent did: predict-no for direction R in state State-B 6795In State-B moving R 6796ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6797predict error 0 6798dir: dir isR 6799\-/949: O: O1898 (predict-no) 6800I see 1 and I'm going to do: predict-no 6801ENV: Agent did: predict-no for direction R in state State-B 6802In State-B moving R 6803ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6804predict error 0 6805dir: dir isU 6806|\-950: O: O1900 (predict-no) 6807I see 1 and I'm going to do: predict-no 6808ENV: Agent did: predict-no for direction U in state State-B 6809In State-B moving U 6810ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6811predict error 0 6812dir: dir isU 6813/|\-/|\-/--- Input Phase --- 6814=>WM: (13307: I2 ^dir U) 6815=>WM: (13306: I2 ^reward 1) 6816=>WM: (13305: I2 ^see 0) 6817=>WM: (13304: N950 ^status complete) 6818<=WM: (13293: I2 ^dir U) 6819<=WM: (13292: I2 ^reward 1) 6820<=WM: (13291: I2 ^see 0) 6821=>WM: (13308: I2 ^level-1 R0-root) 6822<=WM: (13294: I2 ^level-1 R0-root) 6823 6824--- END Input Phase --- 6825 6826--- Proposal Phase --- 6827 6828--- Inner Elaboration Phase, active level 1 (S1) --- 6829Firing elaborate*copy-see-to-output-link 6830 --> 6831 (I3 ^see 0 +) 6832Firing elaborate*reward*based*on*reward 6833 --> 6834 (R954 ^value 1 +) 6835 (R1 ^reward R954 +) 6836Firing propose*predict-yes 6837 --> 6838 (O1901 ^name predict-yes +) 6839 (S1 ^operator O1901 +) 6840Firing propose*predict-no 6841 --> 6842 (O1902 ^name predict-no +) 6843 (S1 ^operator O1902 +) 6844Firing rl*prefer*rvt*predict-no*H0*4 6845 --> 6846 (S1 ^operator O1900 = 1.) 6847Firing rl*prefer*rvt*predict-yes*H0*3 6848 --> 6849 (S1 ^operator O1899 = 0.) 6850Firing prefer*rvt*predict-yes*H0 6851 --> 6852Firing prefer*rvt*predict-no*H0 6853 --> 6854Firing elaborate*copy-dir-to-output-link 6855 --> 6856 (I3 ^dir U +) 6857 inner elaboration loop at bottom goal. 6858Retracting elaborate*copy-see-to-output-link 6859 --> 6860 (I3 ^see 0 +) 6861Retracting propose*predict-no 6862 --> 6863 (O1900 ^name predict-no +) 6864 (S1 ^operator O1900 +) 6865Retracting propose*predict-yes 6866 --> 6867 (O1899 ^name predict-yes +) 6868 (S1 ^operator O1899 +) 6869Retracting elaborate*reward*based*on*reward 6870 --> 6871 (R953 ^value 1 +) 6872 (R1 ^reward R953 +) 6873Retracting elaborate*copy-dir-to-output-link 6874 --> 6875 (I3 ^dir U +) 6876Retracting rl*prefer*rvt*predict-no*H0*4 6877 --> 6878 (S1 ^operator O1900 = 1.) 6879Retracting rl*prefer*rvt*predict-yes*H0*3 6880 --> 6881 (S1 ^operator O1899 = 0.) 6882=>WM: (13314: S1 ^operator O1902 +) 6883=>WM: (13313: S1 ^operator O1901 +) 6884=>WM: (13312: O1902 ^name predict-no) 6885=>WM: (13311: O1901 ^name predict-yes) 6886=>WM: (13310: R954 ^value 1) 6887=>WM: (13309: R1 ^reward R954) 6888<=WM: (13300: S1 ^operator O1899 +) 6889<=WM: (13301: S1 ^operator O1900 +) 6890<=WM: (13302: S1 ^operator O1900) 6891<=WM: (13295: R1 ^reward R953) 6892<=WM: (13298: O1900 ^name predict-no) 6893<=WM: (13297: O1899 ^name predict-yes) 6894<=WM: (13296: R953 ^value 1) 6895 6896--- Inner Elaboration Phase, active level 1 (S1) --- 6897Firing prefer*rvt*predict-yes*H0 6898 --> 6899Firing rl*prefer*rvt*predict-yes*H0*3 6900 --> 6901 (S1 ^operator O1901 = 0.) 6902Firing prefer*rvt*predict-no*H0 6903 --> 6904Firing rl*prefer*rvt*predict-no*H0*4 6905 --> 6906 (S1 ^operator O1902 = 1.) 6907 inner elaboration loop at bottom goal. 6908Retracting rl*prefer*rvt*predict-no*H0*4 6909 --> 6910 (S1 ^operator O1900 = 1.) 6911Retracting rl*prefer*rvt*predict-yes*H0*3 6912 --> 6913 (S1 ^operator O1899 = 0.) 6914 6915--- END Proposal Phase --- 6916 6917--- Decision Phase --- 6918RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 6919=>WM: (13315: S1 ^operator O1902) 6920 6921 951: O: O1902 (predict-no) 6922--- END Decision Phase --- 6923 6924--- Application Phase --- 6925 --- Firing Productions (PE) For State At Depth 1 --- 6926 6927--- Inner Elaboration Phase, active level 1 (S1) --- 6928Firing apply*operator 6929 --> 6930 (I3 ^predict-no N951 + :O ) 6931Firing apply*operator*complete 6932 --> 6933 (I3 ^predict-no N950 - :O ) 6934 inner elaboration loop at bottom goal. 6935 --- Change Working Memory (PE) --- 6936=>WM: (13316: I3 ^predict-no N951) 6937<=WM: (13304: N950 ^status complete) 6938<=WM: (13303: I3 ^predict-no N950) 6939 --- Firing Productions (IE) For State At Depth 1 --- 6940 6941--- Inner Elaboration Phase, active level 1 (S1) --- 6942Firing monitor*world 6943 --> 6944 6945I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 6946 --- Change Working Memory (IE) --- 6947 6948--- END Application Phase --- 6949--- Output Phase --- 6950ENV: Agent did: predict-no for direction U in state State-B 6951In State-B moving U 6952ENV: (next state, see, prediction correct?) = (State-B, 0, True) 6953predict error 0 6954dir: dir isL 6955--- END Output Phase --- 6956|--- Input Phase --- 6957=>WM: (13320: I2 ^dir L) 6958=>WM: (13319: I2 ^reward 1) 6959=>WM: (13318: I2 ^see 0) 6960=>WM: (13317: N951 ^status complete) 6961<=WM: (13307: I2 ^dir U) 6962<=WM: (13306: I2 ^reward 1) 6963<=WM: (13305: I2 ^see 0) 6964=>WM: (13321: I2 ^level-1 R0-root) 6965<=WM: (13308: I2 ^level-1 R0-root) 6966 6967--- END Input Phase --- 6968 6969--- Proposal Phase --- 6970 6971--- Inner Elaboration Phase, active level 1 (S1) --- 6972Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 6973 --> 6974 (S1 ^operator O1901 = 0.6195564468661043) 6975Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 6976 --> 6977 (S1 ^operator O1902 = -0.2190661556260421) 6978Firing prefer*rvt*predict-no*H0*2*v1*H1 6979 --> 6980Firing prefer*rvt*predict-yes*H0*1*v1*H1 6981 --> 6982Firing elaborate*copy-see-to-output-link 6983 --> 6984 (I3 ^see 0 +) 6985Firing elaborate*reward*based*on*reward 6986 --> 6987 (R955 ^value 1 +) 6988 (R1 ^reward R955 +) 6989Firing propose*predict-yes 6990 --> 6991 (O1903 ^name predict-yes +) 6992 (S1 ^operator O1903 +) 6993Firing propose*predict-no 6994 --> 6995 (O1904 ^name predict-no +) 6996 (S1 ^operator O1904 +) 6997Firing rl*prefer*rvt*predict-no*H0*2 6998 --> 6999 (S1 ^operator O1902 = 0.314040627026034) 7000Firing rl*prefer*rvt*predict-yes*H0*1 7001 --> 7002 (S1 ^operator O1901 = 0.3804224030022332) 7003Firing prefer*rvt*predict-yes*H0 7004 --> 7005Firing prefer*rvt*predict-no*H0 7006 --> 7007Firing elaborate*copy-dir-to-output-link 7008 --> 7009 (I3 ^dir L +) 7010 inner elaboration loop at bottom goal. 7011Retracting elaborate*copy-see-to-output-link 7012 --> 7013 (I3 ^see 0 +) 7014Retracting propose*predict-no 7015 --> 7016 (O1902 ^name predict-no +) 7017 (S1 ^operator O1902 +) 7018Retracting propose*predict-yes 7019 --> 7020 (O1901 ^name predict-yes +) 7021 (S1 ^operator O1901 +) 7022Retracting elaborate*reward*based*on*reward 7023 --> 7024 (R954 ^value 1 +) 7025 (R1 ^reward R954 +) 7026Retracting elaborate*copy-dir-to-output-link 7027 --> 7028 (I3 ^dir U +) 7029Retracting rl*prefer*rvt*predict-no*H0*4 7030 --> 7031 (S1 ^operator O1902 = 1.) 7032Retracting rl*prefer*rvt*predict-yes*H0*3 7033 --> 7034 (S1 ^operator O1901 = 0.) 7035=>WM: (13328: S1 ^operator O1904 +) 7036=>WM: (13327: S1 ^operator O1903 +) 7037=>WM: (13326: I3 ^dir L) 7038=>WM: (13325: O1904 ^name predict-no) 7039=>WM: (13324: O1903 ^name predict-yes) 7040=>WM: (13323: R955 ^value 1) 7041=>WM: (13322: R1 ^reward R955) 7042<=WM: (13313: S1 ^operator O1901 +) 7043<=WM: (13314: S1 ^operator O1902 +) 7044<=WM: (13315: S1 ^operator O1902) 7045<=WM: (13299: I3 ^dir U) 7046<=WM: (13309: R1 ^reward R954) 7047<=WM: (13312: O1902 ^name predict-no) 7048<=WM: (13311: O1901 ^name predict-yes) 7049<=WM: (13310: R954 ^value 1) 7050 7051--- Inner Elaboration Phase, active level 1 (S1) --- 7052Firing prefer*rvt*predict-yes*H0 7053 --> 7054Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7055 --> 7056 (S1 ^operator O1903 = 0.6195564468661043) 7057Firing rl*prefer*rvt*predict-yes*H0*1 7058 --> 7059 (S1 ^operator O1903 = 0.3804224030022332) 7060Firing prefer*rvt*predict-yes*H0*1*v1*H1 7061 --> 7062Firing prefer*rvt*predict-no*H0 7063 --> 7064Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7065 --> 7066 (S1 ^operator O1904 = -0.2190661556260421) 7067Firing rl*prefer*rvt*predict-no*H0*2 7068 --> 7069 (S1 ^operator O1904 = 0.314040627026034) 7070Firing prefer*rvt*predict-no*H0*2*v1*H1 7071 --> 7072 inner elaboration loop at bottom goal. 7073Retracting rl*prefer*rvt*predict-no*H0*2 7074 --> 7075 (S1 ^operator O1902 = 0.314040627026034) 7076Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7077 --> 7078 (S1 ^operator O1902 = -0.2190661556260421) 7079Retracting rl*prefer*rvt*predict-yes*H0*1 7080 --> 7081 (S1 ^operator O1901 = 0.3804224030022332) 7082Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7083 --> 7084 (S1 ^operator O1901 = 0.6195564468661043) 7085 7086--- END Proposal Phase --- 7087 7088--- Decision Phase --- 7089RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 7090=>WM: (13329: S1 ^operator O1903) 7091 7092 952: O: O1903 (predict-yes) 7093--- END Decision Phase --- 7094 7095--- Application Phase --- 7096 --- Firing Productions (PE) For State At Depth 1 --- 7097 7098--- Inner Elaboration Phase, active level 1 (S1) --- 7099Firing apply*operator 7100 --> 7101 (I3 ^predict-yes N952 + :O ) 7102Firing apply*operator*complete 7103 --> 7104 (I3 ^predict-no N951 - :O ) 7105 inner elaboration loop at bottom goal. 7106 --- Change Working Memory (PE) --- 7107=>WM: (13330: I3 ^predict-yes N952) 7108<=WM: (13317: N951 ^status complete) 7109<=WM: (13316: I3 ^predict-no N951) 7110 --- Firing Productions (IE) For State At Depth 1 --- 7111 7112--- Inner Elaboration Phase, active level 1 (S1) --- 7113Firing monitor*world 7114 --> 7115 7116I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 7117 --- Change Working Memory (IE) --- 7118 7119--- END Application Phase --- 7120--- Output Phase --- 7121ENV: Agent did: predict-yes for direction L in state State-B 7122In State-B moving L 7123ENV: (next state, see, prediction correct?) = (State-A, 1, True) 7124predict error 0 7125dir: dir isR 7126--- END Output Phase --- 7127\-/--- Input Phase --- 7128=>WM: (13334: I2 ^dir R) 7129=>WM: (13333: I2 ^reward 1) 7130=>WM: (13332: I2 ^see 1) 7131=>WM: (13331: N952 ^status complete) 7132<=WM: (13320: I2 ^dir L) 7133<=WM: (13319: I2 ^reward 1) 7134<=WM: (13318: I2 ^see 0) 7135=>WM: (13335: I2 ^level-1 L1-root) 7136<=WM: (13321: I2 ^level-1 R0-root) 7137 7138--- END Input Phase --- 7139 7140--- Proposal Phase --- 7141 7142--- Inner Elaboration Phase, active level 1 (S1) --- 7143Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 7144 --> 7145 (S1 ^operator O1903 = 0.7066224695034091) 7146Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 7147 --> 7148 (S1 ^operator O1904 = -0.1937987592593187) 7149Firing prefer*rvt*predict-no*H0*6*v1*H1 7150 --> 7151Firing prefer*rvt*predict-yes*H0*5*v1*H1 7152 --> 7153Firing elaborate*copy-see-to-output-link 7154 --> 7155 (I3 ^see 1 +) 7156Firing elaborate*reward*based*on*reward 7157 --> 7158 (R956 ^value 1 +) 7159 (R1 ^reward R956 +) 7160Firing propose*predict-yes 7161 --> 7162 (O1905 ^name predict-yes +) 7163 (S1 ^operator O1905 +) 7164Firing propose*predict-no 7165 --> 7166 (O1906 ^name predict-no +) 7167 (S1 ^operator O1906 +) 7168Firing rl*prefer*rvt*predict-no*H0*6 7169 --> 7170 (S1 ^operator O1904 = 0.2298785768141863) 7171Firing rl*prefer*rvt*predict-yes*H0*5 7172 --> 7173 (S1 ^operator O1903 = 0.2940444083423254) 7174Firing prefer*rvt*predict-yes*H0 7175 --> 7176Firing prefer*rvt*predict-no*H0 7177 --> 7178Firing elaborate*copy-dir-to-output-link 7179 --> 7180 (I3 ^dir R +) 7181 inner elaboration loop at bottom goal. 7182Retracting elaborate*copy-see-to-output-link 7183 --> 7184 (I3 ^see 0 +) 7185Retracting propose*predict-no 7186 --> 7187 (O1904 ^name predict-no +) 7188 (S1 ^operator O1904 +) 7189Retracting propose*predict-yes 7190 --> 7191 (O1903 ^name predict-yes +) 7192 (S1 ^operator O1903 +) 7193Retracting elaborate*reward*based*on*reward 7194 --> 7195 (R955 ^value 1 +) 7196 (R1 ^reward R955 +) 7197Retracting elaborate*copy-dir-to-output-link 7198 --> 7199 (I3 ^dir L +) 7200Retracting rl*prefer*rvt*predict-no*H0*2 7201 --> 7202 (S1 ^operator O1904 = 0.314040627026034) 7203Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7204 --> 7205 (S1 ^operator O1904 = -0.2190661556260421) 7206Retracting rl*prefer*rvt*predict-yes*H0*1 7207 --> 7208 (S1 ^operator O1903 = 0.3804224030022332) 7209Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7210 --> 7211 (S1 ^operator O1903 = 0.6195564468661043) 7212=>WM: (13343: S1 ^operator O1906 +) 7213=>WM: (13342: S1 ^operator O1905 +) 7214=>WM: (13341: I3 ^dir R) 7215=>WM: (13340: O1906 ^name predict-no) 7216=>WM: (13339: O1905 ^name predict-yes) 7217=>WM: (13338: R956 ^value 1) 7218=>WM: (13337: R1 ^reward R956) 7219=>WM: (13336: I3 ^see 1) 7220<=WM: (13327: S1 ^operator O1903 +) 7221<=WM: (13329: S1 ^operator O1903) 7222<=WM: (13328: S1 ^operator O1904 +) 7223<=WM: (13326: I3 ^dir L) 7224<=WM: (13322: R1 ^reward R955) 7225<=WM: (13254: I3 ^see 0) 7226<=WM: (13325: O1904 ^name predict-no) 7227<=WM: (13324: O1903 ^name predict-yes) 7228<=WM: (13323: R955 ^value 1) 7229 7230--- Inner Elaboration Phase, active level 1 (S1) --- 7231Firing prefer*rvt*predict-yes*H0 7232 --> 7233Firing rl*prefer*rvt*predict-yes*H0*5 7234 --> 7235 (S1 ^operator O1905 = 0.2940444083423254) 7236Firing prefer*rvt*predict-yes*H0*5*v1*H1 7237 --> 7238Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 7239 --> 7240 (S1 ^operator O1905 = 0.7066224695034091) 7241Firing prefer*rvt*predict-no*H0 7242 --> 7243Firing rl*prefer*rvt*predict-no*H0*6 7244 --> 7245 (S1 ^operator O1906 = 0.2298785768141863) 7246Firing prefer*rvt*predict-no*H0*6*v1*H1 7247 --> 7248Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 7249 --> 7250 (S1 ^operator O1906 = -0.1937987592593187) 7251 inner elaboration loop at bottom goal. 7252Retracting rl*prefer*rvt*predict-no*H0*6 7253 --> 7254 (S1 ^operator O1904 = 0.2298785768141863) 7255Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 7256 --> 7257 (S1 ^operator O1904 = -0.1937987592593187) 7258Retracting rl*prefer*rvt*predict-yes*H0*5 7259 --> 7260 (S1 ^operator O1903 = 0.2940444083423254) 7261Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 7262 --> 7263 (S1 ^operator O1903 = 0.7066224695034091) 7264 7265--- END Proposal Phase --- 7266 7267--- Decision Phase --- 7268RL update rl*prefer*rvt*predict-yes*H0*1 0.521353 -0.140931 0.380422 -> 0.521355 -0.140931 0.380424(R,m,v=1,0.819355,0.148974) 7269RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478624 0.140933 0.619556 -> 0.478626 0.140932 0.619559(R,m,v=1,1,0) 7270=>WM: (13344: S1 ^operator O1905) 7271 7272 953: O: O1905 (predict-yes) 7273--- END Decision Phase --- 7274 7275--- Application Phase --- 7276 --- Firing Productions (PE) For State At Depth 1 --- 7277 7278--- Inner Elaboration Phase, active level 1 (S1) --- 7279Firing apply*operator 7280 --> 7281 (I3 ^predict-yes N953 + :O ) 7282Firing apply*operator*complete 7283 --> 7284 (I3 ^predict-yes N952 - :O ) 7285 inner elaboration loop at bottom goal. 7286 --- Change Working Memory (PE) --- 7287=>WM: (13345: I3 ^predict-yes N953) 7288<=WM: (13331: N952 ^status complete) 7289<=WM: (13330: I3 ^predict-yes N952) 7290 --- Firing Productions (IE) For State At Depth 1 --- 7291 7292--- Inner Elaboration Phase, active level 1 (S1) --- 7293Firing monitor*world 7294 --> 7295 7296I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 7297 --- Change Working Memory (IE) --- 7298 7299--- END Application Phase --- 7300--- Output Phase --- 7301ENV: Agent did: predict-yes for direction R in state State-A 7302In State-A moving R 7303ENV: (next state, see, prediction correct?) = (State-B, 1, True) 7304predict error 0 7305dir: dir isR 7306--- END Output Phase --- 7307|\---- Input Phase --- 7308=>WM: (13349: I2 ^dir R) 7309=>WM: (13348: I2 ^reward 1) 7310=>WM: (13347: I2 ^see 1) 7311=>WM: (13346: N953 ^status complete) 7312<=WM: (13334: I2 ^dir R) 7313<=WM: (13333: I2 ^reward 1) 7314<=WM: (13332: I2 ^see 1) 7315=>WM: (13350: I2 ^level-1 R1-root) 7316<=WM: (13335: I2 ^level-1 L1-root) 7317 7318--- END Input Phase --- 7319 7320--- Proposal Phase --- 7321 7322--- Inner Elaboration Phase, active level 1 (S1) --- 7323Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 7324 --> 7325 (S1 ^operator O1905 = -0.252585164213872) 7326Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 7327 --> 7328 (S1 ^operator O1906 = 0.7702047625716166) 7329Firing prefer*rvt*predict-no*H0*6*v1*H1 7330 --> 7331Firing prefer*rvt*predict-yes*H0*5*v1*H1 7332 --> 7333Firing elaborate*copy-see-to-output-link 7334 --> 7335 (I3 ^see 1 +) 7336Firing elaborate*reward*based*on*reward 7337 --> 7338 (R957 ^value 1 +) 7339 (R1 ^reward R957 +) 7340Firing propose*predict-yes 7341 --> 7342 (O1907 ^name predict-yes +) 7343 (S1 ^operator O1907 +) 7344Firing propose*predict-no 7345 --> 7346 (O1908 ^name predict-no +) 7347 (S1 ^operator O1908 +) 7348Firing rl*prefer*rvt*predict-no*H0*6 7349 --> 7350 (S1 ^operator O1906 = 0.2298785768141863) 7351Firing rl*prefer*rvt*predict-yes*H0*5 7352 --> 7353 (S1 ^operator O1905 = 0.2940444083423254) 7354Firing prefer*rvt*predict-yes*H0 7355 --> 7356Firing prefer*rvt*predict-no*H0 7357 --> 7358Firing elaborate*copy-dir-to-output-link 7359 --> 7360 (I3 ^dir R +) 7361 inner elaboration loop at bottom goal. 7362Retracting elaborate*copy-see-to-output-link 7363 --> 7364 (I3 ^see 1 +) 7365Retracting propose*predict-no 7366 --> 7367 (O1906 ^name predict-no +) 7368 (S1 ^operator O1906 +) 7369Retracting propose*predict-yes 7370 --> 7371 (O1905 ^name predict-yes +) 7372 (S1 ^operator O1905 +) 7373Retracting elaborate*reward*based*on*reward 7374 --> 7375 (R956 ^value 1 +) 7376 (R1 ^reward R956 +) 7377Retracting elaborate*copy-dir-to-output-link 7378 --> 7379 (I3 ^dir R +) 7380Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 7381 --> 7382 (S1 ^operator O1906 = -0.1937987592593187) 7383Retracting rl*prefer*rvt*predict-no*H0*6 7384 --> 7385 (S1 ^operator O1906 = 0.2298785768141863) 7386Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 7387 --> 7388 (S1 ^operator O1905 = 0.7066224695034091) 7389Retracting rl*prefer*rvt*predict-yes*H0*5 7390 --> 7391 (S1 ^operator O1905 = 0.2940444083423254) 7392=>WM: (13356: S1 ^operator O1908 +) 7393=>WM: (13355: S1 ^operator O1907 +) 7394=>WM: (13354: O1908 ^name predict-no) 7395=>WM: (13353: O1907 ^name predict-yes) 7396=>WM: (13352: R957 ^value 1) 7397=>WM: (13351: R1 ^reward R957) 7398<=WM: (13342: S1 ^operator O1905 +) 7399<=WM: (13344: S1 ^operator O1905) 7400<=WM: (13343: S1 ^operator O1906 +) 7401<=WM: (13337: R1 ^reward R956) 7402<=WM: (13340: O1906 ^name predict-no) 7403<=WM: (13339: O1905 ^name predict-yes) 7404<=WM: (13338: R956 ^value 1) 7405 7406--- Inner Elaboration Phase, active level 1 (S1) --- 7407Firing prefer*rvt*predict-yes*H0 7408 --> 7409Firing rl*prefer*rvt*predict-yes*H0*5 7410 --> 7411 (S1 ^operator O1907 = 0.2940444083423254) 7412Firing prefer*rvt*predict-yes*H0*5*v1*H1 7413 --> 7414Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 7415 --> 7416 (S1 ^operator O1907 = -0.252585164213872) 7417Firing prefer*rvt*predict-no*H0 7418 --> 7419Firing rl*prefer*rvt*predict-no*H0*6 7420 --> 7421 (S1 ^operator O1908 = 0.2298785768141863) 7422Firing prefer*rvt*predict-no*H0*6*v1*H1 7423 --> 7424Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 7425 --> 7426 (S1 ^operator O1908 = 0.7702047625716166) 7427 inner elaboration loop at bottom goal. 7428Retracting rl*prefer*rvt*predict-no*H0*6 7429 --> 7430 (S1 ^operator O1906 = 0.2298785768141863) 7431Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 7432 --> 7433 (S1 ^operator O1906 = 0.7702047625716166) 7434Retracting rl*prefer*rvt*predict-yes*H0*5 7435 --> 7436 (S1 ^operator O1905 = 0.2940444083423254) 7437Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 7438 --> 7439 (S1 ^operator O1905 = -0.252585164213872) 7440 7441--- END Proposal Phase --- 7442 7443--- Decision Phase --- 7444RL update rl*prefer*rvt*predict-yes*H0*5 0.501112 -0.207068 0.294044 -> 0.501062 -0.207073 0.293989(R,m,v=1,0.835616,0.138309) 7445RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499487 0.207136 0.706622 -> 0.499427 0.207129 0.706557(R,m,v=1,1,0) 7446=>WM: (13357: S1 ^operator O1908) 7447 7448 954: O: O1908 (predict-no) 7449--- END Decision Phase --- 7450 7451--- Application Phase --- 7452 --- Firing Productions (PE) For State At Depth 1 --- 7453 7454--- Inner Elaboration Phase, active level 1 (S1) --- 7455Firing apply*operator 7456 --> 7457 (I3 ^predict-no N954 + :O ) 7458Firing apply*operator*complete 7459 --> 7460 (I3 ^predict-yes N953 - :O ) 7461 inner elaboration loop at bottom goal. 7462 --- Change Working Memory (PE) --- 7463=>WM: (13358: I3 ^predict-no N954) 7464<=WM: (13346: N953 ^status complete) 7465<=WM: (13345: I3 ^predict-yes N953) 7466 --- Firing Productions (IE) For State At Depth 1 --- 7467 7468--- Inner Elaboration Phase, active level 1 (S1) --- 7469Firing monitor*world 7470 --> 7471 7472I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 7473 --- Change Working Memory (IE) --- 7474 7475--- END Application Phase --- 7476--- Output Phase --- 7477ENV: Agent did: predict-no for direction R in state State-B 7478In State-B moving R 7479ENV: (next state, see, prediction correct?) = (State-B, 0, True) 7480predict error 0 7481dir: dir isU 7482--- END Output Phase --- 7483/|\--- Input Phase --- 7484=>WM: (13362: I2 ^dir U) 7485=>WM: (13361: I2 ^reward 1) 7486=>WM: (13360: I2 ^see 0) 7487=>WM: (13359: N954 ^status complete) 7488<=WM: (13349: I2 ^dir R) 7489<=WM: (13348: I2 ^reward 1) 7490<=WM: (13347: I2 ^see 1) 7491=>WM: (13363: I2 ^level-1 R0-root) 7492<=WM: (13350: I2 ^level-1 R1-root) 7493 7494--- END Input Phase --- 7495 7496--- Proposal Phase --- 7497 7498--- Inner Elaboration Phase, active level 1 (S1) --- 7499Firing elaborate*copy-see-to-output-link 7500 --> 7501 (I3 ^see 0 +) 7502Firing elaborate*reward*based*on*reward 7503 --> 7504 (R958 ^value 1 +) 7505 (R1 ^reward R958 +) 7506Firing propose*predict-yes 7507 --> 7508 (O1909 ^name predict-yes +) 7509 (S1 ^operator O1909 +) 7510Firing propose*predict-no 7511 --> 7512 (O1910 ^name predict-no +) 7513 (S1 ^operator O1910 +) 7514Firing rl*prefer*rvt*predict-no*H0*4 7515 --> 7516 (S1 ^operator O1908 = 1.) 7517Firing rl*prefer*rvt*predict-yes*H0*3 7518 --> 7519 (S1 ^operator O1907 = 0.) 7520Firing prefer*rvt*predict-yes*H0 7521 --> 7522Firing prefer*rvt*predict-no*H0 7523 --> 7524Firing elaborate*copy-dir-to-output-link 7525 --> 7526 (I3 ^dir U +) 7527 inner elaboration loop at bottom goal. 7528Retracting elaborate*copy-see-to-output-link 7529 --> 7530 (I3 ^see 1 +) 7531Retracting propose*predict-no 7532 --> 7533 (O1908 ^name predict-no +) 7534 (S1 ^operator O1908 +) 7535Retracting propose*predict-yes 7536 --> 7537 (O1907 ^name predict-yes +) 7538 (S1 ^operator O1907 +) 7539Retracting elaborate*reward*based*on*reward 7540 --> 7541 (R957 ^value 1 +) 7542 (R1 ^reward R957 +) 7543Retracting elaborate*copy-dir-to-output-link 7544 --> 7545 (I3 ^dir R +) 7546Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 7547 --> 7548 (S1 ^operator O1908 = 0.7702047625716166) 7549Retracting rl*prefer*rvt*predict-no*H0*6 7550 --> 7551 (S1 ^operator O1908 = 0.2298785768141863) 7552Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 7553 --> 7554 (S1 ^operator O1907 = -0.252585164213872) 7555Retracting rl*prefer*rvt*predict-yes*H0*5 7556 --> 7557 (S1 ^operator O1907 = 0.2939886829338975) 7558=>WM: (13371: S1 ^operator O1910 +) 7559=>WM: (13370: S1 ^operator O1909 +) 7560=>WM: (13369: I3 ^dir U) 7561=>WM: (13368: O1910 ^name predict-no) 7562=>WM: (13367: O1909 ^name predict-yes) 7563=>WM: (13366: R958 ^value 1) 7564=>WM: (13365: R1 ^reward R958) 7565=>WM: (13364: I3 ^see 0) 7566<=WM: (13355: S1 ^operator O1907 +) 7567<=WM: (13356: S1 ^operator O1908 +) 7568<=WM: (13357: S1 ^operator O1908) 7569<=WM: (13341: I3 ^dir R) 7570<=WM: (13351: R1 ^reward R957) 7571<=WM: (13336: I3 ^see 1) 7572<=WM: (13354: O1908 ^name predict-no) 7573<=WM: (13353: O1907 ^name predict-yes) 7574<=WM: (13352: R957 ^value 1) 7575 7576--- Inner Elaboration Phase, active level 1 (S1) --- 7577Firing prefer*rvt*predict-yes*H0 7578 --> 7579Firing rl*prefer*rvt*predict-yes*H0*3 7580 --> 7581 (S1 ^operator O1909 = 0.) 7582Firing prefer*rvt*predict-no*H0 7583 --> 7584Firing rl*prefer*rvt*predict-no*H0*4 7585 --> 7586 (S1 ^operator O1910 = 1.) 7587 inner elaboration loop at bottom goal. 7588Retracting rl*prefer*rvt*predict-no*H0*4 7589 --> 7590 (S1 ^operator O1908 = 1.) 7591Retracting rl*prefer*rvt*predict-yes*H0*3 7592 --> 7593 (S1 ^operator O1907 = 0.) 7594 7595--- END Proposal Phase --- 7596 7597--- Decision Phase --- 7598RL update rl*prefer*rvt*predict-no*H0*6 0.611927 -0.382049 0.229879 -> 0.611922 -0.38205 0.229872(R,m,v=1,0.842105,0.133746) 7599RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.388141 0.382064 0.770205 -> 0.388134 0.382063 0.770196(R,m,v=1,1,0) 7600=>WM: (13372: S1 ^operator O1910) 7601 7602 955: O: O1910 (predict-no) 7603--- END Decision Phase --- 7604 7605--- Application Phase --- 7606 --- Firing Productions (PE) For State At Depth 1 --- 7607 7608--- Inner Elaboration Phase, active level 1 (S1) --- 7609Firing apply*operator 7610 --> 7611 (I3 ^predict-no N955 + :O ) 7612Firing apply*operator*complete 7613 --> 7614 (I3 ^predict-no N954 - :O ) 7615 inner elaboration loop at bottom goal. 7616 --- Change Working Memory (PE) --- 7617=>WM: (13373: I3 ^predict-no N955) 7618<=WM: (13359: N954 ^status complete) 7619<=WM: (13358: I3 ^predict-no N954) 7620 --- Firing Productions (IE) For State At Depth 1 --- 7621 7622--- Inner Elaboration Phase, active level 1 (S1) --- 7623Firing monitor*world 7624 --> 7625 7626I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 7627 --- Change Working Memory (IE) --- 7628 7629--- END Application Phase --- 7630--- Output Phase --- 7631ENV: Agent did: predict-no for direction U in state State-B 7632In State-B moving U 7633ENV: (next state, see, prediction correct?) = (State-B, 0, True) 7634predict error 0 7635dir: dir isL 7636--- END Output Phase --- 7637-/|--- Input Phase --- 7638=>WM: (13377: I2 ^dir L) 7639=>WM: (13376: I2 ^reward 1) 7640=>WM: (13375: I2 ^see 0) 7641=>WM: (13374: N955 ^status complete) 7642<=WM: (13362: I2 ^dir U) 7643<=WM: (13361: I2 ^reward 1) 7644<=WM: (13360: I2 ^see 0) 7645=>WM: (13378: I2 ^level-1 R0-root) 7646<=WM: (13363: I2 ^level-1 R0-root) 7647 7648--- END Input Phase --- 7649 7650--- Proposal Phase --- 7651 7652--- Inner Elaboration Phase, active level 1 (S1) --- 7653Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7654 --> 7655 (S1 ^operator O1909 = 0.6195585094345952) 7656Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7657 --> 7658 (S1 ^operator O1910 = -0.2190661556260421) 7659Firing prefer*rvt*predict-no*H0*2*v1*H1 7660 --> 7661Firing prefer*rvt*predict-yes*H0*1*v1*H1 7662 --> 7663Firing elaborate*copy-see-to-output-link 7664 --> 7665 (I3 ^see 0 +) 7666Firing elaborate*reward*based*on*reward 7667 --> 7668 (R959 ^value 1 +) 7669 (R1 ^reward R959 +) 7670Firing propose*predict-yes 7671 --> 7672 (O1911 ^name predict-yes +) 7673 (S1 ^operator O1911 +) 7674Firing propose*predict-no 7675 --> 7676 (O1912 ^name predict-no +) 7677 (S1 ^operator O1912 +) 7678Firing rl*prefer*rvt*predict-no*H0*2 7679 --> 7680 (S1 ^operator O1910 = 0.314040627026034) 7681Firing rl*prefer*rvt*predict-yes*H0*1 7682 --> 7683 (S1 ^operator O1909 = 0.3804241528486575) 7684Firing prefer*rvt*predict-yes*H0 7685 --> 7686Firing prefer*rvt*predict-no*H0 7687 --> 7688Firing elaborate*copy-dir-to-output-link 7689 --> 7690 (I3 ^dir L +) 7691 inner elaboration loop at bottom goal. 7692Retracting elaborate*copy-see-to-output-link 7693 --> 7694 (I3 ^see 0 +) 7695Retracting propose*predict-no 7696 --> 7697 (O1910 ^name predict-no +) 7698 (S1 ^operator O1910 +) 7699Retracting propose*predict-yes 7700 --> 7701 (O1909 ^name predict-yes +) 7702 (S1 ^operator O1909 +) 7703Retracting elaborate*reward*based*on*reward 7704 --> 7705 (R958 ^value 1 +) 7706 (R1 ^reward R958 +) 7707Retracting elaborate*copy-dir-to-output-link 7708 --> 7709 (I3 ^dir U +) 7710Retracting rl*prefer*rvt*predict-no*H0*4 7711 --> 7712 (S1 ^operator O1910 = 1.) 7713Retracting rl*prefer*rvt*predict-yes*H0*3 7714 --> 7715 (S1 ^operator O1909 = 0.) 7716=>WM: (13385: S1 ^operator O1912 +) 7717=>WM: (13384: S1 ^operator O1911 +) 7718=>WM: (13383: I3 ^dir L) 7719=>WM: (13382: O1912 ^name predict-no) 7720=>WM: (13381: O1911 ^name predict-yes) 7721=>WM: (13380: R959 ^value 1) 7722=>WM: (13379: R1 ^reward R959) 7723<=WM: (13370: S1 ^operator O1909 +) 7724<=WM: (13371: S1 ^operator O1910 +) 7725<=WM: (13372: S1 ^operator O1910) 7726<=WM: (13369: I3 ^dir U) 7727<=WM: (13365: R1 ^reward R958) 7728<=WM: (13368: O1910 ^name predict-no) 7729<=WM: (13367: O1909 ^name predict-yes) 7730<=WM: (13366: R958 ^value 1) 7731 7732--- Inner Elaboration Phase, active level 1 (S1) --- 7733Firing prefer*rvt*predict-yes*H0 7734 --> 7735Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7736 --> 7737 (S1 ^operator O1911 = 0.6195585094345952) 7738Firing rl*prefer*rvt*predict-yes*H0*1 7739 --> 7740 (S1 ^operator O1911 = 0.3804241528486575) 7741Firing prefer*rvt*predict-yes*H0*1*v1*H1 7742 --> 7743Firing prefer*rvt*predict-no*H0 7744 --> 7745Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7746 --> 7747 (S1 ^operator O1912 = -0.2190661556260421) 7748Firing rl*prefer*rvt*predict-no*H0*2 7749 --> 7750 (S1 ^operator O1912 = 0.314040627026034) 7751Firing prefer*rvt*predict-no*H0*2*v1*H1 7752 --> 7753 inner elaboration loop at bottom goal. 7754Retracting rl*prefer*rvt*predict-no*H0*2 7755 --> 7756 (S1 ^operator O1910 = 0.314040627026034) 7757Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7758 --> 7759 (S1 ^operator O1910 = -0.2190661556260421) 7760Retracting rl*prefer*rvt*predict-yes*H0*1 7761 --> 7762 (S1 ^operator O1909 = 0.3804241528486575) 7763Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7764 --> 7765 (S1 ^operator O1909 = 0.6195585094345952) 7766 7767--- END Proposal Phase --- 7768 7769--- Decision Phase --- 7770RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 7771=>WM: (13386: S1 ^operator O1911) 7772 7773 956: O: O1911 (predict-yes) 7774--- END Decision Phase --- 7775 7776--- Application Phase --- 7777 --- Firing Productions (PE) For State At Depth 1 --- 7778 7779--- Inner Elaboration Phase, active level 1 (S1) --- 7780Firing apply*operator 7781 --> 7782 (I3 ^predict-yes N956 + :O ) 7783Firing apply*operator*complete 7784 --> 7785 (I3 ^predict-no N955 - :O ) 7786 inner elaboration loop at bottom goal. 7787 --- Change Working Memory (PE) --- 7788=>WM: (13387: I3 ^predict-yes N956) 7789<=WM: (13374: N955 ^status complete) 7790<=WM: (13373: I3 ^predict-no N955) 7791 --- Firing Productions (IE) For State At Depth 1 --- 7792 7793--- Inner Elaboration Phase, active level 1 (S1) --- 7794Firing monitor*world 7795 --> 7796 7797I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 7798 --- Change Working Memory (IE) --- 7799 7800--- END Application Phase --- 7801--- Output Phase --- 7802ENV: Agent did: predict-yes for direction L in state State-B 7803In State-B moving L 7804ENV: (next state, see, prediction correct?) = (State-A, 1, True) 7805predict error 0 7806dir: dir isL 7807--- END Output Phase --- 7808\-/--- Input Phase --- 7809=>WM: (13391: I2 ^dir L) 7810=>WM: (13390: I2 ^reward 1) 7811=>WM: (13389: I2 ^see 1) 7812=>WM: (13388: N956 ^status complete) 7813<=WM: (13377: I2 ^dir L) 7814<=WM: (13376: I2 ^reward 1) 7815<=WM: (13375: I2 ^see 0) 7816=>WM: (13392: I2 ^level-1 L1-root) 7817<=WM: (13378: I2 ^level-1 R0-root) 7818 7819--- END Input Phase --- 7820 7821--- Proposal Phase --- 7822 7823--- Inner Elaboration Phase, active level 1 (S1) --- 7824Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 7825 --> 7826 (S1 ^operator O1911 = -0.3470159027404986) 7827Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 7828 --> 7829 (S1 ^operator O1912 = 0.6861879370801713) 7830Firing prefer*rvt*predict-no*H0*2*v1*H1 7831 --> 7832Firing prefer*rvt*predict-yes*H0*1*v1*H1 7833 --> 7834Firing elaborate*copy-see-to-output-link 7835 --> 7836 (I3 ^see 1 +) 7837Firing elaborate*reward*based*on*reward 7838 --> 7839 (R960 ^value 1 +) 7840 (R1 ^reward R960 +) 7841Firing propose*predict-yes 7842 --> 7843 (O1913 ^name predict-yes +) 7844 (S1 ^operator O1913 +) 7845Firing propose*predict-no 7846 --> 7847 (O1914 ^name predict-no +) 7848 (S1 ^operator O1914 +) 7849Firing rl*prefer*rvt*predict-no*H0*2 7850 --> 7851 (S1 ^operator O1912 = 0.314040627026034) 7852Firing rl*prefer*rvt*predict-yes*H0*1 7853 --> 7854 (S1 ^operator O1911 = 0.3804241528486575) 7855Firing prefer*rvt*predict-yes*H0 7856 --> 7857Firing prefer*rvt*predict-no*H0 7858 --> 7859Firing elaborate*copy-dir-to-output-link 7860 --> 7861 (I3 ^dir L +) 7862 inner elaboration loop at bottom goal. 7863Retracting elaborate*copy-see-to-output-link 7864 --> 7865 (I3 ^see 0 +) 7866Retracting propose*predict-no 7867 --> 7868 (O1912 ^name predict-no +) 7869 (S1 ^operator O1912 +) 7870Retracting propose*predict-yes 7871 --> 7872 (O1911 ^name predict-yes +) 7873 (S1 ^operator O1911 +) 7874Retracting elaborate*reward*based*on*reward 7875 --> 7876 (R959 ^value 1 +) 7877 (R1 ^reward R959 +) 7878Retracting elaborate*copy-dir-to-output-link 7879 --> 7880 (I3 ^dir L +) 7881Retracting rl*prefer*rvt*predict-no*H0*2 7882 --> 7883 (S1 ^operator O1912 = 0.314040627026034) 7884Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 7885 --> 7886 (S1 ^operator O1912 = -0.2190661556260421) 7887Retracting rl*prefer*rvt*predict-yes*H0*1 7888 --> 7889 (S1 ^operator O1911 = 0.3804241528486575) 7890Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 7891 --> 7892 (S1 ^operator O1911 = 0.6195585094345952) 7893=>WM: (13399: S1 ^operator O1914 +) 7894=>WM: (13398: S1 ^operator O1913 +) 7895=>WM: (13397: O1914 ^name predict-no) 7896=>WM: (13396: O1913 ^name predict-yes) 7897=>WM: (13395: R960 ^value 1) 7898=>WM: (13394: R1 ^reward R960) 7899=>WM: (13393: I3 ^see 1) 7900<=WM: (13384: S1 ^operator O1911 +) 7901<=WM: (13386: S1 ^operator O1911) 7902<=WM: (13385: S1 ^operator O1912 +) 7903<=WM: (13379: R1 ^reward R959) 7904<=WM: (13364: I3 ^see 0) 7905<=WM: (13382: O1912 ^name predict-no) 7906<=WM: (13381: O1911 ^name predict-yes) 7907<=WM: (13380: R959 ^value 1) 7908 7909--- Inner Elaboration Phase, active level 1 (S1) --- 7910Firing prefer*rvt*predict-yes*H0 7911 --> 7912Firing rl*prefer*rvt*predict-yes*H0*1 7913 --> 7914 (S1 ^operator O1913 = 0.3804241528486575) 7915Firing prefer*rvt*predict-yes*H0*1*v1*H1 7916 --> 7917Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 7918 --> 7919 (S1 ^operator O1913 = -0.3470159027404986) 7920Firing prefer*rvt*predict-no*H0 7921 --> 7922Firing rl*prefer*rvt*predict-no*H0*2 7923 --> 7924 (S1 ^operator O1914 = 0.314040627026034) 7925Firing prefer*rvt*predict-no*H0*2*v1*H1 7926 --> 7927Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 7928 --> 7929 (S1 ^operator O1914 = 0.6861879370801713) 7930 inner elaboration loop at bottom goal. 7931Retracting rl*prefer*rvt*predict-no*H0*2 7932 --> 7933 (S1 ^operator O1912 = 0.314040627026034) 7934Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 7935 --> 7936 (S1 ^operator O1912 = 0.6861879370801713) 7937Retracting rl*prefer*rvt*predict-yes*H0*1 7938 --> 7939 (S1 ^operator O1911 = 0.3804241528486575) 7940Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 7941 --> 7942 (S1 ^operator O1911 = -0.3470159027404986) 7943 7944--- END Proposal Phase --- 7945 7946--- Decision Phase --- 7947RL update rl*prefer*rvt*predict-yes*H0*1 0.521355 -0.140931 0.380424 -> 0.521357 -0.140931 0.380426(R,m,v=1,0.820513,0.148222) 7948RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478626 0.140932 0.619559 -> 0.478628 0.140932 0.61956(R,m,v=1,1,0) 7949=>WM: (13400: S1 ^operator O1914) 7950 7951 957: O: O1914 (predict-no) 7952--- END Decision Phase --- 7953 7954--- Application Phase --- 7955 --- Firing Productions (PE) For State At Depth 1 --- 7956 7957--- Inner Elaboration Phase, active level 1 (S1) --- 7958Firing apply*operator 7959 --> 7960 (I3 ^predict-no N957 + :O ) 7961Firing apply*operator*complete 7962 --> 7963 (I3 ^predict-yes N956 - :O ) 7964 inner elaboration loop at bottom goal. 7965 --- Change Working Memory (PE) --- 7966=>WM: (13401: I3 ^predict-no N957) 7967<=WM: (13388: N956 ^status complete) 7968<=WM: (13387: I3 ^predict-yes N956) 7969 --- Firing Productions (IE) For State At Depth 1 --- 7970 7971--- Inner Elaboration Phase, active level 1 (S1) --- 7972Firing monitor*world 7973 --> 7974 7975I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 7976 --- Change Working Memory (IE) --- 7977 7978--- END Application Phase --- 7979--- Output Phase --- 7980ENV: Agent did: predict-no for direction L in state State-A 7981In State-A moving L 7982ENV: (next state, see, prediction correct?) = (State-A, 0, True) 7983predict error 0 7984dir: dir isL 7985--- END Output Phase --- 7986|\---- Input Phase --- 7987=>WM: (13405: I2 ^dir L) 7988=>WM: (13404: I2 ^reward 1) 7989=>WM: (13403: I2 ^see 0) 7990=>WM: (13402: N957 ^status complete) 7991<=WM: (13391: I2 ^dir L) 7992<=WM: (13390: I2 ^reward 1) 7993<=WM: (13389: I2 ^see 1) 7994=>WM: (13406: I2 ^level-1 L0-root) 7995<=WM: (13392: I2 ^level-1 L1-root) 7996 7997--- END Input Phase --- 7998 7999--- Proposal Phase --- 8000 8001--- Inner Elaboration Phase, active level 1 (S1) --- 8002Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*39 8003 --> 8004 (S1 ^operator O1913 = -0.3332708974800781) 8005Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*38 8006 --> 8007 (S1 ^operator O1914 = 0.6857507825115492) 8008Firing prefer*rvt*predict-no*H0*2*v1*H1 8009 --> 8010Firing prefer*rvt*predict-yes*H0*1*v1*H1 8011 --> 8012Firing elaborate*copy-see-to-output-link 8013 --> 8014 (I3 ^see 0 +) 8015Firing elaborate*reward*based*on*reward 8016 --> 8017 (R961 ^value 1 +) 8018 (R1 ^reward R961 +) 8019Firing propose*predict-yes 8020 --> 8021 (O1915 ^name predict-yes +) 8022 (S1 ^operator O1915 +) 8023Firing propose*predict-no 8024 --> 8025 (O1916 ^name predict-no +) 8026 (S1 ^operator O1916 +) 8027Firing rl*prefer*rvt*predict-no*H0*2 8028 --> 8029 (S1 ^operator O1914 = 0.314040627026034) 8030Firing rl*prefer*rvt*predict-yes*H0*1 8031 --> 8032 (S1 ^operator O1913 = 0.3804255857519139) 8033Firing prefer*rvt*predict-yes*H0 8034 --> 8035Firing prefer*rvt*predict-no*H0 8036 --> 8037Firing elaborate*copy-dir-to-output-link 8038 --> 8039 (I3 ^dir L +) 8040 inner elaboration loop at bottom goal. 8041Retracting elaborate*copy-see-to-output-link 8042 --> 8043 (I3 ^see 1 +) 8044Retracting propose*predict-no 8045 --> 8046 (O1914 ^name predict-no +) 8047 (S1 ^operator O1914 +) 8048Retracting propose*predict-yes 8049 --> 8050 (O1913 ^name predict-yes +) 8051 (S1 ^operator O1913 +) 8052Retracting elaborate*reward*based*on*reward 8053 --> 8054 (R960 ^value 1 +) 8055 (R1 ^reward R960 +) 8056Retracting elaborate*copy-dir-to-output-link 8057 --> 8058 (I3 ^dir L +) 8059Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 8060 --> 8061 (S1 ^operator O1914 = 0.6861879370801713) 8062Retracting rl*prefer*rvt*predict-no*H0*2 8063 --> 8064 (S1 ^operator O1914 = 0.314040627026034) 8065Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 8066 --> 8067 (S1 ^operator O1913 = -0.3470159027404986) 8068Retracting rl*prefer*rvt*predict-yes*H0*1 8069 --> 8070 (S1 ^operator O1913 = 0.3804255857519139) 8071=>WM: (13413: S1 ^operator O1916 +) 8072=>WM: (13412: S1 ^operator O1915 +) 8073=>WM: (13411: O1916 ^name predict-no) 8074=>WM: (13410: O1915 ^name predict-yes) 8075=>WM: (13409: R961 ^value 1) 8076=>WM: (13408: R1 ^reward R961) 8077=>WM: (13407: I3 ^see 0) 8078<=WM: (13398: S1 ^operator O1913 +) 8079<=WM: (13399: S1 ^operator O1914 +) 8080<=WM: (13400: S1 ^operator O1914) 8081<=WM: (13394: R1 ^reward R960) 8082<=WM: (13393: I3 ^see 1) 8083<=WM: (13397: O1914 ^name predict-no) 8084<=WM: (13396: O1913 ^name predict-yes) 8085<=WM: (13395: R960 ^value 1) 8086 8087--- Inner Elaboration Phase, active level 1 (S1) --- 8088Firing prefer*rvt*predict-yes*H0 8089 --> 8090Firing rl*prefer*rvt*predict-yes*H0*1 8091 --> 8092 (S1 ^operator O1915 = 0.3804255857519139) 8093Firing prefer*rvt*predict-yes*H0*1*v1*H1 8094 --> 8095Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*39 8096 --> 8097 (S1 ^operator O1915 = -0.3332708974800781) 8098Firing prefer*rvt*predict-no*H0 8099 --> 8100Firing rl*prefer*rvt*predict-no*H0*2 8101 --> 8102 (S1 ^operator O1916 = 0.314040627026034) 8103Firing prefer*rvt*predict-no*H0*2*v1*H1 8104 --> 8105Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*38 8106 --> 8107 (S1 ^operator O1916 = 0.6857507825115492) 8108 inner elaboration loop at bottom goal. 8109Retracting rl*prefer*rvt*predict-no*H0*2 8110 --> 8111 (S1 ^operator O1914 = 0.314040627026034) 8112Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*38 8113 --> 8114 (S1 ^operator O1914 = 0.6857507825115492) 8115Retracting rl*prefer*rvt*predict-yes*H0*1 8116 --> 8117 (S1 ^operator O1913 = 0.3804255857519139) 8118Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*39 8119 --> 8120 (S1 ^operator O1913 = -0.3332708974800781) 8121 8122--- END Proposal Phase --- 8123 8124--- Decision Phase --- 8125RL update rl*prefer*rvt*predict-no*H0*2 0.485046 -0.171006 0.314041 -> 0.485031 -0.17101 0.314022(R,m,v=1,0.858108,0.122587) 8126RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*36 0.515134 0.171054 0.686188 -> 0.515116 0.171049 0.686165(R,m,v=1,1,0) 8127=>WM: (13414: S1 ^operator O1916) 8128 8129 958: O: O1916 (predict-no) 8130--- END Decision Phase --- 8131 8132--- Application Phase --- 8133 --- Firing Productions (PE) For State At Depth 1 --- 8134 8135--- Inner Elaboration Phase, active level 1 (S1) --- 8136Firing apply*operator 8137 --> 8138 (I3 ^predict-no N958 + :O ) 8139Firing apply*operator*complete 8140 --> 8141 (I3 ^predict-no N957 - :O ) 8142 inner elaboration loop at bottom goal. 8143 --- Change Working Memory (PE) --- 8144=>WM: (13415: I3 ^predict-no N958) 8145<=WM: (13402: N957 ^status complete) 8146<=WM: (13401: I3 ^predict-no N957) 8147 --- Firing Productions (IE) For State At Depth 1 --- 8148 8149--- Inner Elaboration Phase, active level 1 (S1) --- 8150Firing monitor*world 8151 --> 8152 8153I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 8154 --- Change Working Memory (IE) --- 8155 8156--- END Application Phase --- 8157--- Output Phase --- 8158ENV: Agent did: predict-no for direction L in state State-A 8159In State-A moving L 8160ENV: (next state, see, prediction correct?) = (State-A, 0, True) 8161predict error 0 8162dir: dir isR 8163--- END Output Phase --- 8164/|\--- Input Phase --- 8165=>WM: (13419: I2 ^dir R) 8166=>WM: (13418: I2 ^reward 1) 8167=>WM: (13417: I2 ^see 0) 8168=>WM: (13416: N958 ^status complete) 8169<=WM: (13405: I2 ^dir L) 8170<=WM: (13404: I2 ^reward 1) 8171<=WM: (13403: I2 ^see 0) 8172=>WM: (13420: I2 ^level-1 L0-root) 8173<=WM: (13406: I2 ^level-1 L0-root) 8174 8175--- END Input Phase --- 8176 8177--- Proposal Phase --- 8178 8179--- Inner Elaboration Phase, active level 1 (S1) --- 8180Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 8181 --> 8182 (S1 ^operator O1915 = 0.7053811599250611) 8183Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 8184 --> 8185 (S1 ^operator O1916 = -0.2023211881870005) 8186Firing prefer*rvt*predict-no*H0*6*v1*H1 8187 --> 8188Firing prefer*rvt*predict-yes*H0*5*v1*H1 8189 --> 8190Firing elaborate*copy-see-to-output-link 8191 --> 8192 (I3 ^see 0 +) 8193Firing elaborate*reward*based*on*reward 8194 --> 8195 (R962 ^value 1 +) 8196 (R1 ^reward R962 +) 8197Firing propose*predict-yes 8198 --> 8199 (O1917 ^name predict-yes +) 8200 (S1 ^operator O1917 +) 8201Firing propose*predict-no 8202 --> 8203 (O1918 ^name predict-no +) 8204 (S1 ^operator O1918 +) 8205Firing rl*prefer*rvt*predict-no*H0*6 8206 --> 8207 (S1 ^operator O1916 = 0.2298717920574965) 8208Firing rl*prefer*rvt*predict-yes*H0*5 8209 --> 8210 (S1 ^operator O1915 = 0.2939886829338975) 8211Firing prefer*rvt*predict-yes*H0 8212 --> 8213Firing prefer*rvt*predict-no*H0 8214 --> 8215Firing elaborate*copy-dir-to-output-link 8216 --> 8217 (I3 ^dir R +) 8218 inner elaboration loop at bottom goal. 8219Retracting elaborate*copy-see-to-output-link 8220 --> 8221 (I3 ^see 0 +) 8222Retracting propose*predict-no 8223 --> 8224 (O1916 ^name predict-no +) 8225 (S1 ^operator O1916 +) 8226Retracting propose*predict-yes 8227 --> 8228 (O1915 ^name predict-yes +) 8229 (S1 ^operator O1915 +) 8230Retracting elaborate*reward*based*on*reward 8231 --> 8232 (R961 ^value 1 +) 8233 (R1 ^reward R961 +) 8234Retracting elaborate*copy-dir-to-output-link 8235 --> 8236 (I3 ^dir L +) 8237Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*38 8238 --> 8239 (S1 ^operator O1916 = 0.6857507825115492) 8240Retracting rl*prefer*rvt*predict-no*H0*2 8241 --> 8242 (S1 ^operator O1916 = 0.3140215711634288) 8243Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*39 8244 --> 8245 (S1 ^operator O1915 = -0.3332708974800781) 8246Retracting rl*prefer*rvt*predict-yes*H0*1 8247 --> 8248 (S1 ^operator O1915 = 0.3804255857519139) 8249=>WM: (13427: S1 ^operator O1918 +) 8250=>WM: (13426: S1 ^operator O1917 +) 8251=>WM: (13425: I3 ^dir R) 8252=>WM: (13424: O1918 ^name predict-no) 8253=>WM: (13423: O1917 ^name predict-yes) 8254=>WM: (13422: R962 ^value 1) 8255=>WM: (13421: R1 ^reward R962) 8256<=WM: (13412: S1 ^operator O1915 +) 8257<=WM: (13413: S1 ^operator O1916 +) 8258<=WM: (13414: S1 ^operator O1916) 8259<=WM: (13383: I3 ^dir L) 8260<=WM: (13408: R1 ^reward R961) 8261<=WM: (13411: O1916 ^name predict-no) 8262<=WM: (13410: O1915 ^name predict-yes) 8263<=WM: (13409: R961 ^value 1) 8264 8265--- Inner Elaboration Phase, active level 1 (S1) --- 8266Firing prefer*rvt*predict-yes*H0 8267 --> 8268Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 8269 --> 8270 (S1 ^operator O1917 = 0.7053811599250611) 8271Firing rl*prefer*rvt*predict-yes*H0*5 8272 --> 8273 (S1 ^operator O1917 = 0.2939886829338975) 8274Firing prefer*rvt*predict-yes*H0*5*v1*H1 8275 --> 8276Firing prefer*rvt*predict-no*H0 8277 --> 8278Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 8279 --> 8280 (S1 ^operator O1918 = -0.2023211881870005) 8281Firing rl*prefer*rvt*predict-no*H0*6 8282 --> 8283 (S1 ^operator O1918 = 0.2298717920574965) 8284Firing prefer*rvt*predict-no*H0*6*v1*H1 8285 --> 8286 inner elaboration loop at bottom goal. 8287Retracting rl*prefer*rvt*predict-no*H0*6 8288 --> 8289 (S1 ^operator O1916 = 0.2298717920574965) 8290Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 8291 --> 8292 (S1 ^operator O1916 = -0.2023211881870005) 8293Retracting rl*prefer*rvt*predict-yes*H0*5 8294 --> 8295 (S1 ^operator O1915 = 0.2939886829338975) 8296Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 8297 --> 8298 (S1 ^operator O1915 = 0.7053811599250611) 8299 8300--- END Proposal Phase --- 8301 8302--- Decision Phase --- 8303RL update rl*prefer*rvt*predict-no*H0*2 0.485031 -0.17101 0.314022 -> 0.485046 -0.171006 0.314041(R,m,v=1,0.85906,0.121894) 8304RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*38 0.514789 0.170962 0.685751 -> 0.514806 0.170967 0.685773(R,m,v=1,1,0) 8305=>WM: (13428: S1 ^operator O1917) 8306 8307 959: O: O1917 (predict-yes) 8308--- END Decision Phase --- 8309 8310--- Application Phase --- 8311 --- Firing Productions (PE) For State At Depth 1 --- 8312 8313--- Inner Elaboration Phase, active level 1 (S1) --- 8314Firing apply*operator 8315 --> 8316 (I3 ^predict-yes N959 + :O ) 8317Firing apply*operator*complete 8318 --> 8319 (I3 ^predict-no N958 - :O ) 8320 inner elaboration loop at bottom goal. 8321 --- Change Working Memory (PE) --- 8322=>WM: (13429: I3 ^predict-yes N959) 8323<=WM: (13416: N958 ^status complete) 8324<=WM: (13415: I3 ^predict-no N958) 8325 --- Firing Productions (IE) For State At Depth 1 --- 8326 8327--- Inner Elaboration Phase, active level 1 (S1) --- 8328Firing monitor*world 8329 --> 8330 8331I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 8332 --- Change Working Memory (IE) --- 8333 8334--- END Application Phase --- 8335--- Output Phase --- 8336ENV: Agent did: predict-yes for direction R in state State-A 8337In State-A moving R 8338ENV: (next state, see, prediction correct?) = (State-B, 1, True) 8339predict error 0 8340dir: dir isU 8341--- END Output Phase --- 8342-/|--- Input Phase --- 8343=>WM: (13433: I2 ^dir U) 8344=>WM: (13432: I2 ^reward 1) 8345=>WM: (13431: I2 ^see 1) 8346=>WM: (13430: N959 ^status complete) 8347<=WM: (13419: I2 ^dir R) 8348<=WM: (13418: I2 ^reward 1) 8349<=WM: (13417: I2 ^see 0) 8350=>WM: (13434: I2 ^level-1 R1-root) 8351<=WM: (13420: I2 ^level-1 L0-root) 8352 8353--- END Input Phase --- 8354 8355--- Proposal Phase --- 8356 8357--- Inner Elaboration Phase, active level 1 (S1) --- 8358Firing elaborate*copy-see-to-output-link 8359 --> 8360 (I3 ^see 1 +) 8361Firing elaborate*reward*based*on*reward 8362 --> 8363 (R963 ^value 1 +) 8364 (R1 ^reward R963 +) 8365Firing propose*predict-yes 8366 --> 8367 (O1919 ^name predict-yes +) 8368 (S1 ^operator O1919 +) 8369Firing propose*predict-no 8370 --> 8371 (O1920 ^name predict-no +) 8372 (S1 ^operator O1920 +) 8373Firing rl*prefer*rvt*predict-no*H0*4 8374 --> 8375 (S1 ^operator O1918 = 1.) 8376Firing rl*prefer*rvt*predict-yes*H0*3 8377 --> 8378 (S1 ^operator O1917 = 0.) 8379Firing prefer*rvt*predict-yes*H0 8380 --> 8381Firing prefer*rvt*predict-no*H0 8382 --> 8383Firing elaborate*copy-dir-to-output-link 8384 --> 8385 (I3 ^dir U +) 8386 inner elaboration loop at bottom goal. 8387Retracting elaborate*copy-see-to-output-link 8388 --> 8389 (I3 ^see 0 +) 8390Retracting propose*predict-no 8391 --> 8392 (O1918 ^name predict-no +) 8393 (S1 ^operator O1918 +) 8394Retracting propose*predict-yes 8395 --> 8396 (O1917 ^name predict-yes +) 8397 (S1 ^operator O1917 +) 8398Retracting elaborate*reward*based*on*reward 8399 --> 8400 (R962 ^value 1 +) 8401 (R1 ^reward R962 +) 8402Retracting elaborate*copy-dir-to-output-link 8403 --> 8404 (I3 ^dir R +) 8405Retracting rl*prefer*rvt*predict-no*H0*6 8406 --> 8407 (S1 ^operator O1918 = 0.2298717920574965) 8408Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 8409 --> 8410 (S1 ^operator O1918 = -0.2023211881870005) 8411Retracting rl*prefer*rvt*predict-yes*H0*5 8412 --> 8413 (S1 ^operator O1917 = 0.2939886829338975) 8414Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 8415 --> 8416 (S1 ^operator O1917 = 0.7053811599250611) 8417=>WM: (13442: S1 ^operator O1920 +) 8418=>WM: (13441: S1 ^operator O1919 +) 8419=>WM: (13440: I3 ^dir U) 8420=>WM: (13439: O1920 ^name predict-no) 8421=>WM: (13438: O1919 ^name predict-yes) 8422=>WM: (13437: R963 ^value 1) 8423=>WM: (13436: R1 ^reward R963) 8424=>WM: (13435: I3 ^see 1) 8425<=WM: (13426: S1 ^operator O1917 +) 8426<=WM: (13428: S1 ^operator O1917) 8427<=WM: (13427: S1 ^operator O1918 +) 8428<=WM: (13425: I3 ^dir R) 8429<=WM: (13421: R1 ^reward R962) 8430<=WM: (13407: I3 ^see 0) 8431<=WM: (13424: O1918 ^name predict-no) 8432<=WM: (13423: O1917 ^name predict-yes) 8433<=WM: (13422: R962 ^value 1) 8434 8435--- Inner Elaboration Phase, active level 1 (S1) --- 8436Firing prefer*rvt*predict-yes*H0 8437 --> 8438Firing rl*prefer*rvt*predict-yes*H0*3 8439 --> 8440 (S1 ^operator O1919 = 0.) 8441Firing prefer*rvt*predict-no*H0 8442 --> 8443Firing rl*prefer*rvt*predict-no*H0*4 8444 --> 8445 (S1 ^operator O1920 = 1.) 8446 inner elaboration loop at bottom goal. 8447Retracting rl*prefer*rvt*predict-no*H0*4 8448 --> 8449 (S1 ^operator O1918 = 1.) 8450Retracting rl*prefer*rvt*predict-yes*H0*3 8451 --> 8452 (S1 ^operator O1917 = 0.) 8453 8454--- END Proposal Phase --- 8455 8456--- Decision Phase --- 8457RL update rl*prefer*rvt*predict-yes*H0*5 0.501062 -0.207073 0.293989 -> 0.50111 -0.207069 0.294041(R,m,v=1,0.836735,0.137545) 8458RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.498366 0.207015 0.705381 -> 0.498423 0.207021 0.705444(R,m,v=1,1,0) 8459=>WM: (13443: S1 ^operator O1920) 8460 8461 960: O: O1920 (predict-no) 8462--- END Decision Phase --- 8463 8464--- Application Phase --- 8465 --- Firing Productions (PE) For State At Depth 1 --- 8466 8467--- Inner Elaboration Phase, active level 1 (S1) --- 8468Firing apply*operator 8469 --> 8470 (I3 ^predict-no N960 + :O ) 8471Firing apply*operator*complete 8472 --> 8473 (I3 ^predict-yes N959 - :O ) 8474 inner elaboration loop at bottom goal. 8475 --- Change Working Memory (PE) --- 8476=>WM: (13444: I3 ^predict-no N960) 8477<=WM: (13430: N959 ^status complete) 8478<=WM: (13429: I3 ^predict-yes N959) 8479 --- Firing Productions (IE) For State At Depth 1 --- 8480 8481--- Inner Elaboration Phase, active level 1 (S1) --- 8482Firing monitor*world 8483 --> 8484 8485I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 8486 --- Change Working Memory (IE) --- 8487 8488--- END Application Phase --- 8489--- Output Phase --- 8490ENV: Agent did: predict-no for direction U in state State-B 8491In State-B moving U 8492ENV: (next state, see, prediction correct?) = (State-B, 0, True) 8493predict error 0 8494dir: dir isU 8495--- END Output Phase --- 8496\---- Input Phase --- 8497=>WM: (13448: I2 ^dir U) 8498=>WM: (13447: I2 ^reward 1) 8499=>WM: (13446: I2 ^see 0) 8500=>WM: (13445: N960 ^status complete) 8501<=WM: (13433: I2 ^dir U) 8502<=WM: (13432: I2 ^reward 1) 8503<=WM: (13431: I2 ^see 1) 8504=>WM: (13449: I2 ^level-1 R1-root) 8505<=WM: (13434: I2 ^level-1 R1-root) 8506 8507--- END Input Phase --- 8508 8509--- Proposal Phase --- 8510 8511--- Inner Elaboration Phase, active level 1 (S1) --- 8512Firing elaborate*copy-see-to-output-link 8513 --> 8514 (I3 ^see 0 +) 8515Firing elaborate*reward*based*on*reward 8516 --> 8517 (R964 ^value 1 +) 8518 (R1 ^reward R964 +) 8519Firing propose*predict-yes 8520 --> 8521 (O1921 ^name predict-yes +) 8522 (S1 ^operator O1921 +) 8523Firing propose*predict-no 8524 --> 8525 (O1922 ^name predict-no +) 8526 (S1 ^operator O1922 +) 8527Firing rl*prefer*rvt*predict-no*H0*4 8528 --> 8529 (S1 ^operator O1920 = 1.) 8530Firing rl*prefer*rvt*predict-yes*H0*3 8531 --> 8532 (S1 ^operator O1919 = 0.) 8533Firing prefer*rvt*predict-yes*H0 8534 --> 8535Firing prefer*rvt*predict-no*H0 8536 --> 8537Firing elaborate*copy-dir-to-output-link 8538 --> 8539 (I3 ^dir U +) 8540 inner elaboration loop at bottom goal. 8541Retracting elaborate*copy-see-to-output-link 8542 --> 8543 (I3 ^see 1 +) 8544Retracting propose*predict-no 8545 --> 8546 (O1920 ^name predict-no +) 8547 (S1 ^operator O1920 +) 8548Retracting propose*predict-yes 8549 --> 8550 (O1919 ^name predict-yes +) 8551 (S1 ^operator O1919 +) 8552Retracting elaborate*reward*based*on*reward 8553 --> 8554 (R963 ^value 1 +) 8555 (R1 ^reward R963 +) 8556Retracting elaborate*copy-dir-to-output-link 8557 --> 8558 (I3 ^dir U +) 8559Retracting rl*prefer*rvt*predict-no*H0*4 8560 --> 8561 (S1 ^operator O1920 = 1.) 8562Retracting rl*prefer*rvt*predict-yes*H0*3 8563 --> 8564 (S1 ^operator O1919 = 0.) 8565=>WM: (13456: S1 ^operator O1922 +) 8566=>WM: (13455: S1 ^operator O1921 +) 8567=>WM: (13454: O1922 ^name predict-no) 8568=>WM: (13453: O1921 ^name predict-yes) 8569=>WM: (13452: R964 ^value 1) 8570=>WM: (13451: R1 ^reward R964) 8571=>WM: (13450: I3 ^see 0) 8572<=WM: (13441: S1 ^operator O1919 +) 8573<=WM: (13442: S1 ^operator O1920 +) 8574<=WM: (13443: S1 ^operator O1920) 8575<=WM: (13436: R1 ^reward R963) 8576<=WM: (13435: I3 ^see 1) 8577<=WM: (13439: O1920 ^name predict-no) 8578<=WM: (13438: O1919 ^name predict-yes) 8579<=WM: (13437: R963 ^value 1) 8580 8581--- Inner Elaboration Phase, active level 1 (S1) --- 8582Firing prefer*rvt*predict-yes*H0 8583 --> 8584Firing rl*prefer*rvt*predict-yes*H0*3 8585 --> 8586 (S1 ^operator O1921 = 0.) 8587Firing prefer*rvt*predict-no*H0 8588 --> 8589Firing rl*prefer*rvt*predict-no*H0*4 8590 --> 8591 (S1 ^operator O1922 = 1.) 8592 inner elaboration loop at bottom goal. 8593Retracting rl*prefer*rvt*predict-no*H0*4 8594 --> 8595 (S1 ^operator O1920 = 1.) 8596Retracting rl*prefer*rvt*predict-yes*H0*3 8597 --> 8598 (S1 ^operator O1919 = 0.) 8599 8600--- END Proposal Phase --- 8601 8602--- Decision Phase --- 8603RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 8604=>WM: (13457: S1 ^operator O1922) 8605 8606 961: O: O1922 (predict-no) 8607--- END Decision Phase --- 8608 8609--- Application Phase --- 8610 --- Firing Productions (PE) For State At Depth 1 --- 8611 8612--- Inner Elaboration Phase, active level 1 (S1) --- 8613Firing apply*operator 8614 --> 8615 (I3 ^predict-no N961 + :O ) 8616Firing apply*operator*complete 8617 --> 8618 (I3 ^predict-no N960 - :O ) 8619 inner elaboration loop at bottom goal. 8620 --- Change Working Memory (PE) --- 8621=>WM: (13458: I3 ^predict-no N961) 8622<=WM: (13445: N960 ^status complete) 8623<=WM: (13444: I3 ^predict-no N960) 8624 --- Firing Productions (IE) For State At Depth 1 --- 8625 8626--- Inner Elaboration Phase, active level 1 (S1) --- 8627Firing monitor*world 8628 --> 8629 8630I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 8631 --- Change Working Memory (IE) --- 8632 8633--- END Application Phase --- 8634--- Output Phase --- 8635ENV: Agent did: predict-no for direction U in state State-B 8636In State-B moving U 8637ENV: (next state, see, prediction correct?) = (State-B, 0, True) 8638predict error 0 8639dir: dir isU 8640--- END Output Phase --- 8641/--- Input Phase --- 8642=>WM: (13462: I2 ^dir U) 8643=>WM: (13461: I2 ^reward 1) 8644=>WM: (13460: I2 ^see 0) 8645=>WM: (13459: N961 ^status complete) 8646<=WM: (13448: I2 ^dir U) 8647<=WM: (13447: I2 ^reward 1) 8648<=WM: (13446: I2 ^see 0) 8649=>WM: (13463: I2 ^level-1 R1-root) 8650<=WM: (13449: I2 ^level-1 R1-root) 8651 8652--- END Input Phase --- 8653 8654--- Proposal Phase --- 8655 8656--- Inner Elaboration Phase, active level 1 (S1) --- 8657Firing elaborate*copy-see-to-output-link 8658 --> 8659 (I3 ^see 0 +) 8660Firing elaborate*reward*based*on*reward 8661 --> 8662 (R965 ^value 1 +) 8663 (R1 ^reward R965 +) 8664Firing propose*predict-yes 8665 --> 8666 (O1923 ^name predict-yes +) 8667 (S1 ^operator O1923 +) 8668Firing propose*predict-no 8669 --> 8670 (O1924 ^name predict-no +) 8671 (S1 ^operator O1924 +) 8672Firing rl*prefer*rvt*predict-no*H0*4 8673 --> 8674 (S1 ^operator O1922 = 1.) 8675Firing rl*prefer*rvt*predict-yes*H0*3 8676 --> 8677 (S1 ^operator O1921 = 0.) 8678Firing prefer*rvt*predict-yes*H0 8679 --> 8680Firing prefer*rvt*predict-no*H0 8681 --> 8682Firing elaborate*copy-dir-to-output-link 8683 --> 8684 (I3 ^dir U +) 8685 inner elaboration loop at bottom goal. 8686Retracting elaborate*copy-see-to-output-link 8687 --> 8688 (I3 ^see 0 +) 8689Retracting propose*predict-no 8690 --> 8691 (O1922 ^name predict-no +) 8692 (S1 ^operator O1922 +) 8693Retracting propose*predict-yes 8694 --> 8695 (O1921 ^name predict-yes +) 8696 (S1 ^operator O1921 +) 8697Retracting elaborate*reward*based*on*reward 8698 --> 8699 (R964 ^value 1 +) 8700 (R1 ^reward R964 +) 8701Retracting elaborate*copy-dir-to-output-link 8702 --> 8703 (I3 ^dir U +) 8704Retracting rl*prefer*rvt*predict-no*H0*4 8705 --> 8706 (S1 ^operator O1922 = 1.) 8707Retracting rl*prefer*rvt*predict-yes*H0*3 8708 --> 8709 (S1 ^operator O1921 = 0.) 8710=>WM: (13469: S1 ^operator O1924 +) 8711=>WM: (13468: S1 ^operator O1923 +) 8712=>WM: (13467: O1924 ^name predict-no) 8713=>WM: (13466: O1923 ^name predict-yes) 8714=>WM: (13465: R965 ^value 1) 8715=>WM: (13464: R1 ^reward R965) 8716<=WM: (13455: S1 ^operator O1921 +) 8717<=WM: (13456: S1 ^operator O1922 +) 8718<=WM: (13457: S1 ^operator O1922) 8719<=WM: (13451: R1 ^reward R964) 8720<=WM: (13454: O1922 ^name predict-no) 8721<=WM: (13453: O1921 ^name predict-yes) 8722<=WM: (13452: R964 ^value 1) 8723 8724--- Inner Elaboration Phase, active level 1 (S1) --- 8725Firing prefer*rvt*predict-yes*H0 8726 --> 8727Firing rl*prefer*rvt*predict-yes*H0*3 8728 --> 8729 (S1 ^operator O1923 = 0.) 8730Firing prefer*rvt*predict-no*H0 8731 --> 8732Firing rl*prefer*rvt*predict-no*H0*4 8733 --> 8734 (S1 ^operator O1924 = 1.) 8735 inner elaboration loop at bottom goal. 8736Retracting rl*prefer*rvt*predict-no*H0*4 8737 --> 8738 (S1 ^operator O1922 = 1.) 8739Retracting rl*prefer*rvt*predict-yes*H0*3 8740 --> 8741 (S1 ^operator O1921 = 0.) 8742 8743--- END Proposal Phase --- 8744 8745--- Decision Phase --- 8746RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 8747=>WM: (13470: S1 ^operator O1924) 8748 8749 962: O: O1924 (predict-no) 8750--- END Decision Phase --- 8751 8752--- Application Phase --- 8753 --- Firing Productions (PE) For State At Depth 1 --- 8754 8755--- Inner Elaboration Phase, active level 1 (S1) --- 8756Firing apply*operator 8757 --> 8758 (I3 ^predict-no N962 + :O ) 8759Firing apply*operator*complete 8760 --> 8761 (I3 ^predict-no N961 - :O ) 8762 inner elaboration loop at bottom goal. 8763 --- Change Working Memory (PE) --- 8764=>WM: (13471: I3 ^predict-no N962) 8765<=WM: (13459: N961 ^status complete) 8766<=WM: (13458: I3 ^predict-no N961) 8767 --- Firing Productions (IE) For State At Depth 1 --- 8768 8769--- Inner Elaboration Phase, active level 1 (S1) --- 8770Firing monitor*world 8771 --> 8772 8773I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 8774 --- Change Working Memory (IE) --- 8775 8776--- END Application Phase --- 8777--- Output Phase --- 8778ENV: Agent did: predict-no for direction U in state State-B 8779In State-B moving U 8780ENV: (next state, see, prediction correct?) = (State-B, 0, True) 8781predict error 0 8782dir: dir isU 8783--- END Output Phase --- 8784|\--- Input Phase --- 8785=>WM: (13475: I2 ^dir U) 8786=>WM: (13474: I2 ^reward 1) 8787=>WM: (13473: I2 ^see 0) 8788=>WM: (13472: N962 ^status complete) 8789<=WM: (13462: I2 ^dir U) 8790<=WM: (13461: I2 ^reward 1) 8791<=WM: (13460: I2 ^see 0) 8792=>WM: (13476: I2 ^level-1 R1-root) 8793<=WM: (13463: I2 ^level-1 R1-root) 8794 8795--- END Input Phase --- 8796 8797--- Proposal Phase --- 8798 8799--- Inner Elaboration Phase, active level 1 (S1) --- 8800Firing elaborate*copy-see-to-output-link 8801 --> 8802 (I3 ^see 0 +) 8803Firing elaborate*reward*based*on*reward 8804 --> 8805 (R966 ^value 1 +) 8806 (R1 ^reward R966 +) 8807Firing propose*predict-yes 8808 --> 8809 (O1925 ^name predict-yes +) 8810 (S1 ^operator O1925 +) 8811Firing propose*predict-no 8812 --> 8813 (O1926 ^name predict-no +) 8814 (S1 ^operator O1926 +) 8815Firing rl*prefer*rvt*predict-no*H0*4 8816 --> 8817 (S1 ^operator O1924 = 1.) 8818Firing rl*prefer*rvt*predict-yes*H0*3 8819 --> 8820 (S1 ^operator O1923 = 0.) 8821Firing prefer*rvt*predict-yes*H0 8822 --> 8823Firing prefer*rvt*predict-no*H0 8824 --> 8825Firing elaborate*copy-dir-to-output-link 8826 --> 8827 (I3 ^dir U +) 8828 inner elaboration loop at bottom goal. 8829Retracting elaborate*copy-see-to-output-link 8830 --> 8831 (I3 ^see 0 +) 8832Retracting propose*predict-no 8833 --> 8834 (O1924 ^name predict-no +) 8835 (S1 ^operator O1924 +) 8836Retracting propose*predict-yes 8837 --> 8838 (O1923 ^name predict-yes +) 8839 (S1 ^operator O1923 +) 8840Retracting elaborate*reward*based*on*reward 8841 --> 8842 (R965 ^value 1 +) 8843 (R1 ^reward R965 +) 8844Retracting elaborate*copy-dir-to-output-link 8845 --> 8846 (I3 ^dir U +) 8847Retracting rl*prefer*rvt*predict-no*H0*4 8848 --> 8849 (S1 ^operator O1924 = 1.) 8850Retracting rl*prefer*rvt*predict-yes*H0*3 8851 --> 8852 (S1 ^operator O1923 = 0.) 8853=>WM: (13482: S1 ^operator O1926 +) 8854=>WM: (13481: S1 ^operator O1925 +) 8855=>WM: (13480: O1926 ^name predict-no) 8856=>WM: (13479: O1925 ^name predict-yes) 8857=>WM: (13478: R966 ^value 1) 8858=>WM: (13477: R1 ^reward R966) 8859<=WM: (13468: S1 ^operator O1923 +) 8860<=WM: (13469: S1 ^operator O1924 +) 8861<=WM: (13470: S1 ^operator O1924) 8862<=WM: (13464: R1 ^reward R965) 8863<=WM: (13467: O1924 ^name predict-no) 8864<=WM: (13466: O1923 ^name predict-yes) 8865<=WM: (13465: R965 ^value 1) 8866 8867--- Inner Elaboration Phase, active level 1 (S1) --- 8868Firing prefer*rvt*predict-yes*H0 8869 --> 8870Firing rl*prefer*rvt*predict-yes*H0*3 8871 --> 8872 (S1 ^operator O1925 = 0.) 8873Firing prefer*rvt*predict-no*H0 8874 --> 8875Firing rl*prefer*rvt*predict-no*H0*4 8876 --> 8877 (S1 ^operator O1926 = 1.) 8878 inner elaboration loop at bottom goal. 8879Retracting rl*prefer*rvt*predict-no*H0*4 8880 --> 8881 (S1 ^operator O1924 = 1.) 8882Retracting rl*prefer*rvt*predict-yes*H0*3 8883 --> 8884 (S1 ^operator O1923 = 0.) 8885 8886--- END Proposal Phase --- 8887 8888--- Decision Phase --- 8889RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 8890=>WM: (13483: S1 ^operator O1926) 8891 8892 963: O: O1926 (predict-no) 8893--- END Decision Phase --- 8894 8895--- Application Phase --- 8896 --- Firing Productions (PE) For State At Depth 1 --- 8897 8898--- Inner Elaboration Phase, active level 1 (S1) --- 8899Firing apply*operator 8900 --> 8901 (I3 ^predict-no N963 + :O ) 8902Firing apply*operator*complete 8903 --> 8904 (I3 ^predict-no N962 - :O ) 8905 inner elaboration loop at bottom goal. 8906 --- Change Working Memory (PE) --- 8907=>WM: (13484: I3 ^predict-no N963) 8908<=WM: (13472: N962 ^status complete) 8909<=WM: (13471: I3 ^predict-no N962) 8910 --- Firing Productions (IE) For State At Depth 1 --- 8911 8912--- Inner Elaboration Phase, active level 1 (S1) --- 8913Firing monitor*world 8914 --> 8915 8916I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 8917 --- Change Working Memory (IE) --- 8918 8919--- END Application Phase --- 8920--- Output Phase --- 8921ENV: Agent did: predict-no for direction U in state State-B 8922In State-B moving U 8923ENV: (next state, see, prediction correct?) = (State-B, 0, True) 8924predict error 0 8925dir: dir isL 8926--- END Output Phase --- 8927---- Input Phase --- 8928=>WM: (13488: I2 ^dir L) 8929=>WM: (13487: I2 ^reward 1) 8930=>WM: (13486: I2 ^see 0) 8931=>WM: (13485: N963 ^status complete) 8932<=WM: (13475: I2 ^dir U) 8933<=WM: (13474: I2 ^reward 1) 8934<=WM: (13473: I2 ^see 0) 8935=>WM: (13489: I2 ^level-1 R1-root) 8936<=WM: (13476: I2 ^level-1 R1-root) 8937 8938--- END Input Phase --- 8939 8940--- Proposal Phase --- 8941 8942--- Inner Elaboration Phase, active level 1 (S1) --- 8943Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 8944 --> 8945 (S1 ^operator O1925 = 0.619629119351056) 8946Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 8947 --> 8948 (S1 ^operator O1926 = -0.1479504104026684) 8949Firing prefer*rvt*predict-no*H0*2*v1*H1 8950 --> 8951Firing prefer*rvt*predict-yes*H0*1*v1*H1 8952 --> 8953Firing elaborate*copy-see-to-output-link 8954 --> 8955 (I3 ^see 0 +) 8956Firing elaborate*reward*based*on*reward 8957 --> 8958 (R967 ^value 1 +) 8959 (R1 ^reward R967 +) 8960Firing propose*predict-yes 8961 --> 8962 (O1927 ^name predict-yes +) 8963 (S1 ^operator O1927 +) 8964Firing propose*predict-no 8965 --> 8966 (O1928 ^name predict-no +) 8967 (S1 ^operator O1928 +) 8968Firing rl*prefer*rvt*predict-no*H0*2 8969 --> 8970 (S1 ^operator O1926 = 0.3140405292214645) 8971Firing rl*prefer*rvt*predict-yes*H0*1 8972 --> 8973 (S1 ^operator O1925 = 0.3804255857519139) 8974Firing prefer*rvt*predict-yes*H0 8975 --> 8976Firing prefer*rvt*predict-no*H0 8977 --> 8978Firing elaborate*copy-dir-to-output-link 8979 --> 8980 (I3 ^dir L +) 8981 inner elaboration loop at bottom goal. 8982Retracting elaborate*copy-see-to-output-link 8983 --> 8984 (I3 ^see 0 +) 8985Retracting propose*predict-no 8986 --> 8987 (O1926 ^name predict-no +) 8988 (S1 ^operator O1926 +) 8989Retracting propose*predict-yes 8990 --> 8991 (O1925 ^name predict-yes +) 8992 (S1 ^operator O1925 +) 8993Retracting elaborate*reward*based*on*reward 8994 --> 8995 (R966 ^value 1 +) 8996 (R1 ^reward R966 +) 8997Retracting elaborate*copy-dir-to-output-link 8998 --> 8999 (I3 ^dir U +) 9000Retracting rl*prefer*rvt*predict-no*H0*4 9001 --> 9002 (S1 ^operator O1926 = 1.) 9003Retracting rl*prefer*rvt*predict-yes*H0*3 9004 --> 9005 (S1 ^operator O1925 = 0.) 9006=>WM: (13496: S1 ^operator O1928 +) 9007=>WM: (13495: S1 ^operator O1927 +) 9008=>WM: (13494: I3 ^dir L) 9009=>WM: (13493: O1928 ^name predict-no) 9010=>WM: (13492: O1927 ^name predict-yes) 9011=>WM: (13491: R967 ^value 1) 9012=>WM: (13490: R1 ^reward R967) 9013<=WM: (13481: S1 ^operator O1925 +) 9014<=WM: (13482: S1 ^operator O1926 +) 9015<=WM: (13483: S1 ^operator O1926) 9016<=WM: (13440: I3 ^dir U) 9017<=WM: (13477: R1 ^reward R966) 9018<=WM: (13480: O1926 ^name predict-no) 9019<=WM: (13479: O1925 ^name predict-yes) 9020<=WM: (13478: R966 ^value 1) 9021 9022--- Inner Elaboration Phase, active level 1 (S1) --- 9023Firing prefer*rvt*predict-yes*H0 9024 --> 9025Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9026 --> 9027 (S1 ^operator O1927 = 0.619629119351056) 9028Firing rl*prefer*rvt*predict-yes*H0*1 9029 --> 9030 (S1 ^operator O1927 = 0.3804255857519139) 9031Firing prefer*rvt*predict-yes*H0*1*v1*H1 9032 --> 9033Firing prefer*rvt*predict-no*H0 9034 --> 9035Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9036 --> 9037 (S1 ^operator O1928 = -0.1479504104026684) 9038Firing rl*prefer*rvt*predict-no*H0*2 9039 --> 9040 (S1 ^operator O1928 = 0.3140405292214645) 9041Firing prefer*rvt*predict-no*H0*2*v1*H1 9042 --> 9043 inner elaboration loop at bottom goal. 9044Retracting rl*prefer*rvt*predict-no*H0*2 9045 --> 9046 (S1 ^operator O1926 = 0.3140405292214645) 9047Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9048 --> 9049 (S1 ^operator O1926 = -0.1479504104026684) 9050Retracting rl*prefer*rvt*predict-yes*H0*1 9051 --> 9052 (S1 ^operator O1925 = 0.3804255857519139) 9053Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9054 --> 9055 (S1 ^operator O1925 = 0.619629119351056) 9056 9057--- END Proposal Phase --- 9058 9059--- Decision Phase --- 9060RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 9061=>WM: (13497: S1 ^operator O1927) 9062 9063 964: O: O1927 (predict-yes) 9064--- END Decision Phase --- 9065 9066--- Application Phase --- 9067 --- Firing Productions (PE) For State At Depth 1 --- 9068 9069--- Inner Elaboration Phase, active level 1 (S1) --- 9070Firing apply*operator 9071 --> 9072 (I3 ^predict-yes N964 + :O ) 9073Firing apply*operator*complete 9074 --> 9075 (I3 ^predict-no N963 - :O ) 9076 inner elaboration loop at bottom goal. 9077 --- Change Working Memory (PE) --- 9078=>WM: (13498: I3 ^predict-yes N964) 9079<=WM: (13485: N963 ^status complete) 9080<=WM: (13484: I3 ^predict-no N963) 9081 --- Firing Productions (IE) For State At Depth 1 --- 9082 9083--- Inner Elaboration Phase, active level 1 (S1) --- 9084Firing monitor*world 9085 --> 9086 9087I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 9088 --- Change Working Memory (IE) --- 9089 9090--- END Application Phase --- 9091--- Output Phase --- 9092ENV: Agent did: predict-yes for direction L in state State-B 9093In State-B moving L 9094ENV: (next state, see, prediction correct?) = (State-A, 1, True) 9095predict error 0 9096dir: dir isR 9097--- END Output Phase --- 9098/|\--- Input Phase --- 9099=>WM: (13502: I2 ^dir R) 9100=>WM: (13501: I2 ^reward 1) 9101=>WM: (13500: I2 ^see 1) 9102=>WM: (13499: N964 ^status complete) 9103<=WM: (13488: I2 ^dir L) 9104<=WM: (13487: I2 ^reward 1) 9105<=WM: (13486: I2 ^see 0) 9106=>WM: (13503: I2 ^level-1 L1-root) 9107<=WM: (13489: I2 ^level-1 R1-root) 9108 9109--- END Input Phase --- 9110 9111--- Proposal Phase --- 9112 9113--- Inner Elaboration Phase, active level 1 (S1) --- 9114Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9115 --> 9116 (S1 ^operator O1927 = 0.7065565782519569) 9117Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9118 --> 9119 (S1 ^operator O1928 = -0.1937987592593187) 9120Firing prefer*rvt*predict-no*H0*6*v1*H1 9121 --> 9122Firing prefer*rvt*predict-yes*H0*5*v1*H1 9123 --> 9124Firing elaborate*copy-see-to-output-link 9125 --> 9126 (I3 ^see 1 +) 9127Firing elaborate*reward*based*on*reward 9128 --> 9129 (R968 ^value 1 +) 9130 (R1 ^reward R968 +) 9131Firing propose*predict-yes 9132 --> 9133 (O1929 ^name predict-yes +) 9134 (S1 ^operator O1929 +) 9135Firing propose*predict-no 9136 --> 9137 (O1930 ^name predict-no +) 9138 (S1 ^operator O1930 +) 9139Firing rl*prefer*rvt*predict-no*H0*6 9140 --> 9141 (S1 ^operator O1928 = 0.2298717920574965) 9142Firing rl*prefer*rvt*predict-yes*H0*5 9143 --> 9144 (S1 ^operator O1927 = 0.2940412798984666) 9145Firing prefer*rvt*predict-yes*H0 9146 --> 9147Firing prefer*rvt*predict-no*H0 9148 --> 9149Firing elaborate*copy-dir-to-output-link 9150 --> 9151 (I3 ^dir R +) 9152 inner elaboration loop at bottom goal. 9153Retracting elaborate*copy-see-to-output-link 9154 --> 9155 (I3 ^see 0 +) 9156Retracting propose*predict-no 9157 --> 9158 (O1928 ^name predict-no +) 9159 (S1 ^operator O1928 +) 9160Retracting propose*predict-yes 9161 --> 9162 (O1927 ^name predict-yes +) 9163 (S1 ^operator O1927 +) 9164Retracting elaborate*reward*based*on*reward 9165 --> 9166 (R967 ^value 1 +) 9167 (R1 ^reward R967 +) 9168Retracting elaborate*copy-dir-to-output-link 9169 --> 9170 (I3 ^dir L +) 9171Retracting rl*prefer*rvt*predict-no*H0*2 9172 --> 9173 (S1 ^operator O1928 = 0.3140405292214645) 9174Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9175 --> 9176 (S1 ^operator O1928 = -0.1479504104026684) 9177Retracting rl*prefer*rvt*predict-yes*H0*1 9178 --> 9179 (S1 ^operator O1927 = 0.3804255857519139) 9180Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9181 --> 9182 (S1 ^operator O1927 = 0.619629119351056) 9183=>WM: (13511: S1 ^operator O1930 +) 9184=>WM: (13510: S1 ^operator O1929 +) 9185=>WM: (13509: I3 ^dir R) 9186=>WM: (13508: O1930 ^name predict-no) 9187=>WM: (13507: O1929 ^name predict-yes) 9188=>WM: (13506: R968 ^value 1) 9189=>WM: (13505: R1 ^reward R968) 9190=>WM: (13504: I3 ^see 1) 9191<=WM: (13495: S1 ^operator O1927 +) 9192<=WM: (13497: S1 ^operator O1927) 9193<=WM: (13496: S1 ^operator O1928 +) 9194<=WM: (13494: I3 ^dir L) 9195<=WM: (13490: R1 ^reward R967) 9196<=WM: (13450: I3 ^see 0) 9197<=WM: (13493: O1928 ^name predict-no) 9198<=WM: (13492: O1927 ^name predict-yes) 9199<=WM: (13491: R967 ^value 1) 9200 9201--- Inner Elaboration Phase, active level 1 (S1) --- 9202Firing prefer*rvt*predict-yes*H0 9203 --> 9204Firing rl*prefer*rvt*predict-yes*H0*5 9205 --> 9206 (S1 ^operator O1929 = 0.2940412798984666) 9207Firing prefer*rvt*predict-yes*H0*5*v1*H1 9208 --> 9209Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9210 --> 9211 (S1 ^operator O1929 = 0.7065565782519569) 9212Firing prefer*rvt*predict-no*H0 9213 --> 9214Firing rl*prefer*rvt*predict-no*H0*6 9215 --> 9216 (S1 ^operator O1930 = 0.2298717920574965) 9217Firing prefer*rvt*predict-no*H0*6*v1*H1 9218 --> 9219Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9220 --> 9221 (S1 ^operator O1930 = -0.1937987592593187) 9222 inner elaboration loop at bottom goal. 9223Retracting rl*prefer*rvt*predict-no*H0*6 9224 --> 9225 (S1 ^operator O1928 = 0.2298717920574965) 9226Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9227 --> 9228 (S1 ^operator O1928 = -0.1937987592593187) 9229Retracting rl*prefer*rvt*predict-yes*H0*5 9230 --> 9231 (S1 ^operator O1927 = 0.2940412798984666) 9232Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9233 --> 9234 (S1 ^operator O1927 = 0.7065565782519569) 9235 9236--- END Proposal Phase --- 9237 9238--- Decision Phase --- 9239RL update rl*prefer*rvt*predict-yes*H0*1 0.521357 -0.140931 0.380426 -> 0.521352 -0.140931 0.380421(R,m,v=1,0.821656,0.147477) 9240RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478703 0.140926 0.619629 -> 0.478697 0.140926 0.619624(R,m,v=1,1,0) 9241=>WM: (13512: S1 ^operator O1929) 9242 9243 965: O: O1929 (predict-yes) 9244--- END Decision Phase --- 9245 9246--- Application Phase --- 9247 --- Firing Productions (PE) For State At Depth 1 --- 9248 9249--- Inner Elaboration Phase, active level 1 (S1) --- 9250Firing apply*operator 9251 --> 9252 (I3 ^predict-yes N965 + :O ) 9253Firing apply*operator*complete 9254 --> 9255 (I3 ^predict-yes N964 - :O ) 9256 inner elaboration loop at bottom goal. 9257 --- Change Working Memory (PE) --- 9258=>WM: (13513: I3 ^predict-yes N965) 9259<=WM: (13499: N964 ^status complete) 9260<=WM: (13498: I3 ^predict-yes N964) 9261 --- Firing Productions (IE) For State At Depth 1 --- 9262 9263--- Inner Elaboration Phase, active level 1 (S1) --- 9264Firing monitor*world 9265 --> 9266 9267I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 9268 --- Change Working Memory (IE) --- 9269 9270--- END Application Phase --- 9271--- Output Phase --- 9272ENV: Agent did: predict-yes for direction R in state State-A 9273In State-A moving R 9274ENV: (next state, see, prediction correct?) = (State-B, 1, True) 9275predict error 0 9276dir: dir isU 9277--- END Output Phase --- 9278-/|--- Input Phase --- 9279=>WM: (13517: I2 ^dir U) 9280=>WM: (13516: I2 ^reward 1) 9281=>WM: (13515: I2 ^see 1) 9282=>WM: (13514: N965 ^status complete) 9283<=WM: (13502: I2 ^dir R) 9284<=WM: (13501: I2 ^reward 1) 9285<=WM: (13500: I2 ^see 1) 9286=>WM: (13518: I2 ^level-1 R1-root) 9287<=WM: (13503: I2 ^level-1 L1-root) 9288 9289--- END Input Phase --- 9290 9291--- Proposal Phase --- 9292 9293--- Inner Elaboration Phase, active level 1 (S1) --- 9294Firing elaborate*copy-see-to-output-link 9295 --> 9296 (I3 ^see 1 +) 9297Firing elaborate*reward*based*on*reward 9298 --> 9299 (R969 ^value 1 +) 9300 (R1 ^reward R969 +) 9301Firing propose*predict-yes 9302 --> 9303 (O1931 ^name predict-yes +) 9304 (S1 ^operator O1931 +) 9305Firing propose*predict-no 9306 --> 9307 (O1932 ^name predict-no +) 9308 (S1 ^operator O1932 +) 9309Firing rl*prefer*rvt*predict-no*H0*4 9310 --> 9311 (S1 ^operator O1930 = 1.) 9312Firing rl*prefer*rvt*predict-yes*H0*3 9313 --> 9314 (S1 ^operator O1929 = 0.) 9315Firing prefer*rvt*predict-yes*H0 9316 --> 9317Firing prefer*rvt*predict-no*H0 9318 --> 9319Firing elaborate*copy-dir-to-output-link 9320 --> 9321 (I3 ^dir U +) 9322 inner elaboration loop at bottom goal. 9323Retracting elaborate*copy-see-to-output-link 9324 --> 9325 (I3 ^see 1 +) 9326Retracting propose*predict-no 9327 --> 9328 (O1930 ^name predict-no +) 9329 (S1 ^operator O1930 +) 9330Retracting propose*predict-yes 9331 --> 9332 (O1929 ^name predict-yes +) 9333 (S1 ^operator O1929 +) 9334Retracting elaborate*reward*based*on*reward 9335 --> 9336 (R968 ^value 1 +) 9337 (R1 ^reward R968 +) 9338Retracting elaborate*copy-dir-to-output-link 9339 --> 9340 (I3 ^dir R +) 9341Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9342 --> 9343 (S1 ^operator O1930 = -0.1937987592593187) 9344Retracting rl*prefer*rvt*predict-no*H0*6 9345 --> 9346 (S1 ^operator O1930 = 0.2298717920574965) 9347Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9348 --> 9349 (S1 ^operator O1929 = 0.7065565782519569) 9350Retracting rl*prefer*rvt*predict-yes*H0*5 9351 --> 9352 (S1 ^operator O1929 = 0.2940412798984666) 9353=>WM: (13525: S1 ^operator O1932 +) 9354=>WM: (13524: S1 ^operator O1931 +) 9355=>WM: (13523: I3 ^dir U) 9356=>WM: (13522: O1932 ^name predict-no) 9357=>WM: (13521: O1931 ^name predict-yes) 9358=>WM: (13520: R969 ^value 1) 9359=>WM: (13519: R1 ^reward R969) 9360<=WM: (13510: S1 ^operator O1929 +) 9361<=WM: (13512: S1 ^operator O1929) 9362<=WM: (13511: S1 ^operator O1930 +) 9363<=WM: (13509: I3 ^dir R) 9364<=WM: (13505: R1 ^reward R968) 9365<=WM: (13508: O1930 ^name predict-no) 9366<=WM: (13507: O1929 ^name predict-yes) 9367<=WM: (13506: R968 ^value 1) 9368 9369--- Inner Elaboration Phase, active level 1 (S1) --- 9370Firing prefer*rvt*predict-yes*H0 9371 --> 9372Firing rl*prefer*rvt*predict-yes*H0*3 9373 --> 9374 (S1 ^operator O1931 = 0.) 9375Firing prefer*rvt*predict-no*H0 9376 --> 9377Firing rl*prefer*rvt*predict-no*H0*4 9378 --> 9379 (S1 ^operator O1932 = 1.) 9380 inner elaboration loop at bottom goal. 9381Retracting rl*prefer*rvt*predict-no*H0*4 9382 --> 9383 (S1 ^operator O1930 = 1.) 9384Retracting rl*prefer*rvt*predict-yes*H0*3 9385 --> 9386 (S1 ^operator O1929 = 0.) 9387 9388--- END Proposal Phase --- 9389 9390--- Decision Phase --- 9391RL update rl*prefer*rvt*predict-yes*H0*5 0.50111 -0.207069 0.294041 -> 0.501065 -0.207074 0.293991(R,m,v=1,0.837838,0.13679) 9392RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499427 0.207129 0.706557 -> 0.499374 0.207123 0.706498(R,m,v=1,1,0) 9393=>WM: (13526: S1 ^operator O1932) 9394 9395 966: O: O1932 (predict-no) 9396--- END Decision Phase --- 9397 9398--- Application Phase --- 9399 --- Firing Productions (PE) For State At Depth 1 --- 9400 9401--- Inner Elaboration Phase, active level 1 (S1) --- 9402Firing apply*operator 9403 --> 9404 (I3 ^predict-no N966 + :O ) 9405Firing apply*operator*complete 9406 --> 9407 (I3 ^predict-yes N965 - :O ) 9408 inner elaboration loop at bottom goal. 9409 --- Change Working Memory (PE) --- 9410=>WM: (13527: I3 ^predict-no N966) 9411<=WM: (13514: N965 ^status complete) 9412<=WM: (13513: I3 ^predict-yes N965) 9413 --- Firing Productions (IE) For State At Depth 1 --- 9414 9415--- Inner Elaboration Phase, active level 1 (S1) --- 9416Firing monitor*world 9417 --> 9418 9419I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 9420 --- Change Working Memory (IE) --- 9421 9422--- END Application Phase --- 9423--- Output Phase --- 9424ENV: Agent did: predict-no for direction U in state State-B 9425In State-B moving U 9426ENV: (next state, see, prediction correct?) = (State-B, 0, True) 9427predict error 0 9428dir: dir isL 9429--- END Output Phase --- 9430\-/--- Input Phase --- 9431=>WM: (13531: I2 ^dir L) 9432=>WM: (13530: I2 ^reward 1) 9433=>WM: (13529: I2 ^see 0) 9434=>WM: (13528: N966 ^status complete) 9435<=WM: (13517: I2 ^dir U) 9436<=WM: (13516: I2 ^reward 1) 9437<=WM: (13515: I2 ^see 1) 9438=>WM: (13532: I2 ^level-1 R1-root) 9439<=WM: (13518: I2 ^level-1 R1-root) 9440 9441--- END Input Phase --- 9442 9443--- Proposal Phase --- 9444 9445--- Inner Elaboration Phase, active level 1 (S1) --- 9446Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9447 --> 9448 (S1 ^operator O1931 = 0.6196238010864294) 9449Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9450 --> 9451 (S1 ^operator O1932 = -0.1479504104026684) 9452Firing prefer*rvt*predict-no*H0*2*v1*H1 9453 --> 9454Firing prefer*rvt*predict-yes*H0*1*v1*H1 9455 --> 9456Firing elaborate*copy-see-to-output-link 9457 --> 9458 (I3 ^see 0 +) 9459Firing elaborate*reward*based*on*reward 9460 --> 9461 (R970 ^value 1 +) 9462 (R1 ^reward R970 +) 9463Firing propose*predict-yes 9464 --> 9465 (O1933 ^name predict-yes +) 9466 (S1 ^operator O1933 +) 9467Firing propose*predict-no 9468 --> 9469 (O1934 ^name predict-no +) 9470 (S1 ^operator O1934 +) 9471Firing rl*prefer*rvt*predict-no*H0*2 9472 --> 9473 (S1 ^operator O1932 = 0.3140405292214645) 9474Firing rl*prefer*rvt*predict-yes*H0*1 9475 --> 9476 (S1 ^operator O1931 = 0.380421069331616) 9477Firing prefer*rvt*predict-yes*H0 9478 --> 9479Firing prefer*rvt*predict-no*H0 9480 --> 9481Firing elaborate*copy-dir-to-output-link 9482 --> 9483 (I3 ^dir L +) 9484 inner elaboration loop at bottom goal. 9485Retracting elaborate*copy-see-to-output-link 9486 --> 9487 (I3 ^see 1 +) 9488Retracting propose*predict-no 9489 --> 9490 (O1932 ^name predict-no +) 9491 (S1 ^operator O1932 +) 9492Retracting propose*predict-yes 9493 --> 9494 (O1931 ^name predict-yes +) 9495 (S1 ^operator O1931 +) 9496Retracting elaborate*reward*based*on*reward 9497 --> 9498 (R969 ^value 1 +) 9499 (R1 ^reward R969 +) 9500Retracting elaborate*copy-dir-to-output-link 9501 --> 9502 (I3 ^dir U +) 9503Retracting rl*prefer*rvt*predict-no*H0*4 9504 --> 9505 (S1 ^operator O1932 = 1.) 9506Retracting rl*prefer*rvt*predict-yes*H0*3 9507 --> 9508 (S1 ^operator O1931 = 0.) 9509=>WM: (13540: S1 ^operator O1934 +) 9510=>WM: (13539: S1 ^operator O1933 +) 9511=>WM: (13538: I3 ^dir L) 9512=>WM: (13537: O1934 ^name predict-no) 9513=>WM: (13536: O1933 ^name predict-yes) 9514=>WM: (13535: R970 ^value 1) 9515=>WM: (13534: R1 ^reward R970) 9516=>WM: (13533: I3 ^see 0) 9517<=WM: (13524: S1 ^operator O1931 +) 9518<=WM: (13525: S1 ^operator O1932 +) 9519<=WM: (13526: S1 ^operator O1932) 9520<=WM: (13523: I3 ^dir U) 9521<=WM: (13519: R1 ^reward R969) 9522<=WM: (13504: I3 ^see 1) 9523<=WM: (13522: O1932 ^name predict-no) 9524<=WM: (13521: O1931 ^name predict-yes) 9525<=WM: (13520: R969 ^value 1) 9526 9527--- Inner Elaboration Phase, active level 1 (S1) --- 9528Firing prefer*rvt*predict-yes*H0 9529 --> 9530Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9531 --> 9532 (S1 ^operator O1933 = 0.6196238010864294) 9533Firing rl*prefer*rvt*predict-yes*H0*1 9534 --> 9535 (S1 ^operator O1933 = 0.380421069331616) 9536Firing prefer*rvt*predict-yes*H0*1*v1*H1 9537 --> 9538Firing prefer*rvt*predict-no*H0 9539 --> 9540Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9541 --> 9542 (S1 ^operator O1934 = -0.1479504104026684) 9543Firing rl*prefer*rvt*predict-no*H0*2 9544 --> 9545 (S1 ^operator O1934 = 0.3140405292214645) 9546Firing prefer*rvt*predict-no*H0*2*v1*H1 9547 --> 9548 inner elaboration loop at bottom goal. 9549Retracting rl*prefer*rvt*predict-no*H0*2 9550 --> 9551 (S1 ^operator O1932 = 0.3140405292214645) 9552Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9553 --> 9554 (S1 ^operator O1932 = -0.1479504104026684) 9555Retracting rl*prefer*rvt*predict-yes*H0*1 9556 --> 9557 (S1 ^operator O1931 = 0.380421069331616) 9558Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9559 --> 9560 (S1 ^operator O1931 = 0.6196238010864294) 9561 9562--- END Proposal Phase --- 9563 9564--- Decision Phase --- 9565RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 9566=>WM: (13541: S1 ^operator O1933) 9567 9568 967: O: O1933 (predict-yes) 9569--- END Decision Phase --- 9570 9571--- Application Phase --- 9572 --- Firing Productions (PE) For State At Depth 1 --- 9573 9574--- Inner Elaboration Phase, active level 1 (S1) --- 9575Firing apply*operator 9576 --> 9577 (I3 ^predict-yes N967 + :O ) 9578Firing apply*operator*complete 9579 --> 9580 (I3 ^predict-no N966 - :O ) 9581 inner elaboration loop at bottom goal. 9582 --- Change Working Memory (PE) --- 9583=>WM: (13542: I3 ^predict-yes N967) 9584<=WM: (13528: N966 ^status complete) 9585<=WM: (13527: I3 ^predict-no N966) 9586 --- Firing Productions (IE) For State At Depth 1 --- 9587 9588--- Inner Elaboration Phase, active level 1 (S1) --- 9589Firing monitor*world 9590 --> 9591 9592I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 9593 --- Change Working Memory (IE) --- 9594 9595--- END Application Phase --- 9596--- Output Phase --- 9597ENV: Agent did: predict-yes for direction L in state State-B 9598In State-B moving L 9599ENV: (next state, see, prediction correct?) = (State-A, 1, True) 9600predict error 0 9601dir: dir isR 9602--- END Output Phase --- 9603|\---- Input Phase --- 9604=>WM: (13546: I2 ^dir R) 9605=>WM: (13545: I2 ^reward 1) 9606=>WM: (13544: I2 ^see 1) 9607=>WM: (13543: N967 ^status complete) 9608<=WM: (13531: I2 ^dir L) 9609<=WM: (13530: I2 ^reward 1) 9610<=WM: (13529: I2 ^see 0) 9611=>WM: (13547: I2 ^level-1 L1-root) 9612<=WM: (13532: I2 ^level-1 R1-root) 9613 9614--- END Input Phase --- 9615 9616--- Proposal Phase --- 9617 9618--- Inner Elaboration Phase, active level 1 (S1) --- 9619Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9620 --> 9621 (S1 ^operator O1933 = 0.7064977054068989) 9622Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9623 --> 9624 (S1 ^operator O1934 = -0.1937987592593187) 9625Firing prefer*rvt*predict-no*H0*6*v1*H1 9626 --> 9627Firing prefer*rvt*predict-yes*H0*5*v1*H1 9628 --> 9629Firing elaborate*copy-see-to-output-link 9630 --> 9631 (I3 ^see 1 +) 9632Firing elaborate*reward*based*on*reward 9633 --> 9634 (R971 ^value 1 +) 9635 (R1 ^reward R971 +) 9636Firing propose*predict-yes 9637 --> 9638 (O1935 ^name predict-yes +) 9639 (S1 ^operator O1935 +) 9640Firing propose*predict-no 9641 --> 9642 (O1936 ^name predict-no +) 9643 (S1 ^operator O1936 +) 9644Firing rl*prefer*rvt*predict-no*H0*6 9645 --> 9646 (S1 ^operator O1934 = 0.2298717920574965) 9647Firing rl*prefer*rvt*predict-yes*H0*5 9648 --> 9649 (S1 ^operator O1933 = 0.2939914352270483) 9650Firing prefer*rvt*predict-yes*H0 9651 --> 9652Firing prefer*rvt*predict-no*H0 9653 --> 9654Firing elaborate*copy-dir-to-output-link 9655 --> 9656 (I3 ^dir R +) 9657 inner elaboration loop at bottom goal. 9658Retracting elaborate*copy-see-to-output-link 9659 --> 9660 (I3 ^see 0 +) 9661Retracting propose*predict-no 9662 --> 9663 (O1934 ^name predict-no +) 9664 (S1 ^operator O1934 +) 9665Retracting propose*predict-yes 9666 --> 9667 (O1933 ^name predict-yes +) 9668 (S1 ^operator O1933 +) 9669Retracting elaborate*reward*based*on*reward 9670 --> 9671 (R970 ^value 1 +) 9672 (R1 ^reward R970 +) 9673Retracting elaborate*copy-dir-to-output-link 9674 --> 9675 (I3 ^dir L +) 9676Retracting rl*prefer*rvt*predict-no*H0*2 9677 --> 9678 (S1 ^operator O1934 = 0.3140405292214645) 9679Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9680 --> 9681 (S1 ^operator O1934 = -0.1479504104026684) 9682Retracting rl*prefer*rvt*predict-yes*H0*1 9683 --> 9684 (S1 ^operator O1933 = 0.380421069331616) 9685Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9686 --> 9687 (S1 ^operator O1933 = 0.6196238010864294) 9688=>WM: (13555: S1 ^operator O1936 +) 9689=>WM: (13554: S1 ^operator O1935 +) 9690=>WM: (13553: I3 ^dir R) 9691=>WM: (13552: O1936 ^name predict-no) 9692=>WM: (13551: O1935 ^name predict-yes) 9693=>WM: (13550: R971 ^value 1) 9694=>WM: (13549: R1 ^reward R971) 9695=>WM: (13548: I3 ^see 1) 9696<=WM: (13539: S1 ^operator O1933 +) 9697<=WM: (13541: S1 ^operator O1933) 9698<=WM: (13540: S1 ^operator O1934 +) 9699<=WM: (13538: I3 ^dir L) 9700<=WM: (13534: R1 ^reward R970) 9701<=WM: (13533: I3 ^see 0) 9702<=WM: (13537: O1934 ^name predict-no) 9703<=WM: (13536: O1933 ^name predict-yes) 9704<=WM: (13535: R970 ^value 1) 9705 9706--- Inner Elaboration Phase, active level 1 (S1) --- 9707Firing prefer*rvt*predict-yes*H0 9708 --> 9709Firing rl*prefer*rvt*predict-yes*H0*5 9710 --> 9711 (S1 ^operator O1935 = 0.2939914352270483) 9712Firing prefer*rvt*predict-yes*H0*5*v1*H1 9713 --> 9714Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9715 --> 9716 (S1 ^operator O1935 = 0.7064977054068989) 9717Firing prefer*rvt*predict-no*H0 9718 --> 9719Firing rl*prefer*rvt*predict-no*H0*6 9720 --> 9721 (S1 ^operator O1936 = 0.2298717920574965) 9722Firing prefer*rvt*predict-no*H0*6*v1*H1 9723 --> 9724Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9725 --> 9726 (S1 ^operator O1936 = -0.1937987592593187) 9727 inner elaboration loop at bottom goal. 9728Retracting rl*prefer*rvt*predict-no*H0*6 9729 --> 9730 (S1 ^operator O1934 = 0.2298717920574965) 9731Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9732 --> 9733 (S1 ^operator O1934 = -0.1937987592593187) 9734Retracting rl*prefer*rvt*predict-yes*H0*5 9735 --> 9736 (S1 ^operator O1933 = 0.2939914352270483) 9737Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9738 --> 9739 (S1 ^operator O1933 = 0.7064977054068989) 9740 9741--- END Proposal Phase --- 9742 9743--- Decision Phase --- 9744RL update rl*prefer*rvt*predict-yes*H0*1 0.521352 -0.140931 0.380421 -> 0.521348 -0.14093 0.380417(R,m,v=1,0.822785,0.146739) 9745RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478697 0.140926 0.619624 -> 0.478693 0.140927 0.619619(R,m,v=1,1,0) 9746=>WM: (13556: S1 ^operator O1935) 9747 9748 968: O: O1935 (predict-yes) 9749--- END Decision Phase --- 9750 9751--- Application Phase --- 9752 --- Firing Productions (PE) For State At Depth 1 --- 9753 9754--- Inner Elaboration Phase, active level 1 (S1) --- 9755Firing apply*operator 9756 --> 9757 (I3 ^predict-yes N968 + :O ) 9758Firing apply*operator*complete 9759 --> 9760 (I3 ^predict-yes N967 - :O ) 9761 inner elaboration loop at bottom goal. 9762 --- Change Working Memory (PE) --- 9763=>WM: (13557: I3 ^predict-yes N968) 9764<=WM: (13543: N967 ^status complete) 9765<=WM: (13542: I3 ^predict-yes N967) 9766 --- Firing Productions (IE) For State At Depth 1 --- 9767 9768--- Inner Elaboration Phase, active level 1 (S1) --- 9769Firing monitor*world 9770 --> 9771 9772I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 9773 --- Change Working Memory (IE) --- 9774 9775--- END Application Phase --- 9776--- Output Phase --- 9777ENV: Agent did: predict-yes for direction R in state State-A 9778In State-A moving R 9779ENV: (next state, see, prediction correct?) = (State-B, 1, True) 9780predict error 0 9781dir: dir isU 9782--- END Output Phase --- 9783/|\--- Input Phase --- 9784=>WM: (13561: I2 ^dir U) 9785=>WM: (13560: I2 ^reward 1) 9786=>WM: (13559: I2 ^see 1) 9787=>WM: (13558: N968 ^status complete) 9788<=WM: (13546: I2 ^dir R) 9789<=WM: (13545: I2 ^reward 1) 9790<=WM: (13544: I2 ^see 1) 9791=>WM: (13562: I2 ^level-1 R1-root) 9792<=WM: (13547: I2 ^level-1 L1-root) 9793 9794--- END Input Phase --- 9795 9796--- Proposal Phase --- 9797 9798--- Inner Elaboration Phase, active level 1 (S1) --- 9799Firing elaborate*copy-see-to-output-link 9800 --> 9801 (I3 ^see 1 +) 9802Firing elaborate*reward*based*on*reward 9803 --> 9804 (R972 ^value 1 +) 9805 (R1 ^reward R972 +) 9806Firing propose*predict-yes 9807 --> 9808 (O1937 ^name predict-yes +) 9809 (S1 ^operator O1937 +) 9810Firing propose*predict-no 9811 --> 9812 (O1938 ^name predict-no +) 9813 (S1 ^operator O1938 +) 9814Firing rl*prefer*rvt*predict-no*H0*4 9815 --> 9816 (S1 ^operator O1936 = 1.) 9817Firing rl*prefer*rvt*predict-yes*H0*3 9818 --> 9819 (S1 ^operator O1935 = 0.) 9820Firing prefer*rvt*predict-yes*H0 9821 --> 9822Firing prefer*rvt*predict-no*H0 9823 --> 9824Firing elaborate*copy-dir-to-output-link 9825 --> 9826 (I3 ^dir U +) 9827 inner elaboration loop at bottom goal. 9828Retracting elaborate*copy-see-to-output-link 9829 --> 9830 (I3 ^see 1 +) 9831Retracting propose*predict-no 9832 --> 9833 (O1936 ^name predict-no +) 9834 (S1 ^operator O1936 +) 9835Retracting propose*predict-yes 9836 --> 9837 (O1935 ^name predict-yes +) 9838 (S1 ^operator O1935 +) 9839Retracting elaborate*reward*based*on*reward 9840 --> 9841 (R971 ^value 1 +) 9842 (R1 ^reward R971 +) 9843Retracting elaborate*copy-dir-to-output-link 9844 --> 9845 (I3 ^dir R +) 9846Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 9847 --> 9848 (S1 ^operator O1936 = -0.1937987592593187) 9849Retracting rl*prefer*rvt*predict-no*H0*6 9850 --> 9851 (S1 ^operator O1936 = 0.2298717920574965) 9852Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 9853 --> 9854 (S1 ^operator O1935 = 0.7064977054068989) 9855Retracting rl*prefer*rvt*predict-yes*H0*5 9856 --> 9857 (S1 ^operator O1935 = 0.2939914352270483) 9858=>WM: (13569: S1 ^operator O1938 +) 9859=>WM: (13568: S1 ^operator O1937 +) 9860=>WM: (13567: I3 ^dir U) 9861=>WM: (13566: O1938 ^name predict-no) 9862=>WM: (13565: O1937 ^name predict-yes) 9863=>WM: (13564: R972 ^value 1) 9864=>WM: (13563: R1 ^reward R972) 9865<=WM: (13554: S1 ^operator O1935 +) 9866<=WM: (13556: S1 ^operator O1935) 9867<=WM: (13555: S1 ^operator O1936 +) 9868<=WM: (13553: I3 ^dir R) 9869<=WM: (13549: R1 ^reward R971) 9870<=WM: (13552: O1936 ^name predict-no) 9871<=WM: (13551: O1935 ^name predict-yes) 9872<=WM: (13550: R971 ^value 1) 9873 9874--- Inner Elaboration Phase, active level 1 (S1) --- 9875Firing prefer*rvt*predict-yes*H0 9876 --> 9877Firing rl*prefer*rvt*predict-yes*H0*3 9878 --> 9879 (S1 ^operator O1937 = 0.) 9880Firing prefer*rvt*predict-no*H0 9881 --> 9882Firing rl*prefer*rvt*predict-no*H0*4 9883 --> 9884 (S1 ^operator O1938 = 1.) 9885 inner elaboration loop at bottom goal. 9886Retracting rl*prefer*rvt*predict-no*H0*4 9887 --> 9888 (S1 ^operator O1936 = 1.) 9889Retracting rl*prefer*rvt*predict-yes*H0*3 9890 --> 9891 (S1 ^operator O1935 = 0.) 9892 9893--- END Proposal Phase --- 9894 9895--- Decision Phase --- 9896RL update rl*prefer*rvt*predict-yes*H0*5 0.501065 -0.207074 0.293991 -> 0.501028 -0.207078 0.293951(R,m,v=1,0.838926,0.136042) 9897RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499374 0.207123 0.706498 -> 0.499331 0.207118 0.70645(R,m,v=1,1,0) 9898=>WM: (13570: S1 ^operator O1938) 9899 9900 969: O: O1938 (predict-no) 9901--- END Decision Phase --- 9902 9903--- Application Phase --- 9904 --- Firing Productions (PE) For State At Depth 1 --- 9905 9906--- Inner Elaboration Phase, active level 1 (S1) --- 9907Firing apply*operator 9908 --> 9909 (I3 ^predict-no N969 + :O ) 9910Firing apply*operator*complete 9911 --> 9912 (I3 ^predict-yes N968 - :O ) 9913 inner elaboration loop at bottom goal. 9914 --- Change Working Memory (PE) --- 9915=>WM: (13571: I3 ^predict-no N969) 9916<=WM: (13558: N968 ^status complete) 9917<=WM: (13557: I3 ^predict-yes N968) 9918 --- Firing Productions (IE) For State At Depth 1 --- 9919 9920--- Inner Elaboration Phase, active level 1 (S1) --- 9921Firing monitor*world 9922 --> 9923 9924I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 9925 --- Change Working Memory (IE) --- 9926 9927--- END Application Phase --- 9928--- Output Phase --- 9929ENV: Agent did: predict-no for direction U in state State-B 9930In State-B moving U 9931ENV: (next state, see, prediction correct?) = (State-B, 0, True) 9932predict error 0 9933dir: dir isL 9934--- END Output Phase --- 9935-/|--- Input Phase --- 9936=>WM: (13575: I2 ^dir L) 9937=>WM: (13574: I2 ^reward 1) 9938=>WM: (13573: I2 ^see 0) 9939=>WM: (13572: N969 ^status complete) 9940<=WM: (13561: I2 ^dir U) 9941<=WM: (13560: I2 ^reward 1) 9942<=WM: (13559: I2 ^see 1) 9943=>WM: (13576: I2 ^level-1 R1-root) 9944<=WM: (13562: I2 ^level-1 R1-root) 9945 9946--- END Input Phase --- 9947 9948--- Proposal Phase --- 9949 9950--- Inner Elaboration Phase, active level 1 (S1) --- 9951Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 9952 --> 9953 (S1 ^operator O1937 = 0.6196194522363663) 9954Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 9955 --> 9956 (S1 ^operator O1938 = -0.1479504104026684) 9957Firing prefer*rvt*predict-no*H0*2*v1*H1 9958 --> 9959Firing prefer*rvt*predict-yes*H0*1*v1*H1 9960 --> 9961Firing elaborate*copy-see-to-output-link 9962 --> 9963 (I3 ^see 0 +) 9964Firing elaborate*reward*based*on*reward 9965 --> 9966 (R973 ^value 1 +) 9967 (R1 ^reward R973 +) 9968Firing propose*predict-yes 9969 --> 9970 (O1939 ^name predict-yes +) 9971 (S1 ^operator O1939 +) 9972Firing propose*predict-no 9973 --> 9974 (O1940 ^name predict-no +) 9975 (S1 ^operator O1940 +) 9976Firing rl*prefer*rvt*predict-no*H0*2 9977 --> 9978 (S1 ^operator O1938 = 0.3140405292214645) 9979Firing rl*prefer*rvt*predict-yes*H0*1 9980 --> 9981 (S1 ^operator O1937 = 0.3804173687365902) 9982Firing prefer*rvt*predict-yes*H0 9983 --> 9984Firing prefer*rvt*predict-no*H0 9985 --> 9986Firing elaborate*copy-dir-to-output-link 9987 --> 9988 (I3 ^dir L +) 9989 inner elaboration loop at bottom goal. 9990Retracting elaborate*copy-see-to-output-link 9991 --> 9992 (I3 ^see 1 +) 9993Retracting propose*predict-no 9994 --> 9995 (O1938 ^name predict-no +) 9996 (S1 ^operator O1938 +) 9997Retracting propose*predict-yes 9998 --> 9999 (O1937 ^name predict-yes +) 10000 (S1 ^operator O1937 +) 10001Retracting elaborate*reward*based*on*reward 10002 --> 10003 (R972 ^value 1 +) 10004 (R1 ^reward R972 +) 10005Retracting elaborate*copy-dir-to-output-link 10006 --> 10007 (I3 ^dir U +) 10008Retracting rl*prefer*rvt*predict-no*H0*4 10009 --> 10010 (S1 ^operator O1938 = 1.) 10011Retracting rl*prefer*rvt*predict-yes*H0*3 10012 --> 10013 (S1 ^operator O1937 = 0.) 10014=>WM: (13584: S1 ^operator O1940 +) 10015=>WM: (13583: S1 ^operator O1939 +) 10016=>WM: (13582: I3 ^dir L) 10017=>WM: (13581: O1940 ^name predict-no) 10018=>WM: (13580: O1939 ^name predict-yes) 10019=>WM: (13579: R973 ^value 1) 10020=>WM: (13578: R1 ^reward R973) 10021=>WM: (13577: I3 ^see 0) 10022<=WM: (13568: S1 ^operator O1937 +) 10023<=WM: (13569: S1 ^operator O1938 +) 10024<=WM: (13570: S1 ^operator O1938) 10025<=WM: (13567: I3 ^dir U) 10026<=WM: (13563: R1 ^reward R972) 10027<=WM: (13548: I3 ^see 1) 10028<=WM: (13566: O1938 ^name predict-no) 10029<=WM: (13565: O1937 ^name predict-yes) 10030<=WM: (13564: R972 ^value 1) 10031 10032--- Inner Elaboration Phase, active level 1 (S1) --- 10033Firing prefer*rvt*predict-yes*H0 10034 --> 10035Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10036 --> 10037 (S1 ^operator O1939 = 0.6196194522363663) 10038Firing rl*prefer*rvt*predict-yes*H0*1 10039 --> 10040 (S1 ^operator O1939 = 0.3804173687365902) 10041Firing prefer*rvt*predict-yes*H0*1*v1*H1 10042 --> 10043Firing prefer*rvt*predict-no*H0 10044 --> 10045Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10046 --> 10047 (S1 ^operator O1940 = -0.1479504104026684) 10048Firing rl*prefer*rvt*predict-no*H0*2 10049 --> 10050 (S1 ^operator O1940 = 0.3140405292214645) 10051Firing prefer*rvt*predict-no*H0*2*v1*H1 10052 --> 10053 inner elaboration loop at bottom goal. 10054Retracting rl*prefer*rvt*predict-no*H0*2 10055 --> 10056 (S1 ^operator O1938 = 0.3140405292214645) 10057Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10058 --> 10059 (S1 ^operator O1938 = -0.1479504104026684) 10060Retracting rl*prefer*rvt*predict-yes*H0*1 10061 --> 10062 (S1 ^operator O1937 = 0.3804173687365902) 10063Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10064 --> 10065 (S1 ^operator O1937 = 0.6196194522363663) 10066 10067--- END Proposal Phase --- 10068 10069--- Decision Phase --- 10070RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 10071=>WM: (13585: S1 ^operator O1939) 10072 10073 970: O: O1939 (predict-yes) 10074--- END Decision Phase --- 10075 10076--- Application Phase --- 10077 --- Firing Productions (PE) For State At Depth 1 --- 10078 10079--- Inner Elaboration Phase, active level 1 (S1) --- 10080Firing apply*operator 10081 --> 10082 (I3 ^predict-yes N970 + :O ) 10083Firing apply*operator*complete 10084 --> 10085 (I3 ^predict-no N969 - :O ) 10086 inner elaboration loop at bottom goal. 10087 --- Change Working Memory (PE) --- 10088=>WM: (13586: I3 ^predict-yes N970) 10089<=WM: (13572: N969 ^status complete) 10090<=WM: (13571: I3 ^predict-no N969) 10091 --- Firing Productions (IE) For State At Depth 1 --- 10092 10093--- Inner Elaboration Phase, active level 1 (S1) --- 10094Firing monitor*world 10095 --> 10096 10097I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 10098 --- Change Working Memory (IE) --- 10099 10100--- END Application Phase --- 10101--- Output Phase --- 10102ENV: Agent did: predict-yes for direction L in state State-B 10103In State-B moving L 10104ENV: (next state, see, prediction correct?) = (State-A, 1, True) 10105predict error 0 10106dir: dir isU 10107--- END Output Phase --- 10108\-/--- Input Phase --- 10109=>WM: (13590: I2 ^dir U) 10110=>WM: (13589: I2 ^reward 1) 10111=>WM: (13588: I2 ^see 1) 10112=>WM: (13587: N970 ^status complete) 10113<=WM: (13575: I2 ^dir L) 10114<=WM: (13574: I2 ^reward 1) 10115<=WM: (13573: I2 ^see 0) 10116=>WM: (13591: I2 ^level-1 L1-root) 10117<=WM: (13576: I2 ^level-1 R1-root) 10118 10119--- END Input Phase --- 10120 10121--- Proposal Phase --- 10122 10123--- Inner Elaboration Phase, active level 1 (S1) --- 10124Firing elaborate*copy-see-to-output-link 10125 --> 10126 (I3 ^see 1 +) 10127Firing elaborate*reward*based*on*reward 10128 --> 10129 (R974 ^value 1 +) 10130 (R1 ^reward R974 +) 10131Firing propose*predict-yes 10132 --> 10133 (O1941 ^name predict-yes +) 10134 (S1 ^operator O1941 +) 10135Firing propose*predict-no 10136 --> 10137 (O1942 ^name predict-no +) 10138 (S1 ^operator O1942 +) 10139Firing rl*prefer*rvt*predict-no*H0*4 10140 --> 10141 (S1 ^operator O1940 = 1.) 10142Firing rl*prefer*rvt*predict-yes*H0*3 10143 --> 10144 (S1 ^operator O1939 = 0.) 10145Firing prefer*rvt*predict-yes*H0 10146 --> 10147Firing prefer*rvt*predict-no*H0 10148 --> 10149Firing elaborate*copy-dir-to-output-link 10150 --> 10151 (I3 ^dir U +) 10152 inner elaboration loop at bottom goal. 10153Retracting elaborate*copy-see-to-output-link 10154 --> 10155 (I3 ^see 0 +) 10156Retracting propose*predict-no 10157 --> 10158 (O1940 ^name predict-no +) 10159 (S1 ^operator O1940 +) 10160Retracting propose*predict-yes 10161 --> 10162 (O1939 ^name predict-yes +) 10163 (S1 ^operator O1939 +) 10164Retracting elaborate*reward*based*on*reward 10165 --> 10166 (R973 ^value 1 +) 10167 (R1 ^reward R973 +) 10168Retracting elaborate*copy-dir-to-output-link 10169 --> 10170 (I3 ^dir L +) 10171Retracting rl*prefer*rvt*predict-no*H0*2 10172 --> 10173 (S1 ^operator O1940 = 0.3140405292214645) 10174Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10175 --> 10176 (S1 ^operator O1940 = -0.1479504104026684) 10177Retracting rl*prefer*rvt*predict-yes*H0*1 10178 --> 10179 (S1 ^operator O1939 = 0.3804173687365902) 10180Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10181 --> 10182 (S1 ^operator O1939 = 0.6196194522363663) 10183=>WM: (13599: S1 ^operator O1942 +) 10184=>WM: (13598: S1 ^operator O1941 +) 10185=>WM: (13597: I3 ^dir U) 10186=>WM: (13596: O1942 ^name predict-no) 10187=>WM: (13595: O1941 ^name predict-yes) 10188=>WM: (13594: R974 ^value 1) 10189=>WM: (13593: R1 ^reward R974) 10190=>WM: (13592: I3 ^see 1) 10191<=WM: (13583: S1 ^operator O1939 +) 10192<=WM: (13585: S1 ^operator O1939) 10193<=WM: (13584: S1 ^operator O1940 +) 10194<=WM: (13582: I3 ^dir L) 10195<=WM: (13578: R1 ^reward R973) 10196<=WM: (13577: I3 ^see 0) 10197<=WM: (13581: O1940 ^name predict-no) 10198<=WM: (13580: O1939 ^name predict-yes) 10199<=WM: (13579: R973 ^value 1) 10200 10201--- Inner Elaboration Phase, active level 1 (S1) --- 10202Firing prefer*rvt*predict-yes*H0 10203 --> 10204Firing rl*prefer*rvt*predict-yes*H0*3 10205 --> 10206 (S1 ^operator O1941 = 0.) 10207Firing prefer*rvt*predict-no*H0 10208 --> 10209Firing rl*prefer*rvt*predict-no*H0*4 10210 --> 10211 (S1 ^operator O1942 = 1.) 10212 inner elaboration loop at bottom goal. 10213Retracting rl*prefer*rvt*predict-no*H0*4 10214 --> 10215 (S1 ^operator O1940 = 1.) 10216Retracting rl*prefer*rvt*predict-yes*H0*3 10217 --> 10218 (S1 ^operator O1939 = 0.) 10219 10220--- END Proposal Phase --- 10221 10222--- Decision Phase --- 10223RL update rl*prefer*rvt*predict-yes*H0*1 0.521348 -0.14093 0.380417 -> 0.521344 -0.14093 0.380414(R,m,v=1,0.823899,0.146007) 10224RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478693 0.140927 0.619619 -> 0.478689 0.140927 0.619616(R,m,v=1,1,0) 10225=>WM: (13600: S1 ^operator O1942) 10226 10227 971: O: O1942 (predict-no) 10228--- END Decision Phase --- 10229 10230--- Application Phase --- 10231 --- Firing Productions (PE) For State At Depth 1 --- 10232 10233--- Inner Elaboration Phase, active level 1 (S1) --- 10234Firing apply*operator 10235 --> 10236 (I3 ^predict-no N971 + :O ) 10237Firing apply*operator*complete 10238 --> 10239 (I3 ^predict-yes N970 - :O ) 10240 inner elaboration loop at bottom goal. 10241 --- Change Working Memory (PE) --- 10242=>WM: (13601: I3 ^predict-no N971) 10243<=WM: (13587: N970 ^status complete) 10244<=WM: (13586: I3 ^predict-yes N970) 10245 --- Firing Productions (IE) For State At Depth 1 --- 10246 10247--- Inner Elaboration Phase, active level 1 (S1) --- 10248Firing monitor*world 10249 --> 10250 10251I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 10252 --- Change Working Memory (IE) --- 10253 10254--- END Application Phase --- 10255--- Output Phase --- 10256ENV: Agent did: predict-no for direction U in state State-A 10257In State-A moving U 10258ENV: (next state, see, prediction correct?) = (State-A, 0, True) 10259predict error 0 10260dir: dir isL 10261--- END Output Phase --- 10262|--- Input Phase --- 10263=>WM: (13605: I2 ^dir L) 10264=>WM: (13604: I2 ^reward 1) 10265=>WM: (13603: I2 ^see 0) 10266=>WM: (13602: N971 ^status complete) 10267<=WM: (13590: I2 ^dir U) 10268<=WM: (13589: I2 ^reward 1) 10269<=WM: (13588: I2 ^see 1) 10270=>WM: (13606: I2 ^level-1 L1-root) 10271<=WM: (13591: I2 ^level-1 L1-root) 10272 10273--- END Input Phase --- 10274 10275--- Proposal Phase --- 10276 10277--- Inner Elaboration Phase, active level 1 (S1) --- 10278Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 10279 --> 10280 (S1 ^operator O1941 = -0.3470159027404986) 10281Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 10282 --> 10283 (S1 ^operator O1942 = 0.6861654297024582) 10284Firing prefer*rvt*predict-no*H0*2*v1*H1 10285 --> 10286Firing prefer*rvt*predict-yes*H0*1*v1*H1 10287 --> 10288Firing elaborate*copy-see-to-output-link 10289 --> 10290 (I3 ^see 0 +) 10291Firing elaborate*reward*based*on*reward 10292 --> 10293 (R975 ^value 1 +) 10294 (R1 ^reward R975 +) 10295Firing propose*predict-yes 10296 --> 10297 (O1943 ^name predict-yes +) 10298 (S1 ^operator O1943 +) 10299Firing propose*predict-no 10300 --> 10301 (O1944 ^name predict-no +) 10302 (S1 ^operator O1944 +) 10303Firing rl*prefer*rvt*predict-no*H0*2 10304 --> 10305 (S1 ^operator O1942 = 0.3140405292214645) 10306Firing rl*prefer*rvt*predict-yes*H0*1 10307 --> 10308 (S1 ^operator O1941 = 0.3804143351598744) 10309Firing prefer*rvt*predict-yes*H0 10310 --> 10311Firing prefer*rvt*predict-no*H0 10312 --> 10313Firing elaborate*copy-dir-to-output-link 10314 --> 10315 (I3 ^dir L +) 10316 inner elaboration loop at bottom goal. 10317Retracting elaborate*copy-see-to-output-link 10318 --> 10319 (I3 ^see 1 +) 10320Retracting propose*predict-no 10321 --> 10322 (O1942 ^name predict-no +) 10323 (S1 ^operator O1942 +) 10324Retracting propose*predict-yes 10325 --> 10326 (O1941 ^name predict-yes +) 10327 (S1 ^operator O1941 +) 10328Retracting elaborate*reward*based*on*reward 10329 --> 10330 (R974 ^value 1 +) 10331 (R1 ^reward R974 +) 10332Retracting elaborate*copy-dir-to-output-link 10333 --> 10334 (I3 ^dir U +) 10335Retracting rl*prefer*rvt*predict-no*H0*4 10336 --> 10337 (S1 ^operator O1942 = 1.) 10338Retracting rl*prefer*rvt*predict-yes*H0*3 10339 --> 10340 (S1 ^operator O1941 = 0.) 10341=>WM: (13614: S1 ^operator O1944 +) 10342=>WM: (13613: S1 ^operator O1943 +) 10343=>WM: (13612: I3 ^dir L) 10344=>WM: (13611: O1944 ^name predict-no) 10345=>WM: (13610: O1943 ^name predict-yes) 10346=>WM: (13609: R975 ^value 1) 10347=>WM: (13608: R1 ^reward R975) 10348=>WM: (13607: I3 ^see 0) 10349<=WM: (13598: S1 ^operator O1941 +) 10350<=WM: (13599: S1 ^operator O1942 +) 10351<=WM: (13600: S1 ^operator O1942) 10352<=WM: (13597: I3 ^dir U) 10353<=WM: (13593: R1 ^reward R974) 10354<=WM: (13592: I3 ^see 1) 10355<=WM: (13596: O1942 ^name predict-no) 10356<=WM: (13595: O1941 ^name predict-yes) 10357<=WM: (13594: R974 ^value 1) 10358 10359--- Inner Elaboration Phase, active level 1 (S1) --- 10360Firing prefer*rvt*predict-yes*H0 10361 --> 10362Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 10363 --> 10364 (S1 ^operator O1943 = -0.3470159027404986) 10365Firing rl*prefer*rvt*predict-yes*H0*1 10366 --> 10367 (S1 ^operator O1943 = 0.3804143351598744) 10368Firing prefer*rvt*predict-yes*H0*1*v1*H1 10369 --> 10370Firing prefer*rvt*predict-no*H0 10371 --> 10372Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 10373 --> 10374 (S1 ^operator O1944 = 0.6861654297024582) 10375Firing rl*prefer*rvt*predict-no*H0*2 10376 --> 10377 (S1 ^operator O1944 = 0.3140405292214645) 10378Firing prefer*rvt*predict-no*H0*2*v1*H1 10379 --> 10380 inner elaboration loop at bottom goal. 10381Retracting rl*prefer*rvt*predict-no*H0*2 10382 --> 10383 (S1 ^operator O1942 = 0.3140405292214645) 10384Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 10385 --> 10386 (S1 ^operator O1942 = 0.6861654297024582) 10387Retracting rl*prefer*rvt*predict-yes*H0*1 10388 --> 10389 (S1 ^operator O1941 = 0.3804143351598744) 10390Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 10391 --> 10392 (S1 ^operator O1941 = -0.3470159027404986) 10393 10394--- END Proposal Phase --- 10395 10396--- Decision Phase --- 10397RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 10398=>WM: (13615: S1 ^operator O1944) 10399 10400 972: O: O1944 (predict-no) 10401--- END Decision Phase --- 10402 10403--- Application Phase --- 10404 --- Firing Productions (PE) For State At Depth 1 --- 10405 10406--- Inner Elaboration Phase, active level 1 (S1) --- 10407Firing apply*operator 10408 --> 10409 (I3 ^predict-no N972 + :O ) 10410Firing apply*operator*complete 10411 --> 10412 (I3 ^predict-no N971 - :O ) 10413 inner elaboration loop at bottom goal. 10414 --- Change Working Memory (PE) --- 10415=>WM: (13616: I3 ^predict-no N972) 10416<=WM: (13602: N971 ^status complete) 10417<=WM: (13601: I3 ^predict-no N971) 10418 --- Firing Productions (IE) For State At Depth 1 --- 10419 10420--- Inner Elaboration Phase, active level 1 (S1) --- 10421Firing monitor*world 10422 --> 10423 10424I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 10425 --- Change Working Memory (IE) --- 10426 10427--- END Application Phase --- 10428--- Output Phase --- 10429ENV: Agent did: predict-no for direction L in state State-A 10430In State-A moving L 10431ENV: (next state, see, prediction correct?) = (State-A, 0, True) 10432predict error 0 10433dir: dir isR 10434--- END Output Phase --- 10435\-/--- Input Phase --- 10436=>WM: (13620: I2 ^dir R) 10437=>WM: (13619: I2 ^reward 1) 10438=>WM: (13618: I2 ^see 0) 10439=>WM: (13617: N972 ^status complete) 10440<=WM: (13605: I2 ^dir L) 10441<=WM: (13604: I2 ^reward 1) 10442<=WM: (13603: I2 ^see 0) 10443=>WM: (13621: I2 ^level-1 L0-root) 10444<=WM: (13606: I2 ^level-1 L1-root) 10445 10446--- END Input Phase --- 10447 10448--- Proposal Phase --- 10449 10450--- Inner Elaboration Phase, active level 1 (S1) --- 10451Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 10452 --> 10453 (S1 ^operator O1943 = 0.7054436376897688) 10454Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 10455 --> 10456 (S1 ^operator O1944 = -0.2023211881870005) 10457Firing prefer*rvt*predict-no*H0*6*v1*H1 10458 --> 10459Firing prefer*rvt*predict-yes*H0*5*v1*H1 10460 --> 10461Firing elaborate*copy-see-to-output-link 10462 --> 10463 (I3 ^see 0 +) 10464Firing elaborate*reward*based*on*reward 10465 --> 10466 (R976 ^value 1 +) 10467 (R1 ^reward R976 +) 10468Firing propose*predict-yes 10469 --> 10470 (O1945 ^name predict-yes +) 10471 (S1 ^operator O1945 +) 10472Firing propose*predict-no 10473 --> 10474 (O1946 ^name predict-no +) 10475 (S1 ^operator O1946 +) 10476Firing rl*prefer*rvt*predict-no*H0*6 10477 --> 10478 (S1 ^operator O1944 = 0.2298717920574965) 10479Firing rl*prefer*rvt*predict-yes*H0*5 10480 --> 10481 (S1 ^operator O1943 = 0.2939507002996337) 10482Firing prefer*rvt*predict-yes*H0 10483 --> 10484Firing prefer*rvt*predict-no*H0 10485 --> 10486Firing elaborate*copy-dir-to-output-link 10487 --> 10488 (I3 ^dir R +) 10489 inner elaboration loop at bottom goal. 10490Retracting elaborate*copy-see-to-output-link 10491 --> 10492 (I3 ^see 0 +) 10493Retracting propose*predict-no 10494 --> 10495 (O1944 ^name predict-no +) 10496 (S1 ^operator O1944 +) 10497Retracting propose*predict-yes 10498 --> 10499 (O1943 ^name predict-yes +) 10500 (S1 ^operator O1943 +) 10501Retracting elaborate*reward*based*on*reward 10502 --> 10503 (R975 ^value 1 +) 10504 (R1 ^reward R975 +) 10505Retracting elaborate*copy-dir-to-output-link 10506 --> 10507 (I3 ^dir L +) 10508Retracting rl*prefer*rvt*predict-no*H0*2 10509 --> 10510 (S1 ^operator O1944 = 0.3140405292214645) 10511Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 10512 --> 10513 (S1 ^operator O1944 = 0.6861654297024582) 10514Retracting rl*prefer*rvt*predict-yes*H0*1 10515 --> 10516 (S1 ^operator O1943 = 0.3804143351598744) 10517Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 10518 --> 10519 (S1 ^operator O1943 = -0.3470159027404986) 10520=>WM: (13628: S1 ^operator O1946 +) 10521=>WM: (13627: S1 ^operator O1945 +) 10522=>WM: (13626: I3 ^dir R) 10523=>WM: (13625: O1946 ^name predict-no) 10524=>WM: (13624: O1945 ^name predict-yes) 10525=>WM: (13623: R976 ^value 1) 10526=>WM: (13622: R1 ^reward R976) 10527<=WM: (13613: S1 ^operator O1943 +) 10528<=WM: (13614: S1 ^operator O1944 +) 10529<=WM: (13615: S1 ^operator O1944) 10530<=WM: (13612: I3 ^dir L) 10531<=WM: (13608: R1 ^reward R975) 10532<=WM: (13611: O1944 ^name predict-no) 10533<=WM: (13610: O1943 ^name predict-yes) 10534<=WM: (13609: R975 ^value 1) 10535 10536--- Inner Elaboration Phase, active level 1 (S1) --- 10537Firing prefer*rvt*predict-yes*H0 10538 --> 10539Firing rl*prefer*rvt*predict-yes*H0*5 10540 --> 10541 (S1 ^operator O1945 = 0.2939507002996337) 10542Firing prefer*rvt*predict-yes*H0*5*v1*H1 10543 --> 10544Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 10545 --> 10546 (S1 ^operator O1945 = 0.7054436376897688) 10547Firing prefer*rvt*predict-no*H0 10548 --> 10549Firing rl*prefer*rvt*predict-no*H0*6 10550 --> 10551 (S1 ^operator O1946 = 0.2298717920574965) 10552Firing prefer*rvt*predict-no*H0*6*v1*H1 10553 --> 10554Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 10555 --> 10556 (S1 ^operator O1946 = -0.2023211881870005) 10557 inner elaboration loop at bottom goal. 10558Retracting rl*prefer*rvt*predict-no*H0*6 10559 --> 10560 (S1 ^operator O1944 = 0.2298717920574965) 10561Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 10562 --> 10563 (S1 ^operator O1944 = -0.2023211881870005) 10564Retracting rl*prefer*rvt*predict-yes*H0*5 10565 --> 10566 (S1 ^operator O1943 = 0.2939507002996337) 10567Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 10568 --> 10569 (S1 ^operator O1943 = 0.7054436376897688) 10570 10571--- END Proposal Phase --- 10572 10573--- Decision Phase --- 10574RL update rl*prefer*rvt*predict-no*H0*2 0.485046 -0.171006 0.314041 -> 0.485033 -0.171009 0.314023(R,m,v=1,0.86,0.121208) 10575RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*36 0.515116 0.171049 0.686165 -> 0.5151 0.171045 0.686145(R,m,v=1,1,0) 10576=>WM: (13629: S1 ^operator O1945) 10577 10578 973: O: O1945 (predict-yes) 10579--- END Decision Phase --- 10580 10581--- Application Phase --- 10582 --- Firing Productions (PE) For State At Depth 1 --- 10583 10584--- Inner Elaboration Phase, active level 1 (S1) --- 10585Firing apply*operator 10586 --> 10587 (I3 ^predict-yes N973 + :O ) 10588Firing apply*operator*complete 10589 --> 10590 (I3 ^predict-no N972 - :O ) 10591 inner elaboration loop at bottom goal. 10592 --- Change Working Memory (PE) --- 10593=>WM: (13630: I3 ^predict-yes N973) 10594<=WM: (13617: N972 ^status complete) 10595<=WM: (13616: I3 ^predict-no N972) 10596 --- Firing Productions (IE) For State At Depth 1 --- 10597 10598--- Inner Elaboration Phase, active level 1 (S1) --- 10599Firing monitor*world 10600 --> 10601 10602I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 10603 --- Change Working Memory (IE) --- 10604 10605--- END Application Phase --- 10606--- Output Phase --- 10607ENV: Agent did: predict-yes for direction R in state State-A 10608In State-A moving R 10609ENV: (next state, see, prediction correct?) = (State-B, 1, True) 10610predict error 0 10611dir: dir isU 10612--- END Output Phase --- 10613|\---- Input Phase --- 10614=>WM: (13634: I2 ^dir U) 10615=>WM: (13633: I2 ^reward 1) 10616=>WM: (13632: I2 ^see 1) 10617=>WM: (13631: N973 ^status complete) 10618<=WM: (13620: I2 ^dir R) 10619<=WM: (13619: I2 ^reward 1) 10620<=WM: (13618: I2 ^see 0) 10621=>WM: (13635: I2 ^level-1 R1-root) 10622<=WM: (13621: I2 ^level-1 L0-root) 10623 10624--- END Input Phase --- 10625 10626--- Proposal Phase --- 10627 10628--- Inner Elaboration Phase, active level 1 (S1) --- 10629Firing elaborate*copy-see-to-output-link 10630 --> 10631 (I3 ^see 1 +) 10632Firing elaborate*reward*based*on*reward 10633 --> 10634 (R977 ^value 1 +) 10635 (R1 ^reward R977 +) 10636Firing propose*predict-yes 10637 --> 10638 (O1947 ^name predict-yes +) 10639 (S1 ^operator O1947 +) 10640Firing propose*predict-no 10641 --> 10642 (O1948 ^name predict-no +) 10643 (S1 ^operator O1948 +) 10644Firing rl*prefer*rvt*predict-no*H0*4 10645 --> 10646 (S1 ^operator O1946 = 1.) 10647Firing rl*prefer*rvt*predict-yes*H0*3 10648 --> 10649 (S1 ^operator O1945 = 0.) 10650Firing prefer*rvt*predict-yes*H0 10651 --> 10652Firing prefer*rvt*predict-no*H0 10653 --> 10654Firing elaborate*copy-dir-to-output-link 10655 --> 10656 (I3 ^dir U +) 10657 inner elaboration loop at bottom goal. 10658Retracting elaborate*copy-see-to-output-link 10659 --> 10660 (I3 ^see 0 +) 10661Retracting propose*predict-no 10662 --> 10663 (O1946 ^name predict-no +) 10664 (S1 ^operator O1946 +) 10665Retracting propose*predict-yes 10666 --> 10667 (O1945 ^name predict-yes +) 10668 (S1 ^operator O1945 +) 10669Retracting elaborate*reward*based*on*reward 10670 --> 10671 (R976 ^value 1 +) 10672 (R1 ^reward R976 +) 10673Retracting elaborate*copy-dir-to-output-link 10674 --> 10675 (I3 ^dir R +) 10676Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 10677 --> 10678 (S1 ^operator O1946 = -0.2023211881870005) 10679Retracting rl*prefer*rvt*predict-no*H0*6 10680 --> 10681 (S1 ^operator O1946 = 0.2298717920574965) 10682Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 10683 --> 10684 (S1 ^operator O1945 = 0.7054436376897688) 10685Retracting rl*prefer*rvt*predict-yes*H0*5 10686 --> 10687 (S1 ^operator O1945 = 0.2939507002996337) 10688=>WM: (13643: S1 ^operator O1948 +) 10689=>WM: (13642: S1 ^operator O1947 +) 10690=>WM: (13641: I3 ^dir U) 10691=>WM: (13640: O1948 ^name predict-no) 10692=>WM: (13639: O1947 ^name predict-yes) 10693=>WM: (13638: R977 ^value 1) 10694=>WM: (13637: R1 ^reward R977) 10695=>WM: (13636: I3 ^see 1) 10696<=WM: (13627: S1 ^operator O1945 +) 10697<=WM: (13629: S1 ^operator O1945) 10698<=WM: (13628: S1 ^operator O1946 +) 10699<=WM: (13626: I3 ^dir R) 10700<=WM: (13622: R1 ^reward R976) 10701<=WM: (13607: I3 ^see 0) 10702<=WM: (13625: O1946 ^name predict-no) 10703<=WM: (13624: O1945 ^name predict-yes) 10704<=WM: (13623: R976 ^value 1) 10705 10706--- Inner Elaboration Phase, active level 1 (S1) --- 10707Firing prefer*rvt*predict-yes*H0 10708 --> 10709Firing rl*prefer*rvt*predict-yes*H0*3 10710 --> 10711 (S1 ^operator O1947 = 0.) 10712Firing prefer*rvt*predict-no*H0 10713 --> 10714Firing rl*prefer*rvt*predict-no*H0*4 10715 --> 10716 (S1 ^operator O1948 = 1.) 10717 inner elaboration loop at bottom goal. 10718Retracting rl*prefer*rvt*predict-no*H0*4 10719 --> 10720 (S1 ^operator O1946 = 1.) 10721Retracting rl*prefer*rvt*predict-yes*H0*3 10722 --> 10723 (S1 ^operator O1945 = 0.) 10724 10725--- END Proposal Phase --- 10726 10727--- Decision Phase --- 10728RL update rl*prefer*rvt*predict-yes*H0*5 0.501028 -0.207078 0.293951 -> 0.501074 -0.207073 0.294001(R,m,v=1,0.84,0.135302) 10729RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.498423 0.207021 0.705444 -> 0.498477 0.207026 0.705503(R,m,v=1,1,0) 10730=>WM: (13644: S1 ^operator O1948) 10731 10732 974: O: O1948 (predict-no) 10733--- END Decision Phase --- 10734 10735--- Application Phase --- 10736 --- Firing Productions (PE) For State At Depth 1 --- 10737 10738--- Inner Elaboration Phase, active level 1 (S1) --- 10739Firing apply*operator 10740 --> 10741 (I3 ^predict-no N974 + :O ) 10742Firing apply*operator*complete 10743 --> 10744 (I3 ^predict-yes N973 - :O ) 10745 inner elaboration loop at bottom goal. 10746 --- Change Working Memory (PE) --- 10747=>WM: (13645: I3 ^predict-no N974) 10748<=WM: (13631: N973 ^status complete) 10749<=WM: (13630: I3 ^predict-yes N973) 10750 --- Firing Productions (IE) For State At Depth 1 --- 10751 10752--- Inner Elaboration Phase, active level 1 (S1) --- 10753Firing monitor*world 10754 --> 10755 10756I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 10757 --- Change Working Memory (IE) --- 10758 10759--- END Application Phase --- 10760--- Output Phase --- 10761ENV: Agent did: predict-no for direction U in state State-B 10762In State-B moving U 10763ENV: (next state, see, prediction correct?) = (State-B, 0, True) 10764predict error 0 10765dir: dir isL 10766--- END Output Phase --- 10767/|\--- Input Phase --- 10768=>WM: (13649: I2 ^dir L) 10769=>WM: (13648: I2 ^reward 1) 10770=>WM: (13647: I2 ^see 0) 10771=>WM: (13646: N974 ^status complete) 10772<=WM: (13634: I2 ^dir U) 10773<=WM: (13633: I2 ^reward 1) 10774<=WM: (13632: I2 ^see 1) 10775=>WM: (13650: I2 ^level-1 R1-root) 10776<=WM: (13635: I2 ^level-1 R1-root) 10777 10778--- END Input Phase --- 10779 10780--- Proposal Phase --- 10781 10782--- Inner Elaboration Phase, active level 1 (S1) --- 10783Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10784 --> 10785 (S1 ^operator O1947 = 0.6196158942331635) 10786Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10787 --> 10788 (S1 ^operator O1948 = -0.1479504104026684) 10789Firing prefer*rvt*predict-no*H0*2*v1*H1 10790 --> 10791Firing prefer*rvt*predict-yes*H0*1*v1*H1 10792 --> 10793Firing elaborate*copy-see-to-output-link 10794 --> 10795 (I3 ^see 0 +) 10796Firing elaborate*reward*based*on*reward 10797 --> 10798 (R978 ^value 1 +) 10799 (R1 ^reward R978 +) 10800Firing propose*predict-yes 10801 --> 10802 (O1949 ^name predict-yes +) 10803 (S1 ^operator O1949 +) 10804Firing propose*predict-no 10805 --> 10806 (O1950 ^name predict-no +) 10807 (S1 ^operator O1950 +) 10808Firing rl*prefer*rvt*predict-no*H0*2 10809 --> 10810 (S1 ^operator O1948 = 0.3140233963466647) 10811Firing rl*prefer*rvt*predict-yes*H0*1 10812 --> 10813 (S1 ^operator O1947 = 0.3804143351598744) 10814Firing prefer*rvt*predict-yes*H0 10815 --> 10816Firing prefer*rvt*predict-no*H0 10817 --> 10818Firing elaborate*copy-dir-to-output-link 10819 --> 10820 (I3 ^dir L +) 10821 inner elaboration loop at bottom goal. 10822Retracting elaborate*copy-see-to-output-link 10823 --> 10824 (I3 ^see 1 +) 10825Retracting propose*predict-no 10826 --> 10827 (O1948 ^name predict-no +) 10828 (S1 ^operator O1948 +) 10829Retracting propose*predict-yes 10830 --> 10831 (O1947 ^name predict-yes +) 10832 (S1 ^operator O1947 +) 10833Retracting elaborate*reward*based*on*reward 10834 --> 10835 (R977 ^value 1 +) 10836 (R1 ^reward R977 +) 10837Retracting elaborate*copy-dir-to-output-link 10838 --> 10839 (I3 ^dir U +) 10840Retracting rl*prefer*rvt*predict-no*H0*4 10841 --> 10842 (S1 ^operator O1948 = 1.) 10843Retracting rl*prefer*rvt*predict-yes*H0*3 10844 --> 10845 (S1 ^operator O1947 = 0.) 10846=>WM: (13658: S1 ^operator O1950 +) 10847=>WM: (13657: S1 ^operator O1949 +) 10848=>WM: (13656: I3 ^dir L) 10849=>WM: (13655: O1950 ^name predict-no) 10850=>WM: (13654: O1949 ^name predict-yes) 10851=>WM: (13653: R978 ^value 1) 10852=>WM: (13652: R1 ^reward R978) 10853=>WM: (13651: I3 ^see 0) 10854<=WM: (13642: S1 ^operator O1947 +) 10855<=WM: (13643: S1 ^operator O1948 +) 10856<=WM: (13644: S1 ^operator O1948) 10857<=WM: (13641: I3 ^dir U) 10858<=WM: (13637: R1 ^reward R977) 10859<=WM: (13636: I3 ^see 1) 10860<=WM: (13640: O1948 ^name predict-no) 10861<=WM: (13639: O1947 ^name predict-yes) 10862<=WM: (13638: R977 ^value 1) 10863 10864--- Inner Elaboration Phase, active level 1 (S1) --- 10865Firing prefer*rvt*predict-yes*H0 10866 --> 10867Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10868 --> 10869 (S1 ^operator O1949 = 0.6196158942331635) 10870Firing rl*prefer*rvt*predict-yes*H0*1 10871 --> 10872 (S1 ^operator O1949 = 0.3804143351598744) 10873Firing prefer*rvt*predict-yes*H0*1*v1*H1 10874 --> 10875Firing prefer*rvt*predict-no*H0 10876 --> 10877Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10878 --> 10879 (S1 ^operator O1950 = -0.1479504104026684) 10880Firing rl*prefer*rvt*predict-no*H0*2 10881 --> 10882 (S1 ^operator O1950 = 0.3140233963466647) 10883Firing prefer*rvt*predict-no*H0*2*v1*H1 10884 --> 10885 inner elaboration loop at bottom goal. 10886Retracting rl*prefer*rvt*predict-no*H0*2 10887 --> 10888 (S1 ^operator O1948 = 0.3140233963466647) 10889Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 10890 --> 10891 (S1 ^operator O1948 = -0.1479504104026684) 10892Retracting rl*prefer*rvt*predict-yes*H0*1 10893 --> 10894 (S1 ^operator O1947 = 0.3804143351598744) 10895Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 10896 --> 10897 (S1 ^operator O1947 = 0.6196158942331635) 10898 10899--- END Proposal Phase --- 10900 10901--- Decision Phase --- 10902RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 10903=>WM: (13659: S1 ^operator O1949) 10904 10905 975: O: O1949 (predict-yes) 10906--- END Decision Phase --- 10907 10908--- Application Phase --- 10909 --- Firing Productions (PE) For State At Depth 1 --- 10910 10911--- Inner Elaboration Phase, active level 1 (S1) --- 10912Firing apply*operator 10913 --> 10914 (I3 ^predict-yes N975 + :O ) 10915Firing apply*operator*complete 10916 --> 10917 (I3 ^predict-no N974 - :O ) 10918 inner elaboration loop at bottom goal. 10919 --- Change Working Memory (PE) --- 10920=>WM: (13660: I3 ^predict-yes N975) 10921<=WM: (13646: N974 ^status complete) 10922<=WM: (13645: I3 ^predict-no N974) 10923 --- Firing Productions (IE) For State At Depth 1 --- 10924 10925--- Inner Elaboration Phase, active level 1 (S1) --- 10926Firing monitor*world 10927 --> 10928 10929I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 10930 --- Change Working Memory (IE) --- 10931 10932--- END Application Phase --- 10933--- Output Phase --- 10934ENV: Agent did: predict-yes for direction L in state State-B 10935In State-B moving L 10936ENV: (next state, see, prediction correct?) = (State-A, 1, True) 10937predict error 0 10938dir: dir isR 10939--- END Output Phase --- 10940-/|--- Input Phase --- 10941=>WM: (13664: I2 ^dir R) 10942=>WM: (13663: I2 ^reward 1) 10943=>WM: (13662: I2 ^see 1) 10944=>WM: (13661: N975 ^status complete) 10945<=WM: (13649: I2 ^dir L) 10946<=WM: (13648: I2 ^reward 1) 10947<=WM: (13647: I2 ^see 0) 10948=>WM: (13665: I2 ^level-1 L1-root) 10949<=WM: (13650: I2 ^level-1 R1-root) 10950 10951--- END Input Phase --- 10952 10953--- Proposal Phase --- 10954 10955--- Inner Elaboration Phase, active level 1 (S1) --- 10956Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 10957 --> 10958 (S1 ^operator O1949 = 0.7064496972060428) 10959Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 10960 --> 10961 (S1 ^operator O1950 = -0.1937987592593187) 10962Firing prefer*rvt*predict-no*H0*6*v1*H1 10963 --> 10964Firing prefer*rvt*predict-yes*H0*5*v1*H1 10965 --> 10966Firing elaborate*copy-see-to-output-link 10967 --> 10968 (I3 ^see 1 +) 10969Firing elaborate*reward*based*on*reward 10970 --> 10971 (R979 ^value 1 +) 10972 (R1 ^reward R979 +) 10973Firing propose*predict-yes 10974 --> 10975 (O1951 ^name predict-yes +) 10976 (S1 ^operator O1951 +) 10977Firing propose*predict-no 10978 --> 10979 (O1952 ^name predict-no +) 10980 (S1 ^operator O1952 +) 10981Firing rl*prefer*rvt*predict-no*H0*6 10982 --> 10983 (S1 ^operator O1950 = 0.2298717920574965) 10984Firing rl*prefer*rvt*predict-yes*H0*5 10985 --> 10986 (S1 ^operator O1949 = 0.2940010828283485) 10987Firing prefer*rvt*predict-yes*H0 10988 --> 10989Firing prefer*rvt*predict-no*H0 10990 --> 10991Firing elaborate*copy-dir-to-output-link 10992 --> 10993 (I3 ^dir R +) 10994 inner elaboration loop at bottom goal. 10995Retracting elaborate*copy-see-to-output-link 10996 --> 10997 (I3 ^see 0 +) 10998Retracting propose*predict-no 10999 --> 11000 (O1950 ^name predict-no +) 11001 (S1 ^operator O1950 +) 11002Retracting propose*predict-yes 11003 --> 11004 (O1949 ^name predict-yes +) 11005 (S1 ^operator O1949 +) 11006Retracting elaborate*reward*based*on*reward 11007 --> 11008 (R978 ^value 1 +) 11009 (R1 ^reward R978 +) 11010Retracting elaborate*copy-dir-to-output-link 11011 --> 11012 (I3 ^dir L +) 11013Retracting rl*prefer*rvt*predict-no*H0*2 11014 --> 11015 (S1 ^operator O1950 = 0.3140233963466647) 11016Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 11017 --> 11018 (S1 ^operator O1950 = -0.1479504104026684) 11019Retracting rl*prefer*rvt*predict-yes*H0*1 11020 --> 11021 (S1 ^operator O1949 = 0.3804143351598744) 11022Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 11023 --> 11024 (S1 ^operator O1949 = 0.6196158942331635) 11025=>WM: (13673: S1 ^operator O1952 +) 11026=>WM: (13672: S1 ^operator O1951 +) 11027=>WM: (13671: I3 ^dir R) 11028=>WM: (13670: O1952 ^name predict-no) 11029=>WM: (13669: O1951 ^name predict-yes) 11030=>WM: (13668: R979 ^value 1) 11031=>WM: (13667: R1 ^reward R979) 11032=>WM: (13666: I3 ^see 1) 11033<=WM: (13657: S1 ^operator O1949 +) 11034<=WM: (13659: S1 ^operator O1949) 11035<=WM: (13658: S1 ^operator O1950 +) 11036<=WM: (13656: I3 ^dir L) 11037<=WM: (13652: R1 ^reward R978) 11038<=WM: (13651: I3 ^see 0) 11039<=WM: (13655: O1950 ^name predict-no) 11040<=WM: (13654: O1949 ^name predict-yes) 11041<=WM: (13653: R978 ^value 1) 11042 11043--- Inner Elaboration Phase, active level 1 (S1) --- 11044Firing prefer*rvt*predict-yes*H0 11045 --> 11046Firing rl*prefer*rvt*predict-yes*H0*5 11047 --> 11048 (S1 ^operator O1951 = 0.2940010828283485) 11049Firing prefer*rvt*predict-yes*H0*5*v1*H1 11050 --> 11051Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11052 --> 11053 (S1 ^operator O1951 = 0.7064496972060428) 11054Firing prefer*rvt*predict-no*H0 11055 --> 11056Firing rl*prefer*rvt*predict-no*H0*6 11057 --> 11058 (S1 ^operator O1952 = 0.2298717920574965) 11059Firing prefer*rvt*predict-no*H0*6*v1*H1 11060 --> 11061Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11062 --> 11063 (S1 ^operator O1952 = -0.1937987592593187) 11064 inner elaboration loop at bottom goal. 11065Retracting rl*prefer*rvt*predict-no*H0*6 11066 --> 11067 (S1 ^operator O1950 = 0.2298717920574965) 11068Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11069 --> 11070 (S1 ^operator O1950 = -0.1937987592593187) 11071Retracting rl*prefer*rvt*predict-yes*H0*5 11072 --> 11073 (S1 ^operator O1949 = 0.2940010828283485) 11074Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11075 --> 11076 (S1 ^operator O1949 = 0.7064496972060428) 11077 11078--- END Proposal Phase --- 11079 11080--- Decision Phase --- 11081RL update rl*prefer*rvt*predict-yes*H0*1 0.521344 -0.14093 0.380414 -> 0.521342 -0.14093 0.380412(R,m,v=1,0.825,0.145283) 11082RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478689 0.140927 0.619616 -> 0.478686 0.140927 0.619613(R,m,v=1,1,0) 11083=>WM: (13674: S1 ^operator O1951) 11084 11085 976: O: O1951 (predict-yes) 11086--- END Decision Phase --- 11087 11088--- Application Phase --- 11089 --- Firing Productions (PE) For State At Depth 1 --- 11090 11091--- Inner Elaboration Phase, active level 1 (S1) --- 11092Firing apply*operator 11093 --> 11094 (I3 ^predict-yes N976 + :O ) 11095Firing apply*operator*complete 11096 --> 11097 (I3 ^predict-yes N975 - :O ) 11098 inner elaboration loop at bottom goal. 11099 --- Change Working Memory (PE) --- 11100=>WM: (13675: I3 ^predict-yes N976) 11101<=WM: (13661: N975 ^status complete) 11102<=WM: (13660: I3 ^predict-yes N975) 11103 --- Firing Productions (IE) For State At Depth 1 --- 11104 11105--- Inner Elaboration Phase, active level 1 (S1) --- 11106Firing monitor*world 11107 --> 11108 11109I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 11110 --- Change Working Memory (IE) --- 11111 11112--- END Application Phase --- 11113--- Output Phase --- 11114ENV: Agent did: predict-yes for direction R in state State-A 11115In State-A moving R 11116ENV: (next state, see, prediction correct?) = (State-B, 1, True) 11117predict error 0 11118dir: dir isR 11119--- END Output Phase --- 11120\-/--- Input Phase --- 11121=>WM: (13679: I2 ^dir R) 11122=>WM: (13678: I2 ^reward 1) 11123=>WM: (13677: I2 ^see 1) 11124=>WM: (13676: N976 ^status complete) 11125<=WM: (13664: I2 ^dir R) 11126<=WM: (13663: I2 ^reward 1) 11127<=WM: (13662: I2 ^see 1) 11128=>WM: (13680: I2 ^level-1 R1-root) 11129<=WM: (13665: I2 ^level-1 L1-root) 11130 11131--- END Input Phase --- 11132 11133--- Proposal Phase --- 11134 11135--- Inner Elaboration Phase, active level 1 (S1) --- 11136Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 11137 --> 11138 (S1 ^operator O1951 = -0.252585164213872) 11139Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 11140 --> 11141 (S1 ^operator O1952 = 0.7701964997777864) 11142Firing prefer*rvt*predict-no*H0*6*v1*H1 11143 --> 11144Firing prefer*rvt*predict-yes*H0*5*v1*H1 11145 --> 11146Firing elaborate*copy-see-to-output-link 11147 --> 11148 (I3 ^see 1 +) 11149Firing elaborate*reward*based*on*reward 11150 --> 11151 (R980 ^value 1 +) 11152 (R1 ^reward R980 +) 11153Firing propose*predict-yes 11154 --> 11155 (O1953 ^name predict-yes +) 11156 (S1 ^operator O1953 +) 11157Firing propose*predict-no 11158 --> 11159 (O1954 ^name predict-no +) 11160 (S1 ^operator O1954 +) 11161Firing rl*prefer*rvt*predict-no*H0*6 11162 --> 11163 (S1 ^operator O1952 = 0.2298717920574965) 11164Firing rl*prefer*rvt*predict-yes*H0*5 11165 --> 11166 (S1 ^operator O1951 = 0.2940010828283485) 11167Firing prefer*rvt*predict-yes*H0 11168 --> 11169Firing prefer*rvt*predict-no*H0 11170 --> 11171Firing elaborate*copy-dir-to-output-link 11172 --> 11173 (I3 ^dir R +) 11174 inner elaboration loop at bottom goal. 11175Retracting elaborate*copy-see-to-output-link 11176 --> 11177 (I3 ^see 1 +) 11178Retracting propose*predict-no 11179 --> 11180 (O1952 ^name predict-no +) 11181 (S1 ^operator O1952 +) 11182Retracting propose*predict-yes 11183 --> 11184 (O1951 ^name predict-yes +) 11185 (S1 ^operator O1951 +) 11186Retracting elaborate*reward*based*on*reward 11187 --> 11188 (R979 ^value 1 +) 11189 (R1 ^reward R979 +) 11190Retracting elaborate*copy-dir-to-output-link 11191 --> 11192 (I3 ^dir R +) 11193Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11194 --> 11195 (S1 ^operator O1952 = -0.1937987592593187) 11196Retracting rl*prefer*rvt*predict-no*H0*6 11197 --> 11198 (S1 ^operator O1952 = 0.2298717920574965) 11199Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11200 --> 11201 (S1 ^operator O1951 = 0.7064496972060428) 11202Retracting rl*prefer*rvt*predict-yes*H0*5 11203 --> 11204 (S1 ^operator O1951 = 0.2940010828283485) 11205=>WM: (13686: S1 ^operator O1954 +) 11206=>WM: (13685: S1 ^operator O1953 +) 11207=>WM: (13684: O1954 ^name predict-no) 11208=>WM: (13683: O1953 ^name predict-yes) 11209=>WM: (13682: R980 ^value 1) 11210=>WM: (13681: R1 ^reward R980) 11211<=WM: (13672: S1 ^operator O1951 +) 11212<=WM: (13674: S1 ^operator O1951) 11213<=WM: (13673: S1 ^operator O1952 +) 11214<=WM: (13667: R1 ^reward R979) 11215<=WM: (13670: O1952 ^name predict-no) 11216<=WM: (13669: O1951 ^name predict-yes) 11217<=WM: (13668: R979 ^value 1) 11218 11219--- Inner Elaboration Phase, active level 1 (S1) --- 11220Firing prefer*rvt*predict-yes*H0 11221 --> 11222Firing rl*prefer*rvt*predict-yes*H0*5 11223 --> 11224 (S1 ^operator O1953 = 0.2940010828283485) 11225Firing prefer*rvt*predict-yes*H0*5*v1*H1 11226 --> 11227Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 11228 --> 11229 (S1 ^operator O1953 = -0.252585164213872) 11230Firing prefer*rvt*predict-no*H0 11231 --> 11232Firing rl*prefer*rvt*predict-no*H0*6 11233 --> 11234 (S1 ^operator O1954 = 0.2298717920574965) 11235Firing prefer*rvt*predict-no*H0*6*v1*H1 11236 --> 11237Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 11238 --> 11239 (S1 ^operator O1954 = 0.7701964997777864) 11240 inner elaboration loop at bottom goal. 11241Retracting rl*prefer*rvt*predict-no*H0*6 11242 --> 11243 (S1 ^operator O1952 = 0.2298717920574965) 11244Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 11245 --> 11246 (S1 ^operator O1952 = 0.7701964997777864) 11247Retracting rl*prefer*rvt*predict-yes*H0*5 11248 --> 11249 (S1 ^operator O1951 = 0.2940010828283485) 11250Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 11251 --> 11252 (S1 ^operator O1951 = -0.252585164213872) 11253 11254--- END Proposal Phase --- 11255 11256--- Decision Phase --- 11257RL update rl*prefer*rvt*predict-yes*H0*5 0.501074 -0.207073 0.294001 -> 0.50104 -0.207077 0.293964(R,m,v=1,0.84106,0.13457) 11258RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499331 0.207118 0.70645 -> 0.499292 0.207114 0.706406(R,m,v=1,1,0) 11259=>WM: (13687: S1 ^operator O1954) 11260 11261 977: O: O1954 (predict-no) 11262--- END Decision Phase --- 11263 11264--- Application Phase --- 11265 --- Firing Productions (PE) For State At Depth 1 --- 11266 11267--- Inner Elaboration Phase, active level 1 (S1) --- 11268Firing apply*operator 11269 --> 11270 (I3 ^predict-no N977 + :O ) 11271Firing apply*operator*complete 11272 --> 11273 (I3 ^predict-yes N976 - :O ) 11274 inner elaboration loop at bottom goal. 11275 --- Change Working Memory (PE) --- 11276=>WM: (13688: I3 ^predict-no N977) 11277<=WM: (13676: N976 ^status complete) 11278<=WM: (13675: I3 ^predict-yes N976) 11279 --- Firing Productions (IE) For State At Depth 1 --- 11280 11281--- Inner Elaboration Phase, active level 1 (S1) --- 11282Firing monitor*world 11283 --> 11284 11285I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 11286 --- Change Working Memory (IE) --- 11287 11288--- END Application Phase --- 11289--- Output Phase --- 11290ENV: Agent did: predict-no for direction R in state State-B 11291In State-B moving R 11292ENV: (next state, see, prediction correct?) = (State-B, 0, True) 11293predict error 0 11294dir: dir isU 11295--- END Output Phase --- 11296|\--- Input Phase --- 11297=>WM: (13692: I2 ^dir U) 11298=>WM: (13691: I2 ^reward 1) 11299=>WM: (13690: I2 ^see 0) 11300=>WM: (13689: N977 ^status complete) 11301<=WM: (13679: I2 ^dir R) 11302<=WM: (13678: I2 ^reward 1) 11303<=WM: (13677: I2 ^see 1) 11304=>WM: (13693: I2 ^level-1 R0-root) 11305<=WM: (13680: I2 ^level-1 R1-root) 11306 11307--- END Input Phase --- 11308 11309--- Proposal Phase --- 11310 11311--- Inner Elaboration Phase, active level 1 (S1) --- 11312Firing elaborate*copy-see-to-output-link 11313 --> 11314 (I3 ^see 0 +) 11315Firing elaborate*reward*based*on*reward 11316 --> 11317 (R981 ^value 1 +) 11318 (R1 ^reward R981 +) 11319Firing propose*predict-yes 11320 --> 11321 (O1955 ^name predict-yes +) 11322 (S1 ^operator O1955 +) 11323Firing propose*predict-no 11324 --> 11325 (O1956 ^name predict-no +) 11326 (S1 ^operator O1956 +) 11327Firing rl*prefer*rvt*predict-no*H0*4 11328 --> 11329 (S1 ^operator O1954 = 1.) 11330Firing rl*prefer*rvt*predict-yes*H0*3 11331 --> 11332 (S1 ^operator O1953 = 0.) 11333Firing prefer*rvt*predict-yes*H0 11334 --> 11335Firing prefer*rvt*predict-no*H0 11336 --> 11337Firing elaborate*copy-dir-to-output-link 11338 --> 11339 (I3 ^dir U +) 11340 inner elaboration loop at bottom goal. 11341Retracting elaborate*copy-see-to-output-link 11342 --> 11343 (I3 ^see 1 +) 11344Retracting propose*predict-no 11345 --> 11346 (O1954 ^name predict-no +) 11347 (S1 ^operator O1954 +) 11348Retracting propose*predict-yes 11349 --> 11350 (O1953 ^name predict-yes +) 11351 (S1 ^operator O1953 +) 11352Retracting elaborate*reward*based*on*reward 11353 --> 11354 (R980 ^value 1 +) 11355 (R1 ^reward R980 +) 11356Retracting elaborate*copy-dir-to-output-link 11357 --> 11358 (I3 ^dir R +) 11359Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 11360 --> 11361 (S1 ^operator O1954 = 0.7701964997777864) 11362Retracting rl*prefer*rvt*predict-no*H0*6 11363 --> 11364 (S1 ^operator O1954 = 0.2298717920574965) 11365Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 11366 --> 11367 (S1 ^operator O1953 = -0.252585164213872) 11368Retracting rl*prefer*rvt*predict-yes*H0*5 11369 --> 11370 (S1 ^operator O1953 = 0.2939636257009906) 11371=>WM: (13701: S1 ^operator O1956 +) 11372=>WM: (13700: S1 ^operator O1955 +) 11373=>WM: (13699: I3 ^dir U) 11374=>WM: (13698: O1956 ^name predict-no) 11375=>WM: (13697: O1955 ^name predict-yes) 11376=>WM: (13696: R981 ^value 1) 11377=>WM: (13695: R1 ^reward R981) 11378=>WM: (13694: I3 ^see 0) 11379<=WM: (13685: S1 ^operator O1953 +) 11380<=WM: (13686: S1 ^operator O1954 +) 11381<=WM: (13687: S1 ^operator O1954) 11382<=WM: (13671: I3 ^dir R) 11383<=WM: (13681: R1 ^reward R980) 11384<=WM: (13666: I3 ^see 1) 11385<=WM: (13684: O1954 ^name predict-no) 11386<=WM: (13683: O1953 ^name predict-yes) 11387<=WM: (13682: R980 ^value 1) 11388 11389--- Inner Elaboration Phase, active level 1 (S1) --- 11390Firing prefer*rvt*predict-yes*H0 11391 --> 11392Firing rl*prefer*rvt*predict-yes*H0*3 11393 --> 11394 (S1 ^operator O1955 = 0.) 11395Firing prefer*rvt*predict-no*H0 11396 --> 11397Firing rl*prefer*rvt*predict-no*H0*4 11398 --> 11399 (S1 ^operator O1956 = 1.) 11400 inner elaboration loop at bottom goal. 11401Retracting rl*prefer*rvt*predict-no*H0*4 11402 --> 11403 (S1 ^operator O1954 = 1.) 11404Retracting rl*prefer*rvt*predict-yes*H0*3 11405 --> 11406 (S1 ^operator O1953 = 0.) 11407 11408--- END Proposal Phase --- 11409 11410--- Decision Phase --- 11411RL update rl*prefer*rvt*predict-no*H0*6 0.611922 -0.38205 0.229872 -> 0.611917 -0.382051 0.229866(R,m,v=1,0.843023,0.133109) 11412RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.388134 0.382063 0.770196 -> 0.388128 0.382061 0.77019(R,m,v=1,1,0) 11413=>WM: (13702: S1 ^operator O1956) 11414 11415 978: O: O1956 (predict-no) 11416--- END Decision Phase --- 11417 11418--- Application Phase --- 11419 --- Firing Productions (PE) For State At Depth 1 --- 11420 11421--- Inner Elaboration Phase, active level 1 (S1) --- 11422Firing apply*operator 11423 --> 11424 (I3 ^predict-no N978 + :O ) 11425Firing apply*operator*complete 11426 --> 11427 (I3 ^predict-no N977 - :O ) 11428 inner elaboration loop at bottom goal. 11429 --- Change Working Memory (PE) --- 11430=>WM: (13703: I3 ^predict-no N978) 11431<=WM: (13689: N977 ^status complete) 11432<=WM: (13688: I3 ^predict-no N977) 11433 --- Firing Productions (IE) For State At Depth 1 --- 11434 11435--- Inner Elaboration Phase, active level 1 (S1) --- 11436Firing monitor*world 11437 --> 11438 11439I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 11440 --- Change Working Memory (IE) --- 11441 11442--- END Application Phase --- 11443--- Output Phase --- 11444ENV: Agent did: predict-no for direction U in state State-B 11445In State-B moving U 11446ENV: (next state, see, prediction correct?) = (State-B, 0, True) 11447predict error 0 11448dir: dir isU 11449--- END Output Phase --- 11450-/|--- Input Phase --- 11451=>WM: (13707: I2 ^dir U) 11452=>WM: (13706: I2 ^reward 1) 11453=>WM: (13705: I2 ^see 0) 11454=>WM: (13704: N978 ^status complete) 11455<=WM: (13692: I2 ^dir U) 11456<=WM: (13691: I2 ^reward 1) 11457<=WM: (13690: I2 ^see 0) 11458=>WM: (13708: I2 ^level-1 R0-root) 11459<=WM: (13693: I2 ^level-1 R0-root) 11460 11461--- END Input Phase --- 11462 11463--- Proposal Phase --- 11464 11465--- Inner Elaboration Phase, active level 1 (S1) --- 11466Firing elaborate*copy-see-to-output-link 11467 --> 11468 (I3 ^see 0 +) 11469Firing elaborate*reward*based*on*reward 11470 --> 11471 (R982 ^value 1 +) 11472 (R1 ^reward R982 +) 11473Firing propose*predict-yes 11474 --> 11475 (O1957 ^name predict-yes +) 11476 (S1 ^operator O1957 +) 11477Firing propose*predict-no 11478 --> 11479 (O1958 ^name predict-no +) 11480 (S1 ^operator O1958 +) 11481Firing rl*prefer*rvt*predict-no*H0*4 11482 --> 11483 (S1 ^operator O1956 = 1.) 11484Firing rl*prefer*rvt*predict-yes*H0*3 11485 --> 11486 (S1 ^operator O1955 = 0.) 11487Firing prefer*rvt*predict-yes*H0 11488 --> 11489Firing prefer*rvt*predict-no*H0 11490 --> 11491Firing elaborate*copy-dir-to-output-link 11492 --> 11493 (I3 ^dir U +) 11494 inner elaboration loop at bottom goal. 11495Retracting elaborate*copy-see-to-output-link 11496 --> 11497 (I3 ^see 0 +) 11498Retracting propose*predict-no 11499 --> 11500 (O1956 ^name predict-no +) 11501 (S1 ^operator O1956 +) 11502Retracting propose*predict-yes 11503 --> 11504 (O1955 ^name predict-yes +) 11505 (S1 ^operator O1955 +) 11506Retracting elaborate*reward*based*on*reward 11507 --> 11508 (R981 ^value 1 +) 11509 (R1 ^reward R981 +) 11510Retracting elaborate*copy-dir-to-output-link 11511 --> 11512 (I3 ^dir U +) 11513Retracting rl*prefer*rvt*predict-no*H0*4 11514 --> 11515 (S1 ^operator O1956 = 1.) 11516Retracting rl*prefer*rvt*predict-yes*H0*3 11517 --> 11518 (S1 ^operator O1955 = 0.) 11519=>WM: (13714: S1 ^operator O1958 +) 11520=>WM: (13713: S1 ^operator O1957 +) 11521=>WM: (13712: O1958 ^name predict-no) 11522=>WM: (13711: O1957 ^name predict-yes) 11523=>WM: (13710: R982 ^value 1) 11524=>WM: (13709: R1 ^reward R982) 11525<=WM: (13700: S1 ^operator O1955 +) 11526<=WM: (13701: S1 ^operator O1956 +) 11527<=WM: (13702: S1 ^operator O1956) 11528<=WM: (13695: R1 ^reward R981) 11529<=WM: (13698: O1956 ^name predict-no) 11530<=WM: (13697: O1955 ^name predict-yes) 11531<=WM: (13696: R981 ^value 1) 11532 11533--- Inner Elaboration Phase, active level 1 (S1) --- 11534Firing prefer*rvt*predict-yes*H0 11535 --> 11536Firing rl*prefer*rvt*predict-yes*H0*3 11537 --> 11538 (S1 ^operator O1957 = 0.) 11539Firing prefer*rvt*predict-no*H0 11540 --> 11541Firing rl*prefer*rvt*predict-no*H0*4 11542 --> 11543 (S1 ^operator O1958 = 1.) 11544 inner elaboration loop at bottom goal. 11545Retracting rl*prefer*rvt*predict-no*H0*4 11546 --> 11547 (S1 ^operator O1956 = 1.) 11548Retracting rl*prefer*rvt*predict-yes*H0*3 11549 --> 11550 (S1 ^operator O1955 = 0.) 11551 11552--- END Proposal Phase --- 11553 11554--- Decision Phase --- 11555RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 11556=>WM: (13715: S1 ^operator O1958) 11557 11558 979: O: O1958 (predict-no) 11559--- END Decision Phase --- 11560 11561--- Application Phase --- 11562 --- Firing Productions (PE) For State At Depth 1 --- 11563 11564--- Inner Elaboration Phase, active level 1 (S1) --- 11565Firing apply*operator 11566 --> 11567 (I3 ^predict-no N979 + :O ) 11568Firing apply*operator*complete 11569 --> 11570 (I3 ^predict-no N978 - :O ) 11571 inner elaboration loop at bottom goal. 11572 --- Change Working Memory (PE) --- 11573=>WM: (13716: I3 ^predict-no N979) 11574<=WM: (13704: N978 ^status complete) 11575<=WM: (13703: I3 ^predict-no N978) 11576 --- Firing Productions (IE) For State At Depth 1 --- 11577 11578--- Inner Elaboration Phase, active level 1 (S1) --- 11579Firing monitor*world 11580 --> 11581 11582I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 11583 --- Change Working Memory (IE) --- 11584 11585--- END Application Phase --- 11586--- Output Phase --- 11587ENV: Agent did: predict-no for direction U in state State-B 11588In State-B moving U 11589ENV: (next state, see, prediction correct?) = (State-B, 0, True) 11590predict error 0 11591dir: dir isL 11592--- END Output Phase --- 11593\---- Input Phase --- 11594=>WM: (13720: I2 ^dir L) 11595=>WM: (13719: I2 ^reward 1) 11596=>WM: (13718: I2 ^see 0) 11597=>WM: (13717: N979 ^status complete) 11598<=WM: (13707: I2 ^dir U) 11599<=WM: (13706: I2 ^reward 1) 11600<=WM: (13705: I2 ^see 0) 11601=>WM: (13721: I2 ^level-1 R0-root) 11602<=WM: (13708: I2 ^level-1 R0-root) 11603 11604--- END Input Phase --- 11605 11606--- Proposal Phase --- 11607 11608--- Inner Elaboration Phase, active level 1 (S1) --- 11609Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 11610 --> 11611 (S1 ^operator O1957 = 0.6195601949549704) 11612Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 11613 --> 11614 (S1 ^operator O1958 = -0.2190661556260421) 11615Firing prefer*rvt*predict-no*H0*2*v1*H1 11616 --> 11617Firing prefer*rvt*predict-yes*H0*1*v1*H1 11618 --> 11619Firing elaborate*copy-see-to-output-link 11620 --> 11621 (I3 ^see 0 +) 11622Firing elaborate*reward*based*on*reward 11623 --> 11624 (R983 ^value 1 +) 11625 (R1 ^reward R983 +) 11626Firing propose*predict-yes 11627 --> 11628 (O1959 ^name predict-yes +) 11629 (S1 ^operator O1959 +) 11630Firing propose*predict-no 11631 --> 11632 (O1960 ^name predict-no +) 11633 (S1 ^operator O1960 +) 11634Firing rl*prefer*rvt*predict-no*H0*2 11635 --> 11636 (S1 ^operator O1958 = 0.3140233963466647) 11637Firing rl*prefer*rvt*predict-yes*H0*1 11638 --> 11639 (S1 ^operator O1957 = 0.3804118472151704) 11640Firing prefer*rvt*predict-yes*H0 11641 --> 11642Firing prefer*rvt*predict-no*H0 11643 --> 11644Firing elaborate*copy-dir-to-output-link 11645 --> 11646 (I3 ^dir L +) 11647 inner elaboration loop at bottom goal. 11648Retracting elaborate*copy-see-to-output-link 11649 --> 11650 (I3 ^see 0 +) 11651Retracting propose*predict-no 11652 --> 11653 (O1958 ^name predict-no +) 11654 (S1 ^operator O1958 +) 11655Retracting propose*predict-yes 11656 --> 11657 (O1957 ^name predict-yes +) 11658 (S1 ^operator O1957 +) 11659Retracting elaborate*reward*based*on*reward 11660 --> 11661 (R982 ^value 1 +) 11662 (R1 ^reward R982 +) 11663Retracting elaborate*copy-dir-to-output-link 11664 --> 11665 (I3 ^dir U +) 11666Retracting rl*prefer*rvt*predict-no*H0*4 11667 --> 11668 (S1 ^operator O1958 = 1.) 11669Retracting rl*prefer*rvt*predict-yes*H0*3 11670 --> 11671 (S1 ^operator O1957 = 0.) 11672=>WM: (13728: S1 ^operator O1960 +) 11673=>WM: (13727: S1 ^operator O1959 +) 11674=>WM: (13726: I3 ^dir L) 11675=>WM: (13725: O1960 ^name predict-no) 11676=>WM: (13724: O1959 ^name predict-yes) 11677=>WM: (13723: R983 ^value 1) 11678=>WM: (13722: R1 ^reward R983) 11679<=WM: (13713: S1 ^operator O1957 +) 11680<=WM: (13714: S1 ^operator O1958 +) 11681<=WM: (13715: S1 ^operator O1958) 11682<=WM: (13699: I3 ^dir U) 11683<=WM: (13709: R1 ^reward R982) 11684<=WM: (13712: O1958 ^name predict-no) 11685<=WM: (13711: O1957 ^name predict-yes) 11686<=WM: (13710: R982 ^value 1) 11687 11688--- Inner Elaboration Phase, active level 1 (S1) --- 11689Firing prefer*rvt*predict-yes*H0 11690 --> 11691Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 11692 --> 11693 (S1 ^operator O1959 = 0.6195601949549704) 11694Firing rl*prefer*rvt*predict-yes*H0*1 11695 --> 11696 (S1 ^operator O1959 = 0.3804118472151704) 11697Firing prefer*rvt*predict-yes*H0*1*v1*H1 11698 --> 11699Firing prefer*rvt*predict-no*H0 11700 --> 11701Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 11702 --> 11703 (S1 ^operator O1960 = -0.2190661556260421) 11704Firing rl*prefer*rvt*predict-no*H0*2 11705 --> 11706 (S1 ^operator O1960 = 0.3140233963466647) 11707Firing prefer*rvt*predict-no*H0*2*v1*H1 11708 --> 11709 inner elaboration loop at bottom goal. 11710Retracting rl*prefer*rvt*predict-no*H0*2 11711 --> 11712 (S1 ^operator O1958 = 0.3140233963466647) 11713Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 11714 --> 11715 (S1 ^operator O1958 = -0.2190661556260421) 11716Retracting rl*prefer*rvt*predict-yes*H0*1 11717 --> 11718 (S1 ^operator O1957 = 0.3804118472151704) 11719Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 11720 --> 11721 (S1 ^operator O1957 = 0.6195601949549704) 11722 11723--- END Proposal Phase --- 11724 11725--- Decision Phase --- 11726RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 11727=>WM: (13729: S1 ^operator O1959) 11728 11729 980: O: O1959 (predict-yes) 11730--- END Decision Phase --- 11731 11732--- Application Phase --- 11733 --- Firing Productions (PE) For State At Depth 1 --- 11734 11735--- Inner Elaboration Phase, active level 1 (S1) --- 11736Firing apply*operator 11737 --> 11738 (I3 ^predict-yes N980 + :O ) 11739Firing apply*operator*complete 11740 --> 11741 (I3 ^predict-no N979 - :O ) 11742 inner elaboration loop at bottom goal. 11743 --- Change Working Memory (PE) --- 11744=>WM: (13730: I3 ^predict-yes N980) 11745<=WM: (13717: N979 ^status complete) 11746<=WM: (13716: I3 ^predict-no N979) 11747 --- Firing Productions (IE) For State At Depth 1 --- 11748 11749--- Inner Elaboration Phase, active level 1 (S1) --- 11750Firing monitor*world 11751 --> 11752 11753I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 11754 --- Change Working Memory (IE) --- 11755 11756--- END Application Phase --- 11757--- Output Phase --- 11758ENV: Agent did: predict-yes for direction L in state State-B 11759In State-B moving L 11760ENV: (next state, see, prediction correct?) = (State-A, 1, True) 11761predict error 0 11762dir: dir isR 11763--- END Output Phase --- 11764/|\--- Input Phase --- 11765=>WM: (13734: I2 ^dir R) 11766=>WM: (13733: I2 ^reward 1) 11767=>WM: (13732: I2 ^see 1) 11768=>WM: (13731: N980 ^status complete) 11769<=WM: (13720: I2 ^dir L) 11770<=WM: (13719: I2 ^reward 1) 11771<=WM: (13718: I2 ^see 0) 11772=>WM: (13735: I2 ^level-1 L1-root) 11773<=WM: (13721: I2 ^level-1 R0-root) 11774 11775--- END Input Phase --- 11776 11777--- Proposal Phase --- 11778 11779--- Inner Elaboration Phase, active level 1 (S1) --- 11780Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11781 --> 11782 (S1 ^operator O1959 = 0.7064055971121673) 11783Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11784 --> 11785 (S1 ^operator O1960 = -0.1937987592593187) 11786Firing prefer*rvt*predict-no*H0*6*v1*H1 11787 --> 11788Firing prefer*rvt*predict-yes*H0*5*v1*H1 11789 --> 11790Firing elaborate*copy-see-to-output-link 11791 --> 11792 (I3 ^see 1 +) 11793Firing elaborate*reward*based*on*reward 11794 --> 11795 (R984 ^value 1 +) 11796 (R1 ^reward R984 +) 11797Firing propose*predict-yes 11798 --> 11799 (O1961 ^name predict-yes +) 11800 (S1 ^operator O1961 +) 11801Firing propose*predict-no 11802 --> 11803 (O1962 ^name predict-no +) 11804 (S1 ^operator O1962 +) 11805Firing rl*prefer*rvt*predict-no*H0*6 11806 --> 11807 (S1 ^operator O1960 = 0.2298662376128736) 11808Firing rl*prefer*rvt*predict-yes*H0*5 11809 --> 11810 (S1 ^operator O1959 = 0.2939636257009906) 11811Firing prefer*rvt*predict-yes*H0 11812 --> 11813Firing prefer*rvt*predict-no*H0 11814 --> 11815Firing elaborate*copy-dir-to-output-link 11816 --> 11817 (I3 ^dir R +) 11818 inner elaboration loop at bottom goal. 11819Retracting elaborate*copy-see-to-output-link 11820 --> 11821 (I3 ^see 0 +) 11822Retracting propose*predict-no 11823 --> 11824 (O1960 ^name predict-no +) 11825 (S1 ^operator O1960 +) 11826Retracting propose*predict-yes 11827 --> 11828 (O1959 ^name predict-yes +) 11829 (S1 ^operator O1959 +) 11830Retracting elaborate*reward*based*on*reward 11831 --> 11832 (R983 ^value 1 +) 11833 (R1 ^reward R983 +) 11834Retracting elaborate*copy-dir-to-output-link 11835 --> 11836 (I3 ^dir L +) 11837Retracting rl*prefer*rvt*predict-no*H0*2 11838 --> 11839 (S1 ^operator O1960 = 0.3140233963466647) 11840Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 11841 --> 11842 (S1 ^operator O1960 = -0.2190661556260421) 11843Retracting rl*prefer*rvt*predict-yes*H0*1 11844 --> 11845 (S1 ^operator O1959 = 0.3804118472151704) 11846Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 11847 --> 11848 (S1 ^operator O1959 = 0.6195601949549704) 11849=>WM: (13743: S1 ^operator O1962 +) 11850=>WM: (13742: S1 ^operator O1961 +) 11851=>WM: (13741: I3 ^dir R) 11852=>WM: (13740: O1962 ^name predict-no) 11853=>WM: (13739: O1961 ^name predict-yes) 11854=>WM: (13738: R984 ^value 1) 11855=>WM: (13737: R1 ^reward R984) 11856=>WM: (13736: I3 ^see 1) 11857<=WM: (13727: S1 ^operator O1959 +) 11858<=WM: (13729: S1 ^operator O1959) 11859<=WM: (13728: S1 ^operator O1960 +) 11860<=WM: (13726: I3 ^dir L) 11861<=WM: (13722: R1 ^reward R983) 11862<=WM: (13694: I3 ^see 0) 11863<=WM: (13725: O1960 ^name predict-no) 11864<=WM: (13724: O1959 ^name predict-yes) 11865<=WM: (13723: R983 ^value 1) 11866 11867--- Inner Elaboration Phase, active level 1 (S1) --- 11868Firing prefer*rvt*predict-yes*H0 11869 --> 11870Firing rl*prefer*rvt*predict-yes*H0*5 11871 --> 11872 (S1 ^operator O1961 = 0.2939636257009906) 11873Firing prefer*rvt*predict-yes*H0*5*v1*H1 11874 --> 11875Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11876 --> 11877 (S1 ^operator O1961 = 0.7064055971121673) 11878Firing prefer*rvt*predict-no*H0 11879 --> 11880Firing rl*prefer*rvt*predict-no*H0*6 11881 --> 11882 (S1 ^operator O1962 = 0.2298662376128736) 11883Firing prefer*rvt*predict-no*H0*6*v1*H1 11884 --> 11885Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11886 --> 11887 (S1 ^operator O1962 = -0.1937987592593187) 11888 inner elaboration loop at bottom goal. 11889Retracting rl*prefer*rvt*predict-no*H0*6 11890 --> 11891 (S1 ^operator O1960 = 0.2298662376128736) 11892Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 11893 --> 11894 (S1 ^operator O1960 = -0.1937987592593187) 11895Retracting rl*prefer*rvt*predict-yes*H0*5 11896 --> 11897 (S1 ^operator O1959 = 0.2939636257009906) 11898Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 11899 --> 11900 (S1 ^operator O1959 = 0.7064055971121673) 11901 11902--- END Proposal Phase --- 11903 11904--- Decision Phase --- 11905RL update rl*prefer*rvt*predict-yes*H0*1 0.521342 -0.14093 0.380412 -> 0.521344 -0.14093 0.380414(R,m,v=1,0.826087,0.144565) 11906RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478628 0.140932 0.61956 -> 0.478631 0.140932 0.619563(R,m,v=1,1,0) 11907=>WM: (13744: S1 ^operator O1961) 11908 11909 981: O: O1961 (predict-yes) 11910--- END Decision Phase --- 11911 11912--- Application Phase --- 11913 --- Firing Productions (PE) For State At Depth 1 --- 11914 11915--- Inner Elaboration Phase, active level 1 (S1) --- 11916Firing apply*operator 11917 --> 11918 (I3 ^predict-yes N981 + :O ) 11919Firing apply*operator*complete 11920 --> 11921 (I3 ^predict-yes N980 - :O ) 11922 inner elaboration loop at bottom goal. 11923 --- Change Working Memory (PE) --- 11924=>WM: (13745: I3 ^predict-yes N981) 11925<=WM: (13731: N980 ^status complete) 11926<=WM: (13730: I3 ^predict-yes N980) 11927 --- Firing Productions (IE) For State At Depth 1 --- 11928 11929--- Inner Elaboration Phase, active level 1 (S1) --- 11930Firing monitor*world 11931 --> 11932 11933I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 11934 --- Change Working Memory (IE) --- 11935 11936--- END Application Phase --- 11937--- Output Phase --- 11938ENV: Agent did: predict-yes for direction R in state State-A 11939In State-A moving R 11940ENV: (next state, see, prediction correct?) = (State-B, 1, True) 11941predict error 0 11942dir: dir isU 11943--- END Output Phase --- 11944---- Input Phase --- 11945=>WM: (13749: I2 ^dir U) 11946=>WM: (13748: I2 ^reward 1) 11947=>WM: (13747: I2 ^see 1) 11948=>WM: (13746: N981 ^status complete) 11949<=WM: (13734: I2 ^dir R) 11950<=WM: (13733: I2 ^reward 1) 11951<=WM: (13732: I2 ^see 1) 11952=>WM: (13750: I2 ^level-1 R1-root) 11953<=WM: (13735: I2 ^level-1 L1-root) 11954 11955--- END Input Phase --- 11956 11957--- Proposal Phase --- 11958 11959--- Inner Elaboration Phase, active level 1 (S1) --- 11960Firing elaborate*copy-see-to-output-link 11961 --> 11962 (I3 ^see 1 +) 11963Firing elaborate*reward*based*on*reward 11964 --> 11965 (R985 ^value 1 +) 11966 (R1 ^reward R985 +) 11967Firing propose*predict-yes 11968 --> 11969 (O1963 ^name predict-yes +) 11970 (S1 ^operator O1963 +) 11971Firing propose*predict-no 11972 --> 11973 (O1964 ^name predict-no +) 11974 (S1 ^operator O1964 +) 11975Firing rl*prefer*rvt*predict-no*H0*4 11976 --> 11977 (S1 ^operator O1962 = 1.) 11978Firing rl*prefer*rvt*predict-yes*H0*3 11979 --> 11980 (S1 ^operator O1961 = 0.) 11981Firing prefer*rvt*predict-yes*H0 11982 --> 11983Firing prefer*rvt*predict-no*H0 11984 --> 11985Firing elaborate*copy-dir-to-output-link 11986 --> 11987 (I3 ^dir U +) 11988 inner elaboration loop at bottom goal. 11989Retracting elaborate*copy-see-to-output-link 11990 --> 11991 (I3 ^see 1 +) 11992Retracting propose*predict-no 11993 --> 11994 (O1962 ^name predict-no +) 11995 (S1 ^operator O1962 +) 11996Retracting propose*predict-yes 11997 --> 11998 (O1961 ^name predict-yes +) 11999 (S1 ^operator O1961 +) 12000Retracting elaborate*reward*based*on*reward 12001 --> 12002 (R984 ^value 1 +) 12003 (R1 ^reward R984 +) 12004Retracting elaborate*copy-dir-to-output-link 12005 --> 12006 (I3 ^dir R +) 12007Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 12008 --> 12009 (S1 ^operator O1962 = -0.1937987592593187) 12010Retracting rl*prefer*rvt*predict-no*H0*6 12011 --> 12012 (S1 ^operator O1962 = 0.2298662376128736) 12013Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 12014 --> 12015 (S1 ^operator O1961 = 0.7064055971121673) 12016Retracting rl*prefer*rvt*predict-yes*H0*5 12017 --> 12018 (S1 ^operator O1961 = 0.2939636257009906) 12019=>WM: (13757: S1 ^operator O1964 +) 12020=>WM: (13756: S1 ^operator O1963 +) 12021=>WM: (13755: I3 ^dir U) 12022=>WM: (13754: O1964 ^name predict-no) 12023=>WM: (13753: O1963 ^name predict-yes) 12024=>WM: (13752: R985 ^value 1) 12025=>WM: (13751: R1 ^reward R985) 12026<=WM: (13742: S1 ^operator O1961 +) 12027<=WM: (13744: S1 ^operator O1961) 12028<=WM: (13743: S1 ^operator O1962 +) 12029<=WM: (13741: I3 ^dir R) 12030<=WM: (13737: R1 ^reward R984) 12031<=WM: (13740: O1962 ^name predict-no) 12032<=WM: (13739: O1961 ^name predict-yes) 12033<=WM: (13738: R984 ^value 1) 12034 12035--- Inner Elaboration Phase, active level 1 (S1) --- 12036Firing prefer*rvt*predict-yes*H0 12037 --> 12038Firing rl*prefer*rvt*predict-yes*H0*3 12039 --> 12040 (S1 ^operator O1963 = 0.) 12041Firing prefer*rvt*predict-no*H0 12042 --> 12043Firing rl*prefer*rvt*predict-no*H0*4 12044 --> 12045 (S1 ^operator O1964 = 1.) 12046 inner elaboration loop at bottom goal. 12047Retracting rl*prefer*rvt*predict-no*H0*4 12048 --> 12049 (S1 ^operator O1962 = 1.) 12050Retracting rl*prefer*rvt*predict-yes*H0*3 12051 --> 12052 (S1 ^operator O1961 = 0.) 12053 12054--- END Proposal Phase --- 12055 12056--- Decision Phase --- 12057RL update rl*prefer*rvt*predict-yes*H0*5 0.50104 -0.207077 0.293964 -> 0.501013 -0.20708 0.293933(R,m,v=1,0.842105,0.133845) 12058RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499292 0.207114 0.706406 -> 0.499259 0.20711 0.70637(R,m,v=1,1,0) 12059=>WM: (13758: S1 ^operator O1964) 12060 12061 982: O: O1964 (predict-no) 12062--- END Decision Phase --- 12063 12064--- Application Phase --- 12065 --- Firing Productions (PE) For State At Depth 1 --- 12066 12067--- Inner Elaboration Phase, active level 1 (S1) --- 12068Firing apply*operator 12069 --> 12070 (I3 ^predict-no N982 + :O ) 12071Firing apply*operator*complete 12072 --> 12073 (I3 ^predict-yes N981 - :O ) 12074 inner elaboration loop at bottom goal. 12075 --- Change Working Memory (PE) --- 12076=>WM: (13759: I3 ^predict-no N982) 12077<=WM: (13746: N981 ^status complete) 12078<=WM: (13745: I3 ^predict-yes N981) 12079 --- Firing Productions (IE) For State At Depth 1 --- 12080 12081--- Inner Elaboration Phase, active level 1 (S1) --- 12082Firing monitor*world 12083 --> 12084 12085I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 12086 --- Change Working Memory (IE) --- 12087 12088--- END Application Phase --- 12089--- Output Phase --- 12090ENV: Agent did: predict-no for direction U in state State-B 12091In State-B moving U 12092ENV: (next state, see, prediction correct?) = (State-B, 0, True) 12093predict error 0 12094dir: dir isR 12095--- END Output Phase --- 12096/|--- Input Phase --- 12097=>WM: (13763: I2 ^dir R) 12098=>WM: (13762: I2 ^reward 1) 12099=>WM: (13761: I2 ^see 0) 12100=>WM: (13760: N982 ^status complete) 12101<=WM: (13749: I2 ^dir U) 12102<=WM: (13748: I2 ^reward 1) 12103<=WM: (13747: I2 ^see 1) 12104=>WM: (13764: I2 ^level-1 R1-root) 12105<=WM: (13750: I2 ^level-1 R1-root) 12106 12107--- END Input Phase --- 12108 12109--- Proposal Phase --- 12110 12111--- Inner Elaboration Phase, active level 1 (S1) --- 12112Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12113 --> 12114 (S1 ^operator O1963 = -0.252585164213872) 12115Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12116 --> 12117 (S1 ^operator O1964 = 0.7701897521634826) 12118Firing prefer*rvt*predict-no*H0*6*v1*H1 12119 --> 12120Firing prefer*rvt*predict-yes*H0*5*v1*H1 12121 --> 12122Firing elaborate*copy-see-to-output-link 12123 --> 12124 (I3 ^see 0 +) 12125Firing elaborate*reward*based*on*reward 12126 --> 12127 (R986 ^value 1 +) 12128 (R1 ^reward R986 +) 12129Firing propose*predict-yes 12130 --> 12131 (O1965 ^name predict-yes +) 12132 (S1 ^operator O1965 +) 12133Firing propose*predict-no 12134 --> 12135 (O1966 ^name predict-no +) 12136 (S1 ^operator O1966 +) 12137Firing rl*prefer*rvt*predict-no*H0*6 12138 --> 12139 (S1 ^operator O1964 = 0.2298662376128736) 12140Firing rl*prefer*rvt*predict-yes*H0*5 12141 --> 12142 (S1 ^operator O1963 = 0.2939329791093226) 12143Firing prefer*rvt*predict-yes*H0 12144 --> 12145Firing prefer*rvt*predict-no*H0 12146 --> 12147Firing elaborate*copy-dir-to-output-link 12148 --> 12149 (I3 ^dir R +) 12150 inner elaboration loop at bottom goal. 12151Retracting elaborate*copy-see-to-output-link 12152 --> 12153 (I3 ^see 1 +) 12154Retracting propose*predict-no 12155 --> 12156 (O1964 ^name predict-no +) 12157 (S1 ^operator O1964 +) 12158Retracting propose*predict-yes 12159 --> 12160 (O1963 ^name predict-yes +) 12161 (S1 ^operator O1963 +) 12162Retracting elaborate*reward*based*on*reward 12163 --> 12164 (R985 ^value 1 +) 12165 (R1 ^reward R985 +) 12166Retracting elaborate*copy-dir-to-output-link 12167 --> 12168 (I3 ^dir U +) 12169Retracting rl*prefer*rvt*predict-no*H0*4 12170 --> 12171 (S1 ^operator O1964 = 1.) 12172Retracting rl*prefer*rvt*predict-yes*H0*3 12173 --> 12174 (S1 ^operator O1963 = 0.) 12175=>WM: (13772: S1 ^operator O1966 +) 12176=>WM: (13771: S1 ^operator O1965 +) 12177=>WM: (13770: I3 ^dir R) 12178=>WM: (13769: O1966 ^name predict-no) 12179=>WM: (13768: O1965 ^name predict-yes) 12180=>WM: (13767: R986 ^value 1) 12181=>WM: (13766: R1 ^reward R986) 12182=>WM: (13765: I3 ^see 0) 12183<=WM: (13756: S1 ^operator O1963 +) 12184<=WM: (13757: S1 ^operator O1964 +) 12185<=WM: (13758: S1 ^operator O1964) 12186<=WM: (13755: I3 ^dir U) 12187<=WM: (13751: R1 ^reward R985) 12188<=WM: (13736: I3 ^see 1) 12189<=WM: (13754: O1964 ^name predict-no) 12190<=WM: (13753: O1963 ^name predict-yes) 12191<=WM: (13752: R985 ^value 1) 12192 12193--- Inner Elaboration Phase, active level 1 (S1) --- 12194Firing prefer*rvt*predict-yes*H0 12195 --> 12196Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12197 --> 12198 (S1 ^operator O1965 = -0.252585164213872) 12199Firing rl*prefer*rvt*predict-yes*H0*5 12200 --> 12201 (S1 ^operator O1965 = 0.2939329791093226) 12202Firing prefer*rvt*predict-yes*H0*5*v1*H1 12203 --> 12204Firing prefer*rvt*predict-no*H0 12205 --> 12206Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12207 --> 12208 (S1 ^operator O1966 = 0.7701897521634826) 12209Firing rl*prefer*rvt*predict-no*H0*6 12210 --> 12211 (S1 ^operator O1966 = 0.2298662376128736) 12212Firing prefer*rvt*predict-no*H0*6*v1*H1 12213 --> 12214 inner elaboration loop at bottom goal. 12215Retracting rl*prefer*rvt*predict-no*H0*6 12216 --> 12217 (S1 ^operator O1964 = 0.2298662376128736) 12218Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12219 --> 12220 (S1 ^operator O1964 = 0.7701897521634826) 12221Retracting rl*prefer*rvt*predict-yes*H0*5 12222 --> 12223 (S1 ^operator O1963 = 0.2939329791093226) 12224Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12225 --> 12226 (S1 ^operator O1963 = -0.252585164213872) 12227 12228--- END Proposal Phase --- 12229 12230--- Decision Phase --- 12231RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 12232=>WM: (13773: S1 ^operator O1966) 12233 12234 983: O: O1966 (predict-no) 12235--- END Decision Phase --- 12236 12237--- Application Phase --- 12238 --- Firing Productions (PE) For State At Depth 1 --- 12239 12240--- Inner Elaboration Phase, active level 1 (S1) --- 12241Firing apply*operator 12242 --> 12243 (I3 ^predict-no N983 + :O ) 12244Firing apply*operator*complete 12245 --> 12246 (I3 ^predict-no N982 - :O ) 12247 inner elaboration loop at bottom goal. 12248 --- Change Working Memory (PE) --- 12249=>WM: (13774: I3 ^predict-no N983) 12250<=WM: (13760: N982 ^status complete) 12251<=WM: (13759: I3 ^predict-no N982) 12252 --- Firing Productions (IE) For State At Depth 1 --- 12253 12254--- Inner Elaboration Phase, active level 1 (S1) --- 12255Firing monitor*world 12256 --> 12257 12258I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 12259 --- Change Working Memory (IE) --- 12260 12261--- END Application Phase --- 12262--- Output Phase --- 12263ENV: Agent did: predict-no for direction R in state State-B 12264In State-B moving R 12265ENV: (next state, see, prediction correct?) = (State-B, 0, True) 12266predict error 0 12267dir: dir isL 12268--- END Output Phase --- 12269\---- Input Phase --- 12270=>WM: (13778: I2 ^dir L) 12271=>WM: (13777: I2 ^reward 1) 12272=>WM: (13776: I2 ^see 0) 12273=>WM: (13775: N983 ^status complete) 12274<=WM: (13763: I2 ^dir R) 12275<=WM: (13762: I2 ^reward 1) 12276<=WM: (13761: I2 ^see 0) 12277=>WM: (13779: I2 ^level-1 R0-root) 12278<=WM: (13764: I2 ^level-1 R1-root) 12279 12280--- END Input Phase --- 12281 12282--- Proposal Phase --- 12283 12284--- Inner Elaboration Phase, active level 1 (S1) --- 12285Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 12286 --> 12287 (S1 ^operator O1965 = 0.6195629046335391) 12288Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 12289 --> 12290 (S1 ^operator O1966 = -0.2190661556260421) 12291Firing prefer*rvt*predict-no*H0*2*v1*H1 12292 --> 12293Firing prefer*rvt*predict-yes*H0*1*v1*H1 12294 --> 12295Firing elaborate*copy-see-to-output-link 12296 --> 12297 (I3 ^see 0 +) 12298Firing elaborate*reward*based*on*reward 12299 --> 12300 (R987 ^value 1 +) 12301 (R1 ^reward R987 +) 12302Firing propose*predict-yes 12303 --> 12304 (O1967 ^name predict-yes +) 12305 (S1 ^operator O1967 +) 12306Firing propose*predict-no 12307 --> 12308 (O1968 ^name predict-no +) 12309 (S1 ^operator O1968 +) 12310Firing rl*prefer*rvt*predict-no*H0*2 12311 --> 12312 (S1 ^operator O1966 = 0.3140233963466647) 12313Firing rl*prefer*rvt*predict-yes*H0*1 12314 --> 12315 (S1 ^operator O1965 = 0.3804141458478695) 12316Firing prefer*rvt*predict-yes*H0 12317 --> 12318Firing prefer*rvt*predict-no*H0 12319 --> 12320Firing elaborate*copy-dir-to-output-link 12321 --> 12322 (I3 ^dir L +) 12323 inner elaboration loop at bottom goal. 12324Retracting elaborate*copy-see-to-output-link 12325 --> 12326 (I3 ^see 0 +) 12327Retracting propose*predict-no 12328 --> 12329 (O1966 ^name predict-no +) 12330 (S1 ^operator O1966 +) 12331Retracting propose*predict-yes 12332 --> 12333 (O1965 ^name predict-yes +) 12334 (S1 ^operator O1965 +) 12335Retracting elaborate*reward*based*on*reward 12336 --> 12337 (R986 ^value 1 +) 12338 (R1 ^reward R986 +) 12339Retracting elaborate*copy-dir-to-output-link 12340 --> 12341 (I3 ^dir R +) 12342Retracting rl*prefer*rvt*predict-no*H0*6 12343 --> 12344 (S1 ^operator O1966 = 0.2298662376128736) 12345Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12346 --> 12347 (S1 ^operator O1966 = 0.7701897521634826) 12348Retracting rl*prefer*rvt*predict-yes*H0*5 12349 --> 12350 (S1 ^operator O1965 = 0.2939329791093226) 12351Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12352 --> 12353 (S1 ^operator O1965 = -0.252585164213872) 12354=>WM: (13786: S1 ^operator O1968 +) 12355=>WM: (13785: S1 ^operator O1967 +) 12356=>WM: (13784: I3 ^dir L) 12357=>WM: (13783: O1968 ^name predict-no) 12358=>WM: (13782: O1967 ^name predict-yes) 12359=>WM: (13781: R987 ^value 1) 12360=>WM: (13780: R1 ^reward R987) 12361<=WM: (13771: S1 ^operator O1965 +) 12362<=WM: (13772: S1 ^operator O1966 +) 12363<=WM: (13773: S1 ^operator O1966) 12364<=WM: (13770: I3 ^dir R) 12365<=WM: (13766: R1 ^reward R986) 12366<=WM: (13769: O1966 ^name predict-no) 12367<=WM: (13768: O1965 ^name predict-yes) 12368<=WM: (13767: R986 ^value 1) 12369 12370--- Inner Elaboration Phase, active level 1 (S1) --- 12371Firing prefer*rvt*predict-yes*H0 12372 --> 12373Firing rl*prefer*rvt*predict-yes*H0*1 12374 --> 12375 (S1 ^operator O1967 = 0.3804141458478695) 12376Firing prefer*rvt*predict-yes*H0*1*v1*H1 12377 --> 12378Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 12379 --> 12380 (S1 ^operator O1967 = 0.6195629046335391) 12381Firing prefer*rvt*predict-no*H0 12382 --> 12383Firing rl*prefer*rvt*predict-no*H0*2 12384 --> 12385 (S1 ^operator O1968 = 0.3140233963466647) 12386Firing prefer*rvt*predict-no*H0*2*v1*H1 12387 --> 12388Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 12389 --> 12390 (S1 ^operator O1968 = -0.2190661556260421) 12391 inner elaboration loop at bottom goal. 12392Retracting rl*prefer*rvt*predict-no*H0*2 12393 --> 12394 (S1 ^operator O1966 = 0.3140233963466647) 12395Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 12396 --> 12397 (S1 ^operator O1966 = -0.2190661556260421) 12398Retracting rl*prefer*rvt*predict-yes*H0*1 12399 --> 12400 (S1 ^operator O1965 = 0.3804141458478695) 12401Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 12402 --> 12403 (S1 ^operator O1965 = 0.6195629046335391) 12404 12405--- END Proposal Phase --- 12406 12407--- Decision Phase --- 12408RL update rl*prefer*rvt*predict-no*H0*6 0.611917 -0.382051 0.229866 -> 0.611913 -0.382052 0.229862(R,m,v=1,0.843931,0.132477) 12409RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.388128 0.382061 0.77019 -> 0.388124 0.38206 0.770184(R,m,v=1,1,0) 12410=>WM: (13787: S1 ^operator O1967) 12411 12412 984: O: O1967 (predict-yes) 12413--- END Decision Phase --- 12414 12415--- Application Phase --- 12416 --- Firing Productions (PE) For State At Depth 1 --- 12417 12418--- Inner Elaboration Phase, active level 1 (S1) --- 12419Firing apply*operator 12420 --> 12421 (I3 ^predict-yes N984 + :O ) 12422Firing apply*operator*complete 12423 --> 12424 (I3 ^predict-no N983 - :O ) 12425 inner elaboration loop at bottom goal. 12426 --- Change Working Memory (PE) --- 12427=>WM: (13788: I3 ^predict-yes N984) 12428<=WM: (13775: N983 ^status complete) 12429<=WM: (13774: I3 ^predict-no N983) 12430 --- Firing Productions (IE) For State At Depth 1 --- 12431 12432--- Inner Elaboration Phase, active level 1 (S1) --- 12433Firing monitor*world 12434 --> 12435 12436I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 12437 --- Change Working Memory (IE) --- 12438 12439--- END Application Phase --- 12440--- Output Phase --- 12441ENV: Agent did: predict-yes for direction L in state State-B 12442In State-B moving L 12443ENV: (next state, see, prediction correct?) = (State-A, 1, True) 12444predict error 0 12445dir: dir isU 12446--- END Output Phase --- 12447/|\--- Input Phase --- 12448=>WM: (13792: I2 ^dir U) 12449=>WM: (13791: I2 ^reward 1) 12450=>WM: (13790: I2 ^see 1) 12451=>WM: (13789: N984 ^status complete) 12452<=WM: (13778: I2 ^dir L) 12453<=WM: (13777: I2 ^reward 1) 12454<=WM: (13776: I2 ^see 0) 12455=>WM: (13793: I2 ^level-1 L1-root) 12456<=WM: (13779: I2 ^level-1 R0-root) 12457 12458--- END Input Phase --- 12459 12460--- Proposal Phase --- 12461 12462--- Inner Elaboration Phase, active level 1 (S1) --- 12463Firing elaborate*copy-see-to-output-link 12464 --> 12465 (I3 ^see 1 +) 12466Firing elaborate*reward*based*on*reward 12467 --> 12468 (R988 ^value 1 +) 12469 (R1 ^reward R988 +) 12470Firing propose*predict-yes 12471 --> 12472 (O1969 ^name predict-yes +) 12473 (S1 ^operator O1969 +) 12474Firing propose*predict-no 12475 --> 12476 (O1970 ^name predict-no +) 12477 (S1 ^operator O1970 +) 12478Firing rl*prefer*rvt*predict-no*H0*4 12479 --> 12480 (S1 ^operator O1968 = 1.) 12481Firing rl*prefer*rvt*predict-yes*H0*3 12482 --> 12483 (S1 ^operator O1967 = 0.) 12484Firing prefer*rvt*predict-yes*H0 12485 --> 12486Firing prefer*rvt*predict-no*H0 12487 --> 12488Firing elaborate*copy-dir-to-output-link 12489 --> 12490 (I3 ^dir U +) 12491 inner elaboration loop at bottom goal. 12492Retracting elaborate*copy-see-to-output-link 12493 --> 12494 (I3 ^see 0 +) 12495Retracting propose*predict-no 12496 --> 12497 (O1968 ^name predict-no +) 12498 (S1 ^operator O1968 +) 12499Retracting propose*predict-yes 12500 --> 12501 (O1967 ^name predict-yes +) 12502 (S1 ^operator O1967 +) 12503Retracting elaborate*reward*based*on*reward 12504 --> 12505 (R987 ^value 1 +) 12506 (R1 ^reward R987 +) 12507Retracting elaborate*copy-dir-to-output-link 12508 --> 12509 (I3 ^dir L +) 12510Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 12511 --> 12512 (S1 ^operator O1968 = -0.2190661556260421) 12513Retracting rl*prefer*rvt*predict-no*H0*2 12514 --> 12515 (S1 ^operator O1968 = 0.3140233963466647) 12516Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 12517 --> 12518 (S1 ^operator O1967 = 0.6195629046335391) 12519Retracting rl*prefer*rvt*predict-yes*H0*1 12520 --> 12521 (S1 ^operator O1967 = 0.3804141458478695) 12522=>WM: (13801: S1 ^operator O1970 +) 12523=>WM: (13800: S1 ^operator O1969 +) 12524=>WM: (13799: I3 ^dir U) 12525=>WM: (13798: O1970 ^name predict-no) 12526=>WM: (13797: O1969 ^name predict-yes) 12527=>WM: (13796: R988 ^value 1) 12528=>WM: (13795: R1 ^reward R988) 12529=>WM: (13794: I3 ^see 1) 12530<=WM: (13785: S1 ^operator O1967 +) 12531<=WM: (13787: S1 ^operator O1967) 12532<=WM: (13786: S1 ^operator O1968 +) 12533<=WM: (13784: I3 ^dir L) 12534<=WM: (13780: R1 ^reward R987) 12535<=WM: (13765: I3 ^see 0) 12536<=WM: (13783: O1968 ^name predict-no) 12537<=WM: (13782: O1967 ^name predict-yes) 12538<=WM: (13781: R987 ^value 1) 12539 12540--- Inner Elaboration Phase, active level 1 (S1) --- 12541Firing prefer*rvt*predict-yes*H0 12542 --> 12543Firing rl*prefer*rvt*predict-yes*H0*3 12544 --> 12545 (S1 ^operator O1969 = 0.) 12546Firing prefer*rvt*predict-no*H0 12547 --> 12548Firing rl*prefer*rvt*predict-no*H0*4 12549 --> 12550 (S1 ^operator O1970 = 1.) 12551 inner elaboration loop at bottom goal. 12552Retracting rl*prefer*rvt*predict-no*H0*4 12553 --> 12554 (S1 ^operator O1968 = 1.) 12555Retracting rl*prefer*rvt*predict-yes*H0*3 12556 --> 12557 (S1 ^operator O1967 = 0.) 12558 12559--- END Proposal Phase --- 12560 12561--- Decision Phase --- 12562RL update rl*prefer*rvt*predict-yes*H0*1 0.521344 -0.14093 0.380414 -> 0.521346 -0.14093 0.380416(R,m,v=1,0.82716,0.143854) 12563RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478631 0.140932 0.619563 -> 0.478633 0.140932 0.619565(R,m,v=1,1,0) 12564=>WM: (13802: S1 ^operator O1970) 12565 12566 985: O: O1970 (predict-no) 12567--- END Decision Phase --- 12568 12569--- Application Phase --- 12570 --- Firing Productions (PE) For State At Depth 1 --- 12571 12572--- Inner Elaboration Phase, active level 1 (S1) --- 12573Firing apply*operator 12574 --> 12575 (I3 ^predict-no N985 + :O ) 12576Firing apply*operator*complete 12577 --> 12578 (I3 ^predict-yes N984 - :O ) 12579 inner elaboration loop at bottom goal. 12580 --- Change Working Memory (PE) --- 12581=>WM: (13803: I3 ^predict-no N985) 12582<=WM: (13789: N984 ^status complete) 12583<=WM: (13788: I3 ^predict-yes N984) 12584 --- Firing Productions (IE) For State At Depth 1 --- 12585 12586--- Inner Elaboration Phase, active level 1 (S1) --- 12587Firing monitor*world 12588 --> 12589 12590I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 12591 --- Change Working Memory (IE) --- 12592 12593--- END Application Phase --- 12594--- Output Phase --- 12595ENV: Agent did: predict-no for direction U in state State-A 12596In State-A moving U 12597ENV: (next state, see, prediction correct?) = (State-A, 0, True) 12598predict error 0 12599dir: dir isR 12600--- END Output Phase --- 12601-/|--- Input Phase --- 12602=>WM: (13807: I2 ^dir R) 12603=>WM: (13806: I2 ^reward 1) 12604=>WM: (13805: I2 ^see 0) 12605=>WM: (13804: N985 ^status complete) 12606<=WM: (13792: I2 ^dir U) 12607<=WM: (13791: I2 ^reward 1) 12608<=WM: (13790: I2 ^see 1) 12609=>WM: (13808: I2 ^level-1 L1-root) 12610<=WM: (13793: I2 ^level-1 L1-root) 12611 12612--- END Input Phase --- 12613 12614--- Proposal Phase --- 12615 12616--- Inner Elaboration Phase, active level 1 (S1) --- 12617Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 12618 --> 12619 (S1 ^operator O1969 = 0.7063695903698597) 12620Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 12621 --> 12622 (S1 ^operator O1970 = -0.1937987592593187) 12623Firing prefer*rvt*predict-no*H0*6*v1*H1 12624 --> 12625Firing prefer*rvt*predict-yes*H0*5*v1*H1 12626 --> 12627Firing elaborate*copy-see-to-output-link 12628 --> 12629 (I3 ^see 0 +) 12630Firing elaborate*reward*based*on*reward 12631 --> 12632 (R989 ^value 1 +) 12633 (R1 ^reward R989 +) 12634Firing propose*predict-yes 12635 --> 12636 (O1971 ^name predict-yes +) 12637 (S1 ^operator O1971 +) 12638Firing propose*predict-no 12639 --> 12640 (O1972 ^name predict-no +) 12641 (S1 ^operator O1972 +) 12642Firing rl*prefer*rvt*predict-no*H0*6 12643 --> 12644 (S1 ^operator O1970 = 0.2298616880335552) 12645Firing rl*prefer*rvt*predict-yes*H0*5 12646 --> 12647 (S1 ^operator O1969 = 0.2939329791093226) 12648Firing prefer*rvt*predict-yes*H0 12649 --> 12650Firing prefer*rvt*predict-no*H0 12651 --> 12652Firing elaborate*copy-dir-to-output-link 12653 --> 12654 (I3 ^dir R +) 12655 inner elaboration loop at bottom goal. 12656Retracting elaborate*copy-see-to-output-link 12657 --> 12658 (I3 ^see 1 +) 12659Retracting propose*predict-no 12660 --> 12661 (O1970 ^name predict-no +) 12662 (S1 ^operator O1970 +) 12663Retracting propose*predict-yes 12664 --> 12665 (O1969 ^name predict-yes +) 12666 (S1 ^operator O1969 +) 12667Retracting elaborate*reward*based*on*reward 12668 --> 12669 (R988 ^value 1 +) 12670 (R1 ^reward R988 +) 12671Retracting elaborate*copy-dir-to-output-link 12672 --> 12673 (I3 ^dir U +) 12674Retracting rl*prefer*rvt*predict-no*H0*4 12675 --> 12676 (S1 ^operator O1970 = 1.) 12677Retracting rl*prefer*rvt*predict-yes*H0*3 12678 --> 12679 (S1 ^operator O1969 = 0.) 12680=>WM: (13816: S1 ^operator O1972 +) 12681=>WM: (13815: S1 ^operator O1971 +) 12682=>WM: (13814: I3 ^dir R) 12683=>WM: (13813: O1972 ^name predict-no) 12684=>WM: (13812: O1971 ^name predict-yes) 12685=>WM: (13811: R989 ^value 1) 12686=>WM: (13810: R1 ^reward R989) 12687=>WM: (13809: I3 ^see 0) 12688<=WM: (13800: S1 ^operator O1969 +) 12689<=WM: (13801: S1 ^operator O1970 +) 12690<=WM: (13802: S1 ^operator O1970) 12691<=WM: (13799: I3 ^dir U) 12692<=WM: (13795: R1 ^reward R988) 12693<=WM: (13794: I3 ^see 1) 12694<=WM: (13798: O1970 ^name predict-no) 12695<=WM: (13797: O1969 ^name predict-yes) 12696<=WM: (13796: R988 ^value 1) 12697 12698--- Inner Elaboration Phase, active level 1 (S1) --- 12699Firing prefer*rvt*predict-yes*H0 12700 --> 12701Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 12702 --> 12703 (S1 ^operator O1971 = 0.7063695903698597) 12704Firing rl*prefer*rvt*predict-yes*H0*5 12705 --> 12706 (S1 ^operator O1971 = 0.2939329791093226) 12707Firing prefer*rvt*predict-yes*H0*5*v1*H1 12708 --> 12709Firing prefer*rvt*predict-no*H0 12710 --> 12711Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 12712 --> 12713 (S1 ^operator O1972 = -0.1937987592593187) 12714Firing rl*prefer*rvt*predict-no*H0*6 12715 --> 12716 (S1 ^operator O1972 = 0.2298616880335552) 12717Firing prefer*rvt*predict-no*H0*6*v1*H1 12718 --> 12719 inner elaboration loop at bottom goal. 12720Retracting rl*prefer*rvt*predict-no*H0*6 12721 --> 12722 (S1 ^operator O1970 = 0.2298616880335552) 12723Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 12724 --> 12725 (S1 ^operator O1970 = -0.1937987592593187) 12726Retracting rl*prefer*rvt*predict-yes*H0*5 12727 --> 12728 (S1 ^operator O1969 = 0.2939329791093226) 12729Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 12730 --> 12731 (S1 ^operator O1969 = 0.7063695903698597) 12732 12733--- END Proposal Phase --- 12734 12735--- Decision Phase --- 12736RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 12737=>WM: (13817: S1 ^operator O1971) 12738 12739 986: O: O1971 (predict-yes) 12740--- END Decision Phase --- 12741 12742--- Application Phase --- 12743 --- Firing Productions (PE) For State At Depth 1 --- 12744 12745--- Inner Elaboration Phase, active level 1 (S1) --- 12746Firing apply*operator 12747 --> 12748 (I3 ^predict-yes N986 + :O ) 12749Firing apply*operator*complete 12750 --> 12751 (I3 ^predict-no N985 - :O ) 12752 inner elaboration loop at bottom goal. 12753 --- Change Working Memory (PE) --- 12754=>WM: (13818: I3 ^predict-yes N986) 12755<=WM: (13804: N985 ^status complete) 12756<=WM: (13803: I3 ^predict-no N985) 12757 --- Firing Productions (IE) For State At Depth 1 --- 12758 12759--- Inner Elaboration Phase, active level 1 (S1) --- 12760Firing monitor*world 12761 --> 12762 12763I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 12764 --- Change Working Memory (IE) --- 12765 12766--- END Application Phase --- 12767--- Output Phase --- 12768ENV: Agent did: predict-yes for direction R in state State-A 12769In State-A moving R 12770ENV: (next state, see, prediction correct?) = (State-B, 1, True) 12771predict error 0 12772dir: dir isR 12773--- END Output Phase --- 12774\-/--- Input Phase --- 12775=>WM: (13822: I2 ^dir R) 12776=>WM: (13821: I2 ^reward 1) 12777=>WM: (13820: I2 ^see 1) 12778=>WM: (13819: N986 ^status complete) 12779<=WM: (13807: I2 ^dir R) 12780<=WM: (13806: I2 ^reward 1) 12781<=WM: (13805: I2 ^see 0) 12782=>WM: (13823: I2 ^level-1 R1-root) 12783<=WM: (13808: I2 ^level-1 L1-root) 12784 12785--- END Input Phase --- 12786 12787--- Proposal Phase --- 12788 12789--- Inner Elaboration Phase, active level 1 (S1) --- 12790Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12791 --> 12792 (S1 ^operator O1971 = -0.252585164213872) 12793Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12794 --> 12795 (S1 ^operator O1972 = 0.7701842386860367) 12796Firing prefer*rvt*predict-no*H0*6*v1*H1 12797 --> 12798Firing prefer*rvt*predict-yes*H0*5*v1*H1 12799 --> 12800Firing elaborate*copy-see-to-output-link 12801 --> 12802 (I3 ^see 1 +) 12803Firing elaborate*reward*based*on*reward 12804 --> 12805 (R990 ^value 1 +) 12806 (R1 ^reward R990 +) 12807Firing propose*predict-yes 12808 --> 12809 (O1973 ^name predict-yes +) 12810 (S1 ^operator O1973 +) 12811Firing propose*predict-no 12812 --> 12813 (O1974 ^name predict-no +) 12814 (S1 ^operator O1974 +) 12815Firing rl*prefer*rvt*predict-no*H0*6 12816 --> 12817 (S1 ^operator O1972 = 0.2298616880335552) 12818Firing rl*prefer*rvt*predict-yes*H0*5 12819 --> 12820 (S1 ^operator O1971 = 0.2939329791093226) 12821Firing prefer*rvt*predict-yes*H0 12822 --> 12823Firing prefer*rvt*predict-no*H0 12824 --> 12825Firing elaborate*copy-dir-to-output-link 12826 --> 12827 (I3 ^dir R +) 12828 inner elaboration loop at bottom goal. 12829Retracting elaborate*copy-see-to-output-link 12830 --> 12831 (I3 ^see 0 +) 12832Retracting propose*predict-no 12833 --> 12834 (O1972 ^name predict-no +) 12835 (S1 ^operator O1972 +) 12836Retracting propose*predict-yes 12837 --> 12838 (O1971 ^name predict-yes +) 12839 (S1 ^operator O1971 +) 12840Retracting elaborate*reward*based*on*reward 12841 --> 12842 (R989 ^value 1 +) 12843 (R1 ^reward R989 +) 12844Retracting elaborate*copy-dir-to-output-link 12845 --> 12846 (I3 ^dir R +) 12847Retracting rl*prefer*rvt*predict-no*H0*6 12848 --> 12849 (S1 ^operator O1972 = 0.2298616880335552) 12850Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 12851 --> 12852 (S1 ^operator O1972 = -0.1937987592593187) 12853Retracting rl*prefer*rvt*predict-yes*H0*5 12854 --> 12855 (S1 ^operator O1971 = 0.2939329791093226) 12856Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 12857 --> 12858 (S1 ^operator O1971 = 0.7063695903698597) 12859=>WM: (13830: S1 ^operator O1974 +) 12860=>WM: (13829: S1 ^operator O1973 +) 12861=>WM: (13828: O1974 ^name predict-no) 12862=>WM: (13827: O1973 ^name predict-yes) 12863=>WM: (13826: R990 ^value 1) 12864=>WM: (13825: R1 ^reward R990) 12865=>WM: (13824: I3 ^see 1) 12866<=WM: (13815: S1 ^operator O1971 +) 12867<=WM: (13817: S1 ^operator O1971) 12868<=WM: (13816: S1 ^operator O1972 +) 12869<=WM: (13810: R1 ^reward R989) 12870<=WM: (13809: I3 ^see 0) 12871<=WM: (13813: O1972 ^name predict-no) 12872<=WM: (13812: O1971 ^name predict-yes) 12873<=WM: (13811: R989 ^value 1) 12874 12875--- Inner Elaboration Phase, active level 1 (S1) --- 12876Firing prefer*rvt*predict-yes*H0 12877 --> 12878Firing rl*prefer*rvt*predict-yes*H0*5 12879 --> 12880 (S1 ^operator O1973 = 0.2939329791093226) 12881Firing prefer*rvt*predict-yes*H0*5*v1*H1 12882 --> 12883Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12884 --> 12885 (S1 ^operator O1973 = -0.252585164213872) 12886Firing prefer*rvt*predict-no*H0 12887 --> 12888Firing rl*prefer*rvt*predict-no*H0*6 12889 --> 12890 (S1 ^operator O1974 = 0.2298616880335552) 12891Firing prefer*rvt*predict-no*H0*6*v1*H1 12892 --> 12893Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12894 --> 12895 (S1 ^operator O1974 = 0.7701842386860367) 12896 inner elaboration loop at bottom goal. 12897Retracting rl*prefer*rvt*predict-no*H0*6 12898 --> 12899 (S1 ^operator O1972 = 0.2298616880335552) 12900Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 12901 --> 12902 (S1 ^operator O1972 = 0.7701842386860367) 12903Retracting rl*prefer*rvt*predict-yes*H0*5 12904 --> 12905 (S1 ^operator O1971 = 0.2939329791093226) 12906Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 12907 --> 12908 (S1 ^operator O1971 = -0.252585164213872) 12909 12910--- END Proposal Phase --- 12911 12912--- Decision Phase --- 12913RL update rl*prefer*rvt*predict-yes*H0*5 0.501013 -0.20708 0.293933 -> 0.50099 -0.207082 0.293908(R,m,v=1,0.843137,0.133127) 12914RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499259 0.20711 0.70637 -> 0.499233 0.207107 0.70634(R,m,v=1,1,0) 12915=>WM: (13831: S1 ^operator O1974) 12916 12917 987: O: O1974 (predict-no) 12918--- END Decision Phase --- 12919 12920--- Application Phase --- 12921 --- Firing Productions (PE) For State At Depth 1 --- 12922 12923--- Inner Elaboration Phase, active level 1 (S1) --- 12924Firing apply*operator 12925 --> 12926 (I3 ^predict-no N987 + :O ) 12927Firing apply*operator*complete 12928 --> 12929 (I3 ^predict-yes N986 - :O ) 12930 inner elaboration loop at bottom goal. 12931 --- Change Working Memory (PE) --- 12932=>WM: (13832: I3 ^predict-no N987) 12933<=WM: (13819: N986 ^status complete) 12934<=WM: (13818: I3 ^predict-yes N986) 12935 --- Firing Productions (IE) For State At Depth 1 --- 12936 12937--- Inner Elaboration Phase, active level 1 (S1) --- 12938Firing monitor*world 12939 --> 12940 12941I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 12942 --- Change Working Memory (IE) --- 12943 12944--- END Application Phase --- 12945--- Output Phase --- 12946ENV: Agent did: predict-no for direction R in state State-B 12947In State-B moving R 12948ENV: (next state, see, prediction correct?) = (State-B, 0, True) 12949predict error 0 12950dir: dir isL 12951--- END Output Phase --- 12952|\---- Input Phase --- 12953=>WM: (13836: I2 ^dir L) 12954=>WM: (13835: I2 ^reward 1) 12955=>WM: (13834: I2 ^see 0) 12956=>WM: (13833: N987 ^status complete) 12957<=WM: (13822: I2 ^dir R) 12958<=WM: (13821: I2 ^reward 1) 12959<=WM: (13820: I2 ^see 1) 12960=>WM: (13837: I2 ^level-1 R0-root) 12961<=WM: (13823: I2 ^level-1 R1-root) 12962 12963--- END Input Phase --- 12964 12965--- Proposal Phase --- 12966 12967--- Inner Elaboration Phase, active level 1 (S1) --- 12968Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 12969 --> 12970 (S1 ^operator O1973 = 0.6195651222408995) 12971Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 12972 --> 12973 (S1 ^operator O1974 = -0.2190661556260421) 12974Firing prefer*rvt*predict-no*H0*2*v1*H1 12975 --> 12976Firing prefer*rvt*predict-yes*H0*1*v1*H1 12977 --> 12978Firing elaborate*copy-see-to-output-link 12979 --> 12980 (I3 ^see 0 +) 12981Firing elaborate*reward*based*on*reward 12982 --> 12983 (R991 ^value 1 +) 12984 (R1 ^reward R991 +) 12985Firing propose*predict-yes 12986 --> 12987 (O1975 ^name predict-yes +) 12988 (S1 ^operator O1975 +) 12989Firing propose*predict-no 12990 --> 12991 (O1976 ^name predict-no +) 12992 (S1 ^operator O1976 +) 12993Firing rl*prefer*rvt*predict-no*H0*2 12994 --> 12995 (S1 ^operator O1974 = 0.3140233963466647) 12996Firing rl*prefer*rvt*predict-yes*H0*1 12997 --> 12998 (S1 ^operator O1973 = 0.3804160307887663) 12999Firing prefer*rvt*predict-yes*H0 13000 --> 13001Firing prefer*rvt*predict-no*H0 13002 --> 13003Firing elaborate*copy-dir-to-output-link 13004 --> 13005 (I3 ^dir L +) 13006 inner elaboration loop at bottom goal. 13007Retracting elaborate*copy-see-to-output-link 13008 --> 13009 (I3 ^see 1 +) 13010Retracting propose*predict-no 13011 --> 13012 (O1974 ^name predict-no +) 13013 (S1 ^operator O1974 +) 13014Retracting propose*predict-yes 13015 --> 13016 (O1973 ^name predict-yes +) 13017 (S1 ^operator O1973 +) 13018Retracting elaborate*reward*based*on*reward 13019 --> 13020 (R990 ^value 1 +) 13021 (R1 ^reward R990 +) 13022Retracting elaborate*copy-dir-to-output-link 13023 --> 13024 (I3 ^dir R +) 13025Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 13026 --> 13027 (S1 ^operator O1974 = 0.7701842386860367) 13028Retracting rl*prefer*rvt*predict-no*H0*6 13029 --> 13030 (S1 ^operator O1974 = 0.2298616880335552) 13031Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 13032 --> 13033 (S1 ^operator O1973 = -0.252585164213872) 13034Retracting rl*prefer*rvt*predict-yes*H0*5 13035 --> 13036 (S1 ^operator O1973 = 0.2939078922513593) 13037=>WM: (13845: S1 ^operator O1976 +) 13038=>WM: (13844: S1 ^operator O1975 +) 13039=>WM: (13843: I3 ^dir L) 13040=>WM: (13842: O1976 ^name predict-no) 13041=>WM: (13841: O1975 ^name predict-yes) 13042=>WM: (13840: R991 ^value 1) 13043=>WM: (13839: R1 ^reward R991) 13044=>WM: (13838: I3 ^see 0) 13045<=WM: (13829: S1 ^operator O1973 +) 13046<=WM: (13830: S1 ^operator O1974 +) 13047<=WM: (13831: S1 ^operator O1974) 13048<=WM: (13814: I3 ^dir R) 13049<=WM: (13825: R1 ^reward R990) 13050<=WM: (13824: I3 ^see 1) 13051<=WM: (13828: O1974 ^name predict-no) 13052<=WM: (13827: O1973 ^name predict-yes) 13053<=WM: (13826: R990 ^value 1) 13054 13055--- Inner Elaboration Phase, active level 1 (S1) --- 13056Firing prefer*rvt*predict-yes*H0 13057 --> 13058Firing rl*prefer*rvt*predict-yes*H0*1 13059 --> 13060 (S1 ^operator O1975 = 0.3804160307887663) 13061Firing prefer*rvt*predict-yes*H0*1*v1*H1 13062 --> 13063Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 13064 --> 13065 (S1 ^operator O1975 = 0.6195651222408995) 13066Firing prefer*rvt*predict-no*H0 13067 --> 13068Firing rl*prefer*rvt*predict-no*H0*2 13069 --> 13070 (S1 ^operator O1976 = 0.3140233963466647) 13071Firing prefer*rvt*predict-no*H0*2*v1*H1 13072 --> 13073Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 13074 --> 13075 (S1 ^operator O1976 = -0.2190661556260421) 13076 inner elaboration loop at bottom goal. 13077Retracting rl*prefer*rvt*predict-no*H0*2 13078 --> 13079 (S1 ^operator O1974 = 0.3140233963466647) 13080Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 13081 --> 13082 (S1 ^operator O1974 = -0.2190661556260421) 13083Retracting rl*prefer*rvt*predict-yes*H0*1 13084 --> 13085 (S1 ^operator O1973 = 0.3804160307887663) 13086Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 13087 --> 13088 (S1 ^operator O1973 = 0.6195651222408995) 13089 13090--- END Proposal Phase --- 13091 13092--- Decision Phase --- 13093RL update rl*prefer*rvt*predict-no*H0*6 0.611913 -0.382052 0.229862 -> 0.61191 -0.382052 0.229858(R,m,v=1,0.844828,0.131852) 13094RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.388124 0.38206 0.770184 -> 0.38812 0.38206 0.77018(R,m,v=1,1,0) 13095=>WM: (13846: S1 ^operator O1975) 13096 13097 988: O: O1975 (predict-yes) 13098--- END Decision Phase --- 13099 13100--- Application Phase --- 13101 --- Firing Productions (PE) For State At Depth 1 --- 13102 13103--- Inner Elaboration Phase, active level 1 (S1) --- 13104Firing apply*operator 13105 --> 13106 (I3 ^predict-yes N988 + :O ) 13107Firing apply*operator*complete 13108 --> 13109 (I3 ^predict-no N987 - :O ) 13110 inner elaboration loop at bottom goal. 13111 --- Change Working Memory (PE) --- 13112=>WM: (13847: I3 ^predict-yes N988) 13113<=WM: (13833: N987 ^status complete) 13114<=WM: (13832: I3 ^predict-no N987) 13115 --- Firing Productions (IE) For State At Depth 1 --- 13116 13117--- Inner Elaboration Phase, active level 1 (S1) --- 13118Firing monitor*world 13119 --> 13120 13121I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 13122 --- Change Working Memory (IE) --- 13123 13124--- END Application Phase --- 13125--- Output Phase --- 13126ENV: Agent did: predict-yes for direction L in state State-B 13127In State-B moving L 13128ENV: (next state, see, prediction correct?) = (State-A, 1, True) 13129predict error 0 13130dir: dir isU 13131--- END Output Phase --- 13132/|\--- Input Phase --- 13133=>WM: (13851: I2 ^dir U) 13134=>WM: (13850: I2 ^reward 1) 13135=>WM: (13849: I2 ^see 1) 13136=>WM: (13848: N988 ^status complete) 13137<=WM: (13836: I2 ^dir L) 13138<=WM: (13835: I2 ^reward 1) 13139<=WM: (13834: I2 ^see 0) 13140=>WM: (13852: I2 ^level-1 L1-root) 13141<=WM: (13837: I2 ^level-1 R0-root) 13142 13143--- END Input Phase --- 13144 13145--- Proposal Phase --- 13146 13147--- Inner Elaboration Phase, active level 1 (S1) --- 13148Firing elaborate*copy-see-to-output-link 13149 --> 13150 (I3 ^see 1 +) 13151Firing elaborate*reward*based*on*reward 13152 --> 13153 (R992 ^value 1 +) 13154 (R1 ^reward R992 +) 13155Firing propose*predict-yes 13156 --> 13157 (O1977 ^name predict-yes +) 13158 (S1 ^operator O1977 +) 13159Firing propose*predict-no 13160 --> 13161 (O1978 ^name predict-no +) 13162 (S1 ^operator O1978 +) 13163Firing rl*prefer*rvt*predict-no*H0*4 13164 --> 13165 (S1 ^operator O1976 = 1.) 13166Firing rl*prefer*rvt*predict-yes*H0*3 13167 --> 13168 (S1 ^operator O1975 = 0.) 13169Firing prefer*rvt*predict-yes*H0 13170 --> 13171Firing prefer*rvt*predict-no*H0 13172 --> 13173Firing elaborate*copy-dir-to-output-link 13174 --> 13175 (I3 ^dir U +) 13176 inner elaboration loop at bottom goal. 13177Retracting elaborate*copy-see-to-output-link 13178 --> 13179 (I3 ^see 0 +) 13180Retracting propose*predict-no 13181 --> 13182 (O1976 ^name predict-no +) 13183 (S1 ^operator O1976 +) 13184Retracting propose*predict-yes 13185 --> 13186 (O1975 ^name predict-yes +) 13187 (S1 ^operator O1975 +) 13188Retracting elaborate*reward*based*on*reward 13189 --> 13190 (R991 ^value 1 +) 13191 (R1 ^reward R991 +) 13192Retracting elaborate*copy-dir-to-output-link 13193 --> 13194 (I3 ^dir L +) 13195Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 13196 --> 13197 (S1 ^operator O1976 = -0.2190661556260421) 13198Retracting rl*prefer*rvt*predict-no*H0*2 13199 --> 13200 (S1 ^operator O1976 = 0.3140233963466647) 13201Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 13202 --> 13203 (S1 ^operator O1975 = 0.6195651222408995) 13204Retracting rl*prefer*rvt*predict-yes*H0*1 13205 --> 13206 (S1 ^operator O1975 = 0.3804160307887663) 13207=>WM: (13860: S1 ^operator O1978 +) 13208=>WM: (13859: S1 ^operator O1977 +) 13209=>WM: (13858: I3 ^dir U) 13210=>WM: (13857: O1978 ^name predict-no) 13211=>WM: (13856: O1977 ^name predict-yes) 13212=>WM: (13855: R992 ^value 1) 13213=>WM: (13854: R1 ^reward R992) 13214=>WM: (13853: I3 ^see 1) 13215<=WM: (13844: S1 ^operator O1975 +) 13216<=WM: (13846: S1 ^operator O1975) 13217<=WM: (13845: S1 ^operator O1976 +) 13218<=WM: (13843: I3 ^dir L) 13219<=WM: (13839: R1 ^reward R991) 13220<=WM: (13838: I3 ^see 0) 13221<=WM: (13842: O1976 ^name predict-no) 13222<=WM: (13841: O1975 ^name predict-yes) 13223<=WM: (13840: R991 ^value 1) 13224 13225--- Inner Elaboration Phase, active level 1 (S1) --- 13226Firing prefer*rvt*predict-yes*H0 13227 --> 13228Firing rl*prefer*rvt*predict-yes*H0*3 13229 --> 13230 (S1 ^operator O1977 = 0.) 13231Firing prefer*rvt*predict-no*H0 13232 --> 13233Firing rl*prefer*rvt*predict-no*H0*4 13234 --> 13235 (S1 ^operator O1978 = 1.) 13236 inner elaboration loop at bottom goal. 13237Retracting rl*prefer*rvt*predict-no*H0*4 13238 --> 13239 (S1 ^operator O1976 = 1.) 13240Retracting rl*prefer*rvt*predict-yes*H0*3 13241 --> 13242 (S1 ^operator O1975 = 0.) 13243 13244--- END Proposal Phase --- 13245 13246--- Decision Phase --- 13247RL update rl*prefer*rvt*predict-yes*H0*1 0.521346 -0.14093 0.380416 -> 0.521348 -0.14093 0.380418(R,m,v=1,0.828221,0.143149) 13248RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478633 0.140932 0.619565 -> 0.478635 0.140932 0.619567(R,m,v=1,1,0) 13249=>WM: (13861: S1 ^operator O1978) 13250 13251 989: O: O1978 (predict-no) 13252--- END Decision Phase --- 13253 13254--- Application Phase --- 13255 --- Firing Productions (PE) For State At Depth 1 --- 13256 13257--- Inner Elaboration Phase, active level 1 (S1) --- 13258Firing apply*operator 13259 --> 13260 (I3 ^predict-no N989 + :O ) 13261Firing apply*operator*complete 13262 --> 13263 (I3 ^predict-yes N988 - :O ) 13264 inner elaboration loop at bottom goal. 13265 --- Change Working Memory (PE) --- 13266=>WM: (13862: I3 ^predict-no N989) 13267<=WM: (13848: N988 ^status complete) 13268<=WM: (13847: I3 ^predict-yes N988) 13269 --- Firing Productions (IE) For State At Depth 1 --- 13270 13271--- Inner Elaboration Phase, active level 1 (S1) --- 13272Firing monitor*world 13273 --> 13274 13275I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 13276 --- Change Working Memory (IE) --- 13277 13278--- END Application Phase --- 13279--- Output Phase --- 13280ENV: Agent did: predict-no for direction U in state State-A 13281In State-A moving U 13282ENV: (next state, see, prediction correct?) = (State-A, 0, True) 13283predict error 0 13284dir: dir isR 13285--- END Output Phase --- 13286-/|--- Input Phase --- 13287=>WM: (13866: I2 ^dir R) 13288=>WM: (13865: I2 ^reward 1) 13289=>WM: (13864: I2 ^see 0) 13290=>WM: (13863: N989 ^status complete) 13291<=WM: (13851: I2 ^dir U) 13292<=WM: (13850: I2 ^reward 1) 13293<=WM: (13849: I2 ^see 1) 13294=>WM: (13867: I2 ^level-1 L1-root) 13295<=WM: (13852: I2 ^level-1 L1-root) 13296 13297--- END Input Phase --- 13298 13299--- Proposal Phase --- 13300 13301--- Inner Elaboration Phase, active level 1 (S1) --- 13302Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 13303 --> 13304 (S1 ^operator O1977 = 0.7063401754803731) 13305Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 13306 --> 13307 (S1 ^operator O1978 = -0.1937987592593187) 13308Firing prefer*rvt*predict-no*H0*6*v1*H1 13309 --> 13310Firing prefer*rvt*predict-yes*H0*5*v1*H1 13311 --> 13312Firing elaborate*copy-see-to-output-link 13313 --> 13314 (I3 ^see 0 +) 13315Firing elaborate*reward*based*on*reward 13316 --> 13317 (R993 ^value 1 +) 13318 (R1 ^reward R993 +) 13319Firing propose*predict-yes 13320 --> 13321 (O1979 ^name predict-yes +) 13322 (S1 ^operator O1979 +) 13323Firing propose*predict-no 13324 --> 13325 (O1980 ^name predict-no +) 13326 (S1 ^operator O1980 +) 13327Firing rl*prefer*rvt*predict-no*H0*6 13328 --> 13329 (S1 ^operator O1978 = 0.2298579596436188) 13330Firing rl*prefer*rvt*predict-yes*H0*5 13331 --> 13332 (S1 ^operator O1977 = 0.2939078922513593) 13333Firing prefer*rvt*predict-yes*H0 13334 --> 13335Firing prefer*rvt*predict-no*H0 13336 --> 13337Firing elaborate*copy-dir-to-output-link 13338 --> 13339 (I3 ^dir R +) 13340 inner elaboration loop at bottom goal. 13341Retracting elaborate*copy-see-to-output-link 13342 --> 13343 (I3 ^see 1 +) 13344Retracting propose*predict-no 13345 --> 13346 (O1978 ^name predict-no +) 13347 (S1 ^operator O1978 +) 13348Retracting propose*predict-yes 13349 --> 13350 (O1977 ^name predict-yes +) 13351 (S1 ^operator O1977 +) 13352Retracting elaborate*reward*based*on*reward 13353 --> 13354 (R992 ^value 1 +) 13355 (R1 ^reward R992 +) 13356Retracting elaborate*copy-dir-to-output-link 13357 --> 13358 (I3 ^dir U +) 13359Retracting rl*prefer*rvt*predict-no*H0*4 13360 --> 13361 (S1 ^operator O1978 = 1.) 13362Retracting rl*prefer*rvt*predict-yes*H0*3 13363 --> 13364 (S1 ^operator O1977 = 0.) 13365=>WM: (13875: S1 ^operator O1980 +) 13366=>WM: (13874: S1 ^operator O1979 +) 13367=>WM: (13873: I3 ^dir R) 13368=>WM: (13872: O1980 ^name predict-no) 13369=>WM: (13871: O1979 ^name predict-yes) 13370=>WM: (13870: R993 ^value 1) 13371=>WM: (13869: R1 ^reward R993) 13372=>WM: (13868: I3 ^see 0) 13373<=WM: (13859: S1 ^operator O1977 +) 13374<=WM: (13860: S1 ^operator O1978 +) 13375<=WM: (13861: S1 ^operator O1978) 13376<=WM: (13858: I3 ^dir U) 13377<=WM: (13854: R1 ^reward R992) 13378<=WM: (13853: I3 ^see 1) 13379<=WM: (13857: O1978 ^name predict-no) 13380<=WM: (13856: O1977 ^name predict-yes) 13381<=WM: (13855: R992 ^value 1) 13382 13383--- Inner Elaboration Phase, active level 1 (S1) --- 13384Firing prefer*rvt*predict-yes*H0 13385 --> 13386Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 13387 --> 13388 (S1 ^operator O1979 = 0.7063401754803731) 13389Firing rl*prefer*rvt*predict-yes*H0*5 13390 --> 13391 (S1 ^operator O1979 = 0.2939078922513593) 13392Firing prefer*rvt*predict-yes*H0*5*v1*H1 13393 --> 13394Firing prefer*rvt*predict-no*H0 13395 --> 13396Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 13397 --> 13398 (S1 ^operator O1980 = -0.1937987592593187) 13399Firing rl*prefer*rvt*predict-no*H0*6 13400 --> 13401 (S1 ^operator O1980 = 0.2298579596436188) 13402Firing prefer*rvt*predict-no*H0*6*v1*H1 13403 --> 13404 inner elaboration loop at bottom goal. 13405Retracting rl*prefer*rvt*predict-no*H0*6 13406 --> 13407 (S1 ^operator O1978 = 0.2298579596436188) 13408Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 13409 --> 13410 (S1 ^operator O1978 = -0.1937987592593187) 13411Retracting rl*prefer*rvt*predict-yes*H0*5 13412 --> 13413 (S1 ^operator O1977 = 0.2939078922513593) 13414Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 13415 --> 13416 (S1 ^operator O1977 = 0.7063401754803731) 13417 13418--- END Proposal Phase --- 13419 13420--- Decision Phase --- 13421RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 13422=>WM: (13876: S1 ^operator O1979) 13423 13424 990: O: O1979 (predict-yes) 13425--- END Decision Phase --- 13426 13427--- Application Phase --- 13428 --- Firing Productions (PE) For State At Depth 1 --- 13429 13430--- Inner Elaboration Phase, active level 1 (S1) --- 13431Firing apply*operator 13432 --> 13433 (I3 ^predict-yes N990 + :O ) 13434Firing apply*operator*complete 13435 --> 13436 (I3 ^predict-no N989 - :O ) 13437 inner elaboration loop at bottom goal. 13438 --- Change Working Memory (PE) --- 13439=>WM: (13877: I3 ^predict-yes N990) 13440<=WM: (13863: N989 ^status complete) 13441<=WM: (13862: I3 ^predict-no N989) 13442 --- Firing Productions (IE) For State At Depth 1 --- 13443 13444--- Inner Elaboration Phase, active level 1 (S1) --- 13445Firing monitor*world 13446 --> 13447 13448I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 13449 --- Change Working Memory (IE) --- 13450 13451--- END Application Phase --- 13452--- Output Phase --- 13453ENV: Agent did: predict-yes for direction R in state State-A 13454In State-A moving R 13455ENV: (next state, see, prediction correct?) = (State-B, 1, True) 13456predict error 0 13457dir: dir isU 13458--- END Output Phase --- 13459\-/--- Input Phase --- 13460=>WM: (13881: I2 ^dir U) 13461=>WM: (13880: I2 ^reward 1) 13462=>WM: (13879: I2 ^see 1) 13463=>WM: (13878: N990 ^status complete) 13464<=WM: (13866: I2 ^dir R) 13465<=WM: (13865: I2 ^reward 1) 13466<=WM: (13864: I2 ^see 0) 13467=>WM: (13882: I2 ^level-1 R1-root) 13468<=WM: (13867: I2 ^level-1 L1-root) 13469 13470--- END Input Phase --- 13471 13472--- Proposal Phase --- 13473 13474--- Inner Elaboration Phase, active level 1 (S1) --- 13475Firing elaborate*copy-see-to-output-link 13476 --> 13477 (I3 ^see 1 +) 13478Firing elaborate*reward*based*on*reward 13479 --> 13480 (R994 ^value 1 +) 13481 (R1 ^reward R994 +) 13482Firing propose*predict-yes 13483 --> 13484 (O1981 ^name predict-yes +) 13485 (S1 ^operator O1981 +) 13486Firing propose*predict-no 13487 --> 13488 (O1982 ^name predict-no +) 13489 (S1 ^operator O1982 +) 13490Firing rl*prefer*rvt*predict-no*H0*4 13491 --> 13492 (S1 ^operator O1980 = 1.) 13493Firing rl*prefer*rvt*predict-yes*H0*3 13494 --> 13495 (S1 ^operator O1979 = 0.) 13496Firing prefer*rvt*predict-yes*H0 13497 --> 13498Firing prefer*rvt*predict-no*H0 13499 --> 13500Firing elaborate*copy-dir-to-output-link 13501 --> 13502 (I3 ^dir U +) 13503 inner elaboration loop at bottom goal. 13504Retracting elaborate*copy-see-to-output-link 13505 --> 13506 (I3 ^see 0 +) 13507Retracting propose*predict-no 13508 --> 13509 (O1980 ^name predict-no +) 13510 (S1 ^operator O1980 +) 13511Retracting propose*predict-yes 13512 --> 13513 (O1979 ^name predict-yes +) 13514 (S1 ^operator O1979 +) 13515Retracting elaborate*reward*based*on*reward 13516 --> 13517 (R993 ^value 1 +) 13518 (R1 ^reward R993 +) 13519Retracting elaborate*copy-dir-to-output-link 13520 --> 13521 (I3 ^dir R +) 13522Retracting rl*prefer*rvt*predict-no*H0*6 13523 --> 13524 (S1 ^operator O1980 = 0.2298579596436188) 13525Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 13526 --> 13527 (S1 ^operator O1980 = -0.1937987592593187) 13528Retracting rl*prefer*rvt*predict-yes*H0*5 13529 --> 13530 (S1 ^operator O1979 = 0.2939078922513593) 13531Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 13532 --> 13533 (S1 ^operator O1979 = 0.7063401754803731) 13534=>WM: (13890: S1 ^operator O1982 +) 13535=>WM: (13889: S1 ^operator O1981 +) 13536=>WM: (13888: I3 ^dir U) 13537=>WM: (13887: O1982 ^name predict-no) 13538=>WM: (13886: O1981 ^name predict-yes) 13539=>WM: (13885: R994 ^value 1) 13540=>WM: (13884: R1 ^reward R994) 13541=>WM: (13883: I3 ^see 1) 13542<=WM: (13874: S1 ^operator O1979 +) 13543<=WM: (13876: S1 ^operator O1979) 13544<=WM: (13875: S1 ^operator O1980 +) 13545<=WM: (13873: I3 ^dir R) 13546<=WM: (13869: R1 ^reward R993) 13547<=WM: (13868: I3 ^see 0) 13548<=WM: (13872: O1980 ^name predict-no) 13549<=WM: (13871: O1979 ^name predict-yes) 13550<=WM: (13870: R993 ^value 1) 13551 13552--- Inner Elaboration Phase, active level 1 (S1) --- 13553Firing prefer*rvt*predict-yes*H0 13554 --> 13555Firing rl*prefer*rvt*predict-yes*H0*3 13556 --> 13557 (S1 ^operator O1981 = 0.) 13558Firing prefer*rvt*predict-no*H0 13559 --> 13560Firing rl*prefer*rvt*predict-no*H0*4 13561 --> 13562 (S1 ^operator O1982 = 1.) 13563 inner elaboration loop at bottom goal. 13564Retracting rl*prefer*rvt*predict-no*H0*4 13565 --> 13566 (S1 ^operator O1980 = 1.) 13567Retracting rl*prefer*rvt*predict-yes*H0*3 13568 --> 13569 (S1 ^operator O1979 = 0.) 13570 13571--- END Proposal Phase --- 13572 13573--- Decision Phase --- 13574RL update rl*prefer*rvt*predict-yes*H0*5 0.50099 -0.207082 0.293908 -> 0.500972 -0.207084 0.293887(R,m,v=1,0.844156,0.132417) 13575RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499233 0.207107 0.70634 -> 0.499211 0.207105 0.706316(R,m,v=1,1,0) 13576=>WM: (13891: S1 ^operator O1982) 13577 13578 991: O: O1982 (predict-no) 13579--- END Decision Phase --- 13580 13581--- Application Phase --- 13582 --- Firing Productions (PE) For State At Depth 1 --- 13583 13584--- Inner Elaboration Phase, active level 1 (S1) --- 13585Firing apply*operator 13586 --> 13587 (I3 ^predict-no N991 + :O ) 13588Firing apply*operator*complete 13589 --> 13590 (I3 ^predict-yes N990 - :O ) 13591 inner elaboration loop at bottom goal. 13592 --- Change Working Memory (PE) --- 13593=>WM: (13892: I3 ^predict-no N991) 13594<=WM: (13878: N990 ^status complete) 13595<=WM: (13877: I3 ^predict-yes N990) 13596 --- Firing Productions (IE) For State At Depth 1 --- 13597 13598--- Inner Elaboration Phase, active level 1 (S1) --- 13599Firing monitor*world 13600 --> 13601 13602I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 13603 --- Change Working Memory (IE) --- 13604 13605--- END Application Phase --- 13606--- Output Phase --- 13607ENV: Agent did: predict-no for direction U in state State-B 13608In State-B moving U 13609ENV: (next state, see, prediction correct?) = (State-B, 0, True) 13610predict error 0 13611dir: dir isU 13612--- END Output Phase --- 13613|--- Input Phase --- 13614=>WM: (13896: I2 ^dir U) 13615=>WM: (13895: I2 ^reward 1) 13616=>WM: (13894: I2 ^see 0) 13617=>WM: (13893: N991 ^status complete) 13618<=WM: (13881: I2 ^dir U) 13619<=WM: (13880: I2 ^reward 1) 13620<=WM: (13879: I2 ^see 1) 13621=>WM: (13897: I2 ^level-1 R1-root) 13622<=WM: (13882: I2 ^level-1 R1-root) 13623 13624--- END Input Phase --- 13625 13626--- Proposal Phase --- 13627 13628--- Inner Elaboration Phase, active level 1 (S1) --- 13629Firing elaborate*copy-see-to-output-link 13630 --> 13631 (I3 ^see 0 +) 13632Firing elaborate*reward*based*on*reward 13633 --> 13634 (R995 ^value 1 +) 13635 (R1 ^reward R995 +) 13636Firing propose*predict-yes 13637 --> 13638 (O1983 ^name predict-yes +) 13639 (S1 ^operator O1983 +) 13640Firing propose*predict-no 13641 --> 13642 (O1984 ^name predict-no +) 13643 (S1 ^operator O1984 +) 13644Firing rl*prefer*rvt*predict-no*H0*4 13645 --> 13646 (S1 ^operator O1982 = 1.) 13647Firing rl*prefer*rvt*predict-yes*H0*3 13648 --> 13649 (S1 ^operator O1981 = 0.) 13650Firing prefer*rvt*predict-yes*H0 13651 --> 13652Firing prefer*rvt*predict-no*H0 13653 --> 13654Firing elaborate*copy-dir-to-output-link 13655 --> 13656 (I3 ^dir U +) 13657 inner elaboration loop at bottom goal. 13658Retracting elaborate*copy-see-to-output-link 13659 --> 13660 (I3 ^see 1 +) 13661Retracting propose*predict-no 13662 --> 13663 (O1982 ^name predict-no +) 13664 (S1 ^operator O1982 +) 13665Retracting propose*predict-yes 13666 --> 13667 (O1981 ^name predict-yes +) 13668 (S1 ^operator O1981 +) 13669Retracting elaborate*reward*based*on*reward 13670 --> 13671 (R994 ^value 1 +) 13672 (R1 ^reward R994 +) 13673Retracting elaborate*copy-dir-to-output-link 13674 --> 13675 (I3 ^dir U +) 13676Retracting rl*prefer*rvt*predict-no*H0*4 13677 --> 13678 (S1 ^operator O1982 = 1.) 13679Retracting rl*prefer*rvt*predict-yes*H0*3 13680 --> 13681 (S1 ^operator O1981 = 0.) 13682=>WM: (13904: S1 ^operator O1984 +) 13683=>WM: (13903: S1 ^operator O1983 +) 13684=>WM: (13902: O1984 ^name predict-no) 13685=>WM: (13901: O1983 ^name predict-yes) 13686=>WM: (13900: R995 ^value 1) 13687=>WM: (13899: R1 ^reward R995) 13688=>WM: (13898: I3 ^see 0) 13689<=WM: (13889: S1 ^operator O1981 +) 13690<=WM: (13890: S1 ^operator O1982 +) 13691<=WM: (13891: S1 ^operator O1982) 13692<=WM: (13884: R1 ^reward R994) 13693<=WM: (13883: I3 ^see 1) 13694<=WM: (13887: O1982 ^name predict-no) 13695<=WM: (13886: O1981 ^name predict-yes) 13696<=WM: (13885: R994 ^value 1) 13697 13698--- Inner Elaboration Phase, active level 1 (S1) --- 13699Firing prefer*rvt*predict-yes*H0 13700 --> 13701Firing rl*prefer*rvt*predict-yes*H0*3 13702 --> 13703 (S1 ^operator O1983 = 0.) 13704Firing prefer*rvt*predict-no*H0 13705 --> 13706Firing rl*prefer*rvt*predict-no*H0*4 13707 --> 13708 (S1 ^operator O1984 = 1.) 13709 inner elaboration loop at bottom goal. 13710Retracting rl*prefer*rvt*predict-no*H0*4 13711 --> 13712 (S1 ^operator O1982 = 1.) 13713Retracting rl*prefer*rvt*predict-yes*H0*3 13714 --> 13715 (S1 ^operator O1981 = 0.) 13716 13717--- END Proposal Phase --- 13718 13719--- Decision Phase --- 13720RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 13721=>WM: (13905: S1 ^operator O1984) 13722 13723 992: O: O1984 (predict-no) 13724--- END Decision Phase --- 13725 13726--- Application Phase --- 13727 --- Firing Productions (PE) For State At Depth 1 --- 13728 13729--- Inner Elaboration Phase, active level 1 (S1) --- 13730Firing apply*operator 13731 --> 13732 (I3 ^predict-no N992 + :O ) 13733Firing apply*operator*complete 13734 --> 13735 (I3 ^predict-no N991 - :O ) 13736 inner elaboration loop at bottom goal. 13737 --- Change Working Memory (PE) --- 13738=>WM: (13906: I3 ^predict-no N992) 13739<=WM: (13893: N991 ^status complete) 13740<=WM: (13892: I3 ^predict-no N991) 13741 --- Firing Productions (IE) For State At Depth 1 --- 13742 13743--- Inner Elaboration Phase, active level 1 (S1) --- 13744Firing monitor*world 13745 --> 13746 13747I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 13748 --- Change Working Memory (IE) --- 13749 13750--- END Application Phase --- 13751--- Output Phase --- 13752ENV: Agent did: predict-no for direction U in state State-B 13753In State-B moving U 13754ENV: (next state, see, prediction correct?) = (State-B, 0, True) 13755predict error 0 13756dir: dir isL 13757--- END Output Phase --- 13758\-/--- Input Phase --- 13759=>WM: (13910: I2 ^dir L) 13760=>WM: (13909: I2 ^reward 1) 13761=>WM: (13908: I2 ^see 0) 13762=>WM: (13907: N992 ^status complete) 13763<=WM: (13896: I2 ^dir U) 13764<=WM: (13895: I2 ^reward 1) 13765<=WM: (13894: I2 ^see 0) 13766=>WM: (13911: I2 ^level-1 R1-root) 13767<=WM: (13897: I2 ^level-1 R1-root) 13768 13769--- END Input Phase --- 13770 13771--- Proposal Phase --- 13772 13773--- Inner Elaboration Phase, active level 1 (S1) --- 13774Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 13775 --> 13776 (S1 ^operator O1983 = 0.6196129817664832) 13777Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 13778 --> 13779 (S1 ^operator O1984 = -0.1479504104026684) 13780Firing prefer*rvt*predict-no*H0*2*v1*H1 13781 --> 13782Firing prefer*rvt*predict-yes*H0*1*v1*H1 13783 --> 13784Firing elaborate*copy-see-to-output-link 13785 --> 13786 (I3 ^see 0 +) 13787Firing elaborate*reward*based*on*reward 13788 --> 13789 (R996 ^value 1 +) 13790 (R1 ^reward R996 +) 13791Firing propose*predict-yes 13792 --> 13793 (O1985 ^name predict-yes +) 13794 (S1 ^operator O1985 +) 13795Firing propose*predict-no 13796 --> 13797 (O1986 ^name predict-no +) 13798 (S1 ^operator O1986 +) 13799Firing rl*prefer*rvt*predict-no*H0*2 13800 --> 13801 (S1 ^operator O1984 = 0.3140233963466647) 13802Firing rl*prefer*rvt*predict-yes*H0*1 13803 --> 13804 (S1 ^operator O1983 = 0.380417577206794) 13805Firing prefer*rvt*predict-yes*H0 13806 --> 13807Firing prefer*rvt*predict-no*H0 13808 --> 13809Firing elaborate*copy-dir-to-output-link 13810 --> 13811 (I3 ^dir L +) 13812 inner elaboration loop at bottom goal. 13813Retracting elaborate*copy-see-to-output-link 13814 --> 13815 (I3 ^see 0 +) 13816Retracting propose*predict-no 13817 --> 13818 (O1984 ^name predict-no +) 13819 (S1 ^operator O1984 +) 13820Retracting propose*predict-yes 13821 --> 13822 (O1983 ^name predict-yes +) 13823 (S1 ^operator O1983 +) 13824Retracting elaborate*reward*based*on*reward 13825 --> 13826 (R995 ^value 1 +) 13827 (R1 ^reward R995 +) 13828Retracting elaborate*copy-dir-to-output-link 13829 --> 13830 (I3 ^dir U +) 13831Retracting rl*prefer*rvt*predict-no*H0*4 13832 --> 13833 (S1 ^operator O1984 = 1.) 13834Retracting rl*prefer*rvt*predict-yes*H0*3 13835 --> 13836 (S1 ^operator O1983 = 0.) 13837=>WM: (13918: S1 ^operator O1986 +) 13838=>WM: (13917: S1 ^operator O1985 +) 13839=>WM: (13916: I3 ^dir L) 13840=>WM: (13915: O1986 ^name predict-no) 13841=>WM: (13914: O1985 ^name predict-yes) 13842=>WM: (13913: R996 ^value 1) 13843=>WM: (13912: R1 ^reward R996) 13844<=WM: (13903: S1 ^operator O1983 +) 13845<=WM: (13904: S1 ^operator O1984 +) 13846<=WM: (13905: S1 ^operator O1984) 13847<=WM: (13888: I3 ^dir U) 13848<=WM: (13899: R1 ^reward R995) 13849<=WM: (13902: O1984 ^name predict-no) 13850<=WM: (13901: O1983 ^name predict-yes) 13851<=WM: (13900: R995 ^value 1) 13852 13853--- Inner Elaboration Phase, active level 1 (S1) --- 13854Firing prefer*rvt*predict-yes*H0 13855 --> 13856Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 13857 --> 13858 (S1 ^operator O1985 = 0.6196129817664832) 13859Firing rl*prefer*rvt*predict-yes*H0*1 13860 --> 13861 (S1 ^operator O1985 = 0.380417577206794) 13862Firing prefer*rvt*predict-yes*H0*1*v1*H1 13863 --> 13864Firing prefer*rvt*predict-no*H0 13865 --> 13866Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 13867 --> 13868 (S1 ^operator O1986 = -0.1479504104026684) 13869Firing rl*prefer*rvt*predict-no*H0*2 13870 --> 13871 (S1 ^operator O1986 = 0.3140233963466647) 13872Firing prefer*rvt*predict-no*H0*2*v1*H1 13873 --> 13874 inner elaboration loop at bottom goal. 13875Retracting rl*prefer*rvt*predict-no*H0*2 13876 --> 13877 (S1 ^operator O1984 = 0.3140233963466647) 13878Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 13879 --> 13880 (S1 ^operator O1984 = -0.1479504104026684) 13881Retracting rl*prefer*rvt*predict-yes*H0*1 13882 --> 13883 (S1 ^operator O1983 = 0.380417577206794) 13884Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 13885 --> 13886 (S1 ^operator O1983 = 0.6196129817664832) 13887 13888--- END Proposal Phase --- 13889 13890--- Decision Phase --- 13891RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 13892=>WM: (13919: S1 ^operator O1985) 13893 13894 993: O: O1985 (predict-yes) 13895--- END Decision Phase --- 13896 13897--- Application Phase --- 13898 --- Firing Productions (PE) For State At Depth 1 --- 13899 13900--- Inner Elaboration Phase, active level 1 (S1) --- 13901Firing apply*operator 13902 --> 13903 (I3 ^predict-yes N993 + :O ) 13904Firing apply*operator*complete 13905 --> 13906 (I3 ^predict-no N992 - :O ) 13907 inner elaboration loop at bottom goal. 13908 --- Change Working Memory (PE) --- 13909=>WM: (13920: I3 ^predict-yes N993) 13910<=WM: (13907: N992 ^status complete) 13911<=WM: (13906: I3 ^predict-no N992) 13912 --- Firing Productions (IE) For State At Depth 1 --- 13913 13914--- Inner Elaboration Phase, active level 1 (S1) --- 13915Firing monitor*world 13916 --> 13917 13918I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 13919 --- Change Working Memory (IE) --- 13920 13921--- END Application Phase --- 13922--- Output Phase --- 13923ENV: Agent did: predict-yes for direction L in state State-B 13924In State-B moving L 13925ENV: (next state, see, prediction correct?) = (State-A, 1, True) 13926predict error 0 13927dir: dir isR 13928--- END Output Phase --- 13929|\---- Input Phase --- 13930=>WM: (13924: I2 ^dir R) 13931=>WM: (13923: I2 ^reward 1) 13932=>WM: (13922: I2 ^see 1) 13933=>WM: (13921: N993 ^status complete) 13934<=WM: (13910: I2 ^dir L) 13935<=WM: (13909: I2 ^reward 1) 13936<=WM: (13908: I2 ^see 0) 13937=>WM: (13925: I2 ^level-1 L1-root) 13938<=WM: (13911: I2 ^level-1 R1-root) 13939 13940--- END Input Phase --- 13941 13942--- Proposal Phase --- 13943 13944--- Inner Elaboration Phase, active level 1 (S1) --- 13945Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 13946 --> 13947 (S1 ^operator O1985 = 0.7063161327052487) 13948Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 13949 --> 13950 (S1 ^operator O1986 = -0.1937987592593187) 13951Firing prefer*rvt*predict-no*H0*6*v1*H1 13952 --> 13953Firing prefer*rvt*predict-yes*H0*5*v1*H1 13954 --> 13955Firing elaborate*copy-see-to-output-link 13956 --> 13957 (I3 ^see 1 +) 13958Firing elaborate*reward*based*on*reward 13959 --> 13960 (R997 ^value 1 +) 13961 (R1 ^reward R997 +) 13962Firing propose*predict-yes 13963 --> 13964 (O1987 ^name predict-yes +) 13965 (S1 ^operator O1987 +) 13966Firing propose*predict-no 13967 --> 13968 (O1988 ^name predict-no +) 13969 (S1 ^operator O1988 +) 13970Firing rl*prefer*rvt*predict-no*H0*6 13971 --> 13972 (S1 ^operator O1986 = 0.2298579596436188) 13973Firing rl*prefer*rvt*predict-yes*H0*5 13974 --> 13975 (S1 ^operator O1985 = 0.29388734647702) 13976Firing prefer*rvt*predict-yes*H0 13977 --> 13978Firing prefer*rvt*predict-no*H0 13979 --> 13980Firing elaborate*copy-dir-to-output-link 13981 --> 13982 (I3 ^dir R +) 13983 inner elaboration loop at bottom goal. 13984Retracting elaborate*copy-see-to-output-link 13985 --> 13986 (I3 ^see 0 +) 13987Retracting propose*predict-no 13988 --> 13989 (O1986 ^name predict-no +) 13990 (S1 ^operator O1986 +) 13991Retracting propose*predict-yes 13992 --> 13993 (O1985 ^name predict-yes +) 13994 (S1 ^operator O1985 +) 13995Retracting elaborate*reward*based*on*reward 13996 --> 13997 (R996 ^value 1 +) 13998 (R1 ^reward R996 +) 13999Retracting elaborate*copy-dir-to-output-link 14000 --> 14001 (I3 ^dir L +) 14002Retracting rl*prefer*rvt*predict-no*H0*2 14003 --> 14004 (S1 ^operator O1986 = 0.3140233963466647) 14005Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 14006 --> 14007 (S1 ^operator O1986 = -0.1479504104026684) 14008Retracting rl*prefer*rvt*predict-yes*H0*1 14009 --> 14010 (S1 ^operator O1985 = 0.380417577206794) 14011Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 14012 --> 14013 (S1 ^operator O1985 = 0.6196129817664832) 14014=>WM: (13933: S1 ^operator O1988 +) 14015=>WM: (13932: S1 ^operator O1987 +) 14016=>WM: (13931: I3 ^dir R) 14017=>WM: (13930: O1988 ^name predict-no) 14018=>WM: (13929: O1987 ^name predict-yes) 14019=>WM: (13928: R997 ^value 1) 14020=>WM: (13927: R1 ^reward R997) 14021=>WM: (13926: I3 ^see 1) 14022<=WM: (13917: S1 ^operator O1985 +) 14023<=WM: (13919: S1 ^operator O1985) 14024<=WM: (13918: S1 ^operator O1986 +) 14025<=WM: (13916: I3 ^dir L) 14026<=WM: (13912: R1 ^reward R996) 14027<=WM: (13898: I3 ^see 0) 14028<=WM: (13915: O1986 ^name predict-no) 14029<=WM: (13914: O1985 ^name predict-yes) 14030<=WM: (13913: R996 ^value 1) 14031 14032--- Inner Elaboration Phase, active level 1 (S1) --- 14033Firing prefer*rvt*predict-yes*H0 14034 --> 14035Firing rl*prefer*rvt*predict-yes*H0*5 14036 --> 14037 (S1 ^operator O1987 = 0.29388734647702) 14038Firing prefer*rvt*predict-yes*H0*5*v1*H1 14039 --> 14040Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 14041 --> 14042 (S1 ^operator O1987 = 0.7063161327052487) 14043Firing prefer*rvt*predict-no*H0 14044 --> 14045Firing rl*prefer*rvt*predict-no*H0*6 14046 --> 14047 (S1 ^operator O1988 = 0.2298579596436188) 14048Firing prefer*rvt*predict-no*H0*6*v1*H1 14049 --> 14050Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*26 14051 --> 14052 (S1 ^operator O1988 = -0.1937987592593187) 14053 inner elaboration loop at bottom goal. 14054Retracting rl*prefer*rvt*predict-no*H0*6 14055 --> 14056 (S1 ^operator O1986 = 0.2298579596436188) 14057Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 14058 --> 14059 (S1 ^operator O1986 = -0.1937987592593187) 14060Retracting rl*prefer*rvt*predict-yes*H0*5 14061 --> 14062 (S1 ^operator O1985 = 0.29388734647702) 14063Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 14064 --> 14065 (S1 ^operator O1985 = 0.7063161327052487) 14066 14067--- END Proposal Phase --- 14068 14069--- Decision Phase --- 14070RL update rl*prefer*rvt*predict-yes*H0*1 0.521348 -0.14093 0.380418 -> 0.521345 -0.14093 0.380415(R,m,v=1,0.829268,0.142451) 14071RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478686 0.140927 0.619613 -> 0.478682 0.140928 0.61961(R,m,v=1,1,0) 14072=>WM: (13934: S1 ^operator O1987) 14073 14074 994: O: O1987 (predict-yes) 14075--- END Decision Phase --- 14076 14077--- Application Phase --- 14078 --- Firing Productions (PE) For State At Depth 1 --- 14079 14080--- Inner Elaboration Phase, active level 1 (S1) --- 14081Firing apply*operator 14082 --> 14083 (I3 ^predict-yes N994 + :O ) 14084Firing apply*operator*complete 14085 --> 14086 (I3 ^predict-yes N993 - :O ) 14087 inner elaboration loop at bottom goal. 14088 --- Change Working Memory (PE) --- 14089=>WM: (13935: I3 ^predict-yes N994) 14090<=WM: (13921: N993 ^status complete) 14091<=WM: (13920: I3 ^predict-yes N993) 14092 --- Firing Productions (IE) For State At Depth 1 --- 14093 14094--- Inner Elaboration Phase, active level 1 (S1) --- 14095Firing monitor*world 14096 --> 14097 14098I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 14099 --- Change Working Memory (IE) --- 14100 14101--- END Application Phase --- 14102--- Output Phase --- 14103ENV: Agent did: predict-yes for direction R in state State-A 14104In State-A moving R 14105ENV: (next state, see, prediction correct?) = (State-B, 1, True) 14106predict error 0 14107dir: dir isR 14108--- END Output Phase --- 14109/|\--- Input Phase --- 14110=>WM: (13939: I2 ^dir R) 14111=>WM: (13938: I2 ^reward 1) 14112=>WM: (13937: I2 ^see 1) 14113=>WM: (13936: N994 ^status complete) 14114<=WM: (13924: I2 ^dir R) 14115<=WM: (13923: I2 ^reward 1) 14116<=WM: (13922: I2 ^see 1) 14117=>WM: (13940: I2 ^level-1 R1-root) 14118<=WM: (13925: I2 ^level-1 L1-root) 14119 14120--- END Input Phase --- 14121 14122--- Proposal Phase --- 14123 14124--- Inner Elaboration Phase, active level 1 (S1) --- 14125Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 14126 --> 14127 (S1 ^operator O1987 = -0.252585164213872) 14128Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 14129 --> 14130 (S1 ^operator O1988 = 0.7701797310679288) 14131Firing prefer*rvt*predict-no*H0*6*v1*H1 14132 --> 14133Firing prefer*rvt*predict-yes*H0*5*v1*H1 14134 --> 14135Firing elaborate*copy-see-to-output-link 14136 --> 14137 (I3 ^see 1 +) 14138Firing elaborate*reward*based*on*reward 14139 --> 14140 (R998 ^value 1 +) 14141 (R1 ^reward R998 +) 14142Firing propose*predict-yes 14143 --> 14144 (O1989 ^name predict-yes +) 14145 (S1 ^operator O1989 +) 14146Firing propose*predict-no 14147 --> 14148 (O1990 ^name predict-no +) 14149 (S1 ^operator O1990 +) 14150Firing rl*prefer*rvt*predict-no*H0*6 14151 --> 14152 (S1 ^operator O1988 = 0.2298579596436188) 14153Firing rl*prefer*rvt*predict-yes*H0*5 14154 --> 14155 (S1 ^operator O1987 = 0.29388734647702) 14156Firing prefer*rvt*predict-yes*H0 14157 --> 14158Firing prefer*rvt*predict-no*H0 14159 --> 14160Firing elaborate*copy-dir-to-output-link 14161 --> 14162 (I3 ^dir R +) 14163 inner elaboration loop at bottom goal. 14164Retracting elaborate*copy-see-to-output-link 14165 --> 14166 (I3 ^see 1 +) 14167Retracting propose*predict-no 14168 --> 14169 (O1988 ^name predict-no +) 14170 (S1 ^operator O1988 +) 14171Retracting propose*predict-yes 14172 --> 14173 (O1987 ^name predict-yes +) 14174 (S1 ^operator O1987 +) 14175Retracting elaborate*reward*based*on*reward 14176 --> 14177 (R997 ^value 1 +) 14178 (R1 ^reward R997 +) 14179Retracting elaborate*copy-dir-to-output-link 14180 --> 14181 (I3 ^dir R +) 14182Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*26 14183 --> 14184 (S1 ^operator O1988 = -0.1937987592593187) 14185Retracting rl*prefer*rvt*predict-no*H0*6 14186 --> 14187 (S1 ^operator O1988 = 0.2298579596436188) 14188Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 14189 --> 14190 (S1 ^operator O1987 = 0.7063161327052487) 14191Retracting rl*prefer*rvt*predict-yes*H0*5 14192 --> 14193 (S1 ^operator O1987 = 0.29388734647702) 14194=>WM: (13946: S1 ^operator O1990 +) 14195=>WM: (13945: S1 ^operator O1989 +) 14196=>WM: (13944: O1990 ^name predict-no) 14197=>WM: (13943: O1989 ^name predict-yes) 14198=>WM: (13942: R998 ^value 1) 14199=>WM: (13941: R1 ^reward R998) 14200<=WM: (13932: S1 ^operator O1987 +) 14201<=WM: (13934: S1 ^operator O1987) 14202<=WM: (13933: S1 ^operator O1988 +) 14203<=WM: (13927: R1 ^reward R997) 14204<=WM: (13930: O1988 ^name predict-no) 14205<=WM: (13929: O1987 ^name predict-yes) 14206<=WM: (13928: R997 ^value 1) 14207 14208--- Inner Elaboration Phase, active level 1 (S1) --- 14209Firing prefer*rvt*predict-yes*H0 14210 --> 14211Firing rl*prefer*rvt*predict-yes*H0*5 14212 --> 14213 (S1 ^operator O1989 = 0.29388734647702) 14214Firing prefer*rvt*predict-yes*H0*5*v1*H1 14215 --> 14216Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 14217 --> 14218 (S1 ^operator O1989 = -0.252585164213872) 14219Firing prefer*rvt*predict-no*H0 14220 --> 14221Firing rl*prefer*rvt*predict-no*H0*6 14222 --> 14223 (S1 ^operator O1990 = 0.2298579596436188) 14224Firing prefer*rvt*predict-no*H0*6*v1*H1 14225 --> 14226Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 14227 --> 14228 (S1 ^operator O1990 = 0.7701797310679288) 14229 inner elaboration loop at bottom goal. 14230Retracting rl*prefer*rvt*predict-no*H0*6 14231 --> 14232 (S1 ^operator O1988 = 0.2298579596436188) 14233Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 14234 --> 14235 (S1 ^operator O1988 = 0.7701797310679288) 14236Retracting rl*prefer*rvt*predict-yes*H0*5 14237 --> 14238 (S1 ^operator O1987 = 0.29388734647702) 14239Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 14240 --> 14241 (S1 ^operator O1987 = -0.252585164213872) 14242 14243--- END Proposal Phase --- 14244 14245--- Decision Phase --- 14246RL update rl*prefer*rvt*predict-yes*H0*5 0.500972 -0.207084 0.293887 -> 0.500957 -0.207086 0.293871(R,m,v=1,0.845161,0.131713) 14247RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*27 0.499211 0.207105 0.706316 -> 0.499194 0.207103 0.706296(R,m,v=1,1,0) 14248=>WM: (13947: S1 ^operator O1990) 14249 14250 995: O: O1990 (predict-no) 14251--- END Decision Phase --- 14252 14253--- Application Phase --- 14254 --- Firing Productions (PE) For State At Depth 1 --- 14255 14256--- Inner Elaboration Phase, active level 1 (S1) --- 14257Firing apply*operator 14258 --> 14259 (I3 ^predict-no N995 + :O ) 14260Firing apply*operator*complete 14261 --> 14262 (I3 ^predict-yes N994 - :O ) 14263 inner elaboration loop at bottom goal. 14264 --- Change Working Memory (PE) --- 14265=>WM: (13948: I3 ^predict-no N995) 14266<=WM: (13936: N994 ^status complete) 14267<=WM: (13935: I3 ^predict-yes N994) 14268 --- Firing Productions (IE) For State At Depth 1 --- 14269 14270--- Inner Elaboration Phase, active level 1 (S1) --- 14271Firing monitor*world 14272 --> 14273 14274I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 14275 --- Change Working Memory (IE) --- 14276 14277--- END Application Phase --- 14278--- Output Phase --- 14279ENV: Agent did: predict-no for direction R in state State-B 14280In State-B moving R 14281ENV: (next state, see, prediction correct?) = (State-B, 0, True) 14282predict error 0 14283dir: dir isU 14284--- END Output Phase --- 14285-/|--- Input Phase --- 14286=>WM: (13952: I2 ^dir U) 14287=>WM: (13951: I2 ^reward 1) 14288=>WM: (13950: I2 ^see 0) 14289=>WM: (13949: N995 ^status complete) 14290<=WM: (13939: I2 ^dir R) 14291<=WM: (13938: I2 ^reward 1) 14292<=WM: (13937: I2 ^see 1) 14293=>WM: (13953: I2 ^level-1 R0-root) 14294<=WM: (13940: I2 ^level-1 R1-root) 14295 14296--- END Input Phase --- 14297 14298--- Proposal Phase --- 14299 14300--- Inner Elaboration Phase, active level 1 (S1) --- 14301Firing elaborate*copy-see-to-output-link 14302 --> 14303 (I3 ^see 0 +) 14304Firing elaborate*reward*based*on*reward 14305 --> 14306 (R999 ^value 1 +) 14307 (R1 ^reward R999 +) 14308Firing propose*predict-yes 14309 --> 14310 (O1991 ^name predict-yes +) 14311 (S1 ^operator O1991 +) 14312Firing propose*predict-no 14313 --> 14314 (O1992 ^name predict-no +) 14315 (S1 ^operator O1992 +) 14316Firing rl*prefer*rvt*predict-no*H0*4 14317 --> 14318 (S1 ^operator O1990 = 1.) 14319Firing rl*prefer*rvt*predict-yes*H0*3 14320 --> 14321 (S1 ^operator O1989 = 0.) 14322Firing prefer*rvt*predict-yes*H0 14323 --> 14324Firing prefer*rvt*predict-no*H0 14325 --> 14326Firing elaborate*copy-dir-to-output-link 14327 --> 14328 (I3 ^dir U +) 14329 inner elaboration loop at bottom goal. 14330Retracting elaborate*copy-see-to-output-link 14331 --> 14332 (I3 ^see 1 +) 14333Retracting propose*predict-no 14334 --> 14335 (O1990 ^name predict-no +) 14336 (S1 ^operator O1990 +) 14337Retracting propose*predict-yes 14338 --> 14339 (O1989 ^name predict-yes +) 14340 (S1 ^operator O1989 +) 14341Retracting elaborate*reward*based*on*reward 14342 --> 14343 (R998 ^value 1 +) 14344 (R1 ^reward R998 +) 14345Retracting elaborate*copy-dir-to-output-link 14346 --> 14347 (I3 ^dir R +) 14348Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 14349 --> 14350 (S1 ^operator O1990 = 0.7701797310679288) 14351Retracting rl*prefer*rvt*predict-no*H0*6 14352 --> 14353 (S1 ^operator O1990 = 0.2298579596436188) 14354Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 14355 --> 14356 (S1 ^operator O1989 = -0.252585164213872) 14357Retracting rl*prefer*rvt*predict-yes*H0*5 14358 --> 14359 (S1 ^operator O1989 = 0.2938705117203769) 14360=>WM: (13961: S1 ^operator O1992 +) 14361=>WM: (13960: S1 ^operator O1991 +) 14362=>WM: (13959: I3 ^dir U) 14363=>WM: (13958: O1992 ^name predict-no) 14364=>WM: (13957: O1991 ^name predict-yes) 14365=>WM: (13956: R999 ^value 1) 14366=>WM: (13955: R1 ^reward R999) 14367=>WM: (13954: I3 ^see 0) 14368<=WM: (13945: S1 ^operator O1989 +) 14369<=WM: (13946: S1 ^operator O1990 +) 14370<=WM: (13947: S1 ^operator O1990) 14371<=WM: (13931: I3 ^dir R) 14372<=WM: (13941: R1 ^reward R998) 14373<=WM: (13926: I3 ^see 1) 14374<=WM: (13944: O1990 ^name predict-no) 14375<=WM: (13943: O1989 ^name predict-yes) 14376<=WM: (13942: R998 ^value 1) 14377 14378--- Inner Elaboration Phase, active level 1 (S1) --- 14379Firing prefer*rvt*predict-yes*H0 14380 --> 14381Firing rl*prefer*rvt*predict-yes*H0*3 14382 --> 14383 (S1 ^operator O1991 = 0.) 14384Firing prefer*rvt*predict-no*H0 14385 --> 14386Firing rl*prefer*rvt*predict-no*H0*4 14387 --> 14388 (S1 ^operator O1992 = 1.) 14389 inner elaboration loop at bottom goal. 14390Retracting rl*prefer*rvt*predict-no*H0*4 14391 --> 14392 (S1 ^operator O1990 = 1.) 14393Retracting rl*prefer*rvt*predict-yes*H0*3 14394 --> 14395 (S1 ^operator O1989 = 0.) 14396 14397--- END Proposal Phase --- 14398 14399--- Decision Phase --- 14400RL update rl*prefer*rvt*predict-no*H0*6 0.61191 -0.382052 0.229858 -> 0.611908 -0.382053 0.229855(R,m,v=1,0.845714,0.131232) 14401RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.38812 0.38206 0.77018 -> 0.388117 0.382059 0.770176(R,m,v=1,1,0) 14402=>WM: (13962: S1 ^operator O1992) 14403 14404 996: O: O1992 (predict-no) 14405--- END Decision Phase --- 14406 14407--- Application Phase --- 14408 --- Firing Productions (PE) For State At Depth 1 --- 14409 14410--- Inner Elaboration Phase, active level 1 (S1) --- 14411Firing apply*operator 14412 --> 14413 (I3 ^predict-no N996 + :O ) 14414Firing apply*operator*complete 14415 --> 14416 (I3 ^predict-no N995 - :O ) 14417 inner elaboration loop at bottom goal. 14418 --- Change Working Memory (PE) --- 14419=>WM: (13963: I3 ^predict-no N996) 14420<=WM: (13949: N995 ^status complete) 14421<=WM: (13948: I3 ^predict-no N995) 14422 --- Firing Productions (IE) For State At Depth 1 --- 14423 14424--- Inner Elaboration Phase, active level 1 (S1) --- 14425Firing monitor*world 14426 --> 14427 14428I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 14429 --- Change Working Memory (IE) --- 14430 14431--- END Application Phase --- 14432--- Output Phase --- 14433ENV: Agent did: predict-no for direction U in state State-B 14434In State-B moving U 14435ENV: (next state, see, prediction correct?) = (State-B, 0, True) 14436predict error 0 14437dir: dir isU 14438--- END Output Phase --- 14439\-/--- Input Phase --- 14440=>WM: (13967: I2 ^dir U) 14441=>WM: (13966: I2 ^reward 1) 14442=>WM: (13965: I2 ^see 0) 14443=>WM: (13964: N996 ^status complete) 14444<=WM: (13952: I2 ^dir U) 14445<=WM: (13951: I2 ^reward 1) 14446<=WM: (13950: I2 ^see 0) 14447=>WM: (13968: I2 ^level-1 R0-root) 14448<=WM: (13953: I2 ^level-1 R0-root) 14449 14450--- END Input Phase --- 14451 14452--- Proposal Phase --- 14453 14454--- Inner Elaboration Phase, active level 1 (S1) --- 14455Firing elaborate*copy-see-to-output-link 14456 --> 14457 (I3 ^see 0 +) 14458Firing elaborate*reward*based*on*reward 14459 --> 14460 (R1000 ^value 1 +) 14461 (R1 ^reward R1000 +) 14462Firing propose*predict-yes 14463 --> 14464 (O1993 ^name predict-yes +) 14465 (S1 ^operator O1993 +) 14466Firing propose*predict-no 14467 --> 14468 (O1994 ^name predict-no +) 14469 (S1 ^operator O1994 +) 14470Firing rl*prefer*rvt*predict-no*H0*4 14471 --> 14472 (S1 ^operator O1992 = 1.) 14473Firing rl*prefer*rvt*predict-yes*H0*3 14474 --> 14475 (S1 ^operator O1991 = 0.) 14476Firing prefer*rvt*predict-yes*H0 14477 --> 14478Firing prefer*rvt*predict-no*H0 14479 --> 14480Firing elaborate*copy-dir-to-output-link 14481 --> 14482 (I3 ^dir U +) 14483 inner elaboration loop at bottom goal. 14484Retracting elaborate*copy-see-to-output-link 14485 --> 14486 (I3 ^see 0 +) 14487Retracting propose*predict-no 14488 --> 14489 (O1992 ^name predict-no +) 14490 (S1 ^operator O1992 +) 14491Retracting propose*predict-yes 14492 --> 14493 (O1991 ^name predict-yes +) 14494 (S1 ^operator O1991 +) 14495Retracting elaborate*reward*based*on*reward 14496 --> 14497 (R999 ^value 1 +) 14498 (R1 ^reward R999 +) 14499Retracting elaborate*copy-dir-to-output-link 14500 --> 14501 (I3 ^dir U +) 14502Retracting rl*prefer*rvt*predict-no*H0*4 14503 --> 14504 (S1 ^operator O1992 = 1.) 14505Retracting rl*prefer*rvt*predict-yes*H0*3 14506 --> 14507 (S1 ^operator O1991 = 0.) 14508=>WM: (13974: S1 ^operator O1994 +) 14509=>WM: (13973: S1 ^operator O1993 +) 14510=>WM: (13972: O1994 ^name predict-no) 14511=>WM: (13971: O1993 ^name predict-yes) 14512=>WM: (13970: R1000 ^value 1) 14513=>WM: (13969: R1 ^reward R1000) 14514<=WM: (13960: S1 ^operator O1991 +) 14515<=WM: (13961: S1 ^operator O1992 +) 14516<=WM: (13962: S1 ^operator O1992) 14517<=WM: (13955: R1 ^reward R999) 14518<=WM: (13958: O1992 ^name predict-no) 14519<=WM: (13957: O1991 ^name predict-yes) 14520<=WM: (13956: R999 ^value 1) 14521 14522--- Inner Elaboration Phase, active level 1 (S1) --- 14523Firing prefer*rvt*predict-yes*H0 14524 --> 14525Firing rl*prefer*rvt*predict-yes*H0*3 14526 --> 14527 (S1 ^operator O1993 = 0.) 14528Firing prefer*rvt*predict-no*H0 14529 --> 14530Firing rl*prefer*rvt*predict-no*H0*4 14531 --> 14532 (S1 ^operator O1994 = 1.) 14533 inner elaboration loop at bottom goal. 14534Retracting rl*prefer*rvt*predict-no*H0*4 14535 --> 14536 (S1 ^operator O1992 = 1.) 14537Retracting rl*prefer*rvt*predict-yes*H0*3 14538 --> 14539 (S1 ^operator O1991 = 0.) 14540 14541--- END Proposal Phase --- 14542 14543--- Decision Phase --- 14544RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 14545=>WM: (13975: S1 ^operator O1994) 14546 14547 997: O: O1994 (predict-no) 14548--- END Decision Phase --- 14549 14550--- Application Phase --- 14551 --- Firing Productions (PE) For State At Depth 1 --- 14552 14553--- Inner Elaboration Phase, active level 1 (S1) --- 14554Firing apply*operator 14555 --> 14556 (I3 ^predict-no N997 + :O ) 14557Firing apply*operator*complete 14558 --> 14559 (I3 ^predict-no N996 - :O ) 14560 inner elaboration loop at bottom goal. 14561 --- Change Working Memory (PE) --- 14562=>WM: (13976: I3 ^predict-no N997) 14563<=WM: (13964: N996 ^status complete) 14564<=WM: (13963: I3 ^predict-no N996) 14565 --- Firing Productions (IE) For State At Depth 1 --- 14566 14567--- Inner Elaboration Phase, active level 1 (S1) --- 14568Firing monitor*world 14569 --> 14570 14571I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 14572 --- Change Working Memory (IE) --- 14573 14574--- END Application Phase --- 14575--- Output Phase --- 14576ENV: Agent did: predict-no for direction U in state State-B 14577In State-B moving U 14578ENV: (next state, see, prediction correct?) = (State-B, 0, True) 14579predict error 0 14580dir: dir isL 14581--- END Output Phase --- 14582|\--- Input Phase --- 14583=>WM: (13980: I2 ^dir L) 14584=>WM: (13979: I2 ^reward 1) 14585=>WM: (13978: I2 ^see 0) 14586=>WM: (13977: N997 ^status complete) 14587<=WM: (13967: I2 ^dir U) 14588<=WM: (13966: I2 ^reward 1) 14589<=WM: (13965: I2 ^see 0) 14590=>WM: (13981: I2 ^level-1 R0-root) 14591<=WM: (13968: I2 ^level-1 R0-root) 14592 14593--- END Input Phase --- 14594 14595--- Proposal Phase --- 14596 14597--- Inner Elaboration Phase, active level 1 (S1) --- 14598Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 14599 --> 14600 (S1 ^operator O1993 = 0.6195669380621123) 14601Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 14602 --> 14603 (S1 ^operator O1994 = -0.2190661556260421) 14604Firing prefer*rvt*predict-no*H0*2*v1*H1 14605 --> 14606Firing prefer*rvt*predict-yes*H0*1*v1*H1 14607 --> 14608Firing elaborate*copy-see-to-output-link 14609 --> 14610 (I3 ^see 0 +) 14611Firing elaborate*reward*based*on*reward 14612 --> 14613 (R1001 ^value 1 +) 14614 (R1 ^reward R1001 +) 14615Firing propose*predict-yes 14616 --> 14617 (O1995 ^name predict-yes +) 14618 (S1 ^operator O1995 +) 14619Firing propose*predict-no 14620 --> 14621 (O1996 ^name predict-no +) 14622 (S1 ^operator O1996 +) 14623Firing rl*prefer*rvt*predict-no*H0*2 14624 --> 14625 (S1 ^operator O1994 = 0.3140233963466647) 14626Firing rl*prefer*rvt*predict-yes*H0*1 14627 --> 14628 (S1 ^operator O1993 = 0.380415072318069) 14629Firing prefer*rvt*predict-yes*H0 14630 --> 14631Firing prefer*rvt*predict-no*H0 14632 --> 14633Firing elaborate*copy-dir-to-output-link 14634 --> 14635 (I3 ^dir L +) 14636 inner elaboration loop at bottom goal. 14637Retracting elaborate*copy-see-to-output-link 14638 --> 14639 (I3 ^see 0 +) 14640Retracting propose*predict-no 14641 --> 14642 (O1994 ^name predict-no +) 14643 (S1 ^operator O1994 +) 14644Retracting propose*predict-yes 14645 --> 14646 (O1993 ^name predict-yes +) 14647 (S1 ^operator O1993 +) 14648Retracting elaborate*reward*based*on*reward 14649 --> 14650 (R1000 ^value 1 +) 14651 (R1 ^reward R1000 +) 14652Retracting elaborate*copy-dir-to-output-link 14653 --> 14654 (I3 ^dir U +) 14655Retracting rl*prefer*rvt*predict-no*H0*4 14656 --> 14657 (S1 ^operator O1994 = 1.) 14658Retracting rl*prefer*rvt*predict-yes*H0*3 14659 --> 14660 (S1 ^operator O1993 = 0.) 14661=>WM: (13988: S1 ^operator O1996 +) 14662=>WM: (13987: S1 ^operator O1995 +) 14663=>WM: (13986: I3 ^dir L) 14664=>WM: (13985: O1996 ^name predict-no) 14665=>WM: (13984: O1995 ^name predict-yes) 14666=>WM: (13983: R1001 ^value 1) 14667=>WM: (13982: R1 ^reward R1001) 14668<=WM: (13973: S1 ^operator O1993 +) 14669<=WM: (13974: S1 ^operator O1994 +) 14670<=WM: (13975: S1 ^operator O1994) 14671<=WM: (13959: I3 ^dir U) 14672<=WM: (13969: R1 ^reward R1000) 14673<=WM: (13972: O1994 ^name predict-no) 14674<=WM: (13971: O1993 ^name predict-yes) 14675<=WM: (13970: R1000 ^value 1) 14676 14677--- Inner Elaboration Phase, active level 1 (S1) --- 14678Firing prefer*rvt*predict-yes*H0 14679 --> 14680Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 14681 --> 14682 (S1 ^operator O1995 = 0.6195669380621123) 14683Firing rl*prefer*rvt*predict-yes*H0*1 14684 --> 14685 (S1 ^operator O1995 = 0.380415072318069) 14686Firing prefer*rvt*predict-yes*H0*1*v1*H1 14687 --> 14688Firing prefer*rvt*predict-no*H0 14689 --> 14690Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*34 14691 --> 14692 (S1 ^operator O1996 = -0.2190661556260421) 14693Firing rl*prefer*rvt*predict-no*H0*2 14694 --> 14695 (S1 ^operator O1996 = 0.3140233963466647) 14696Firing prefer*rvt*predict-no*H0*2*v1*H1 14697 --> 14698 inner elaboration loop at bottom goal. 14699Retracting rl*prefer*rvt*predict-no*H0*2 14700 --> 14701 (S1 ^operator O1994 = 0.3140233963466647) 14702Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 14703 --> 14704 (S1 ^operator O1994 = -0.2190661556260421) 14705Retracting rl*prefer*rvt*predict-yes*H0*1 14706 --> 14707 (S1 ^operator O1993 = 0.380415072318069) 14708Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 14709 --> 14710 (S1 ^operator O1993 = 0.6195669380621123) 14711 14712--- END Proposal Phase --- 14713 14714--- Decision Phase --- 14715RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 14716=>WM: (13989: S1 ^operator O1995) 14717 14718 998: O: O1995 (predict-yes) 14719--- END Decision Phase --- 14720 14721--- Application Phase --- 14722 --- Firing Productions (PE) For State At Depth 1 --- 14723 14724--- Inner Elaboration Phase, active level 1 (S1) --- 14725Firing apply*operator 14726 --> 14727 (I3 ^predict-yes N998 + :O ) 14728Firing apply*operator*complete 14729 --> 14730 (I3 ^predict-no N997 - :O ) 14731 inner elaboration loop at bottom goal. 14732 --- Change Working Memory (PE) --- 14733=>WM: (13990: I3 ^predict-yes N998) 14734<=WM: (13977: N997 ^status complete) 14735<=WM: (13976: I3 ^predict-no N997) 14736 --- Firing Productions (IE) For State At Depth 1 --- 14737 14738--- Inner Elaboration Phase, active level 1 (S1) --- 14739Firing monitor*world 14740 --> 14741 14742I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 14743 --- Change Working Memory (IE) --- 14744 14745--- END Application Phase --- 14746--- Output Phase --- 14747ENV: Agent did: predict-yes for direction L in state State-B 14748In State-B moving L 14749ENV: (next state, see, prediction correct?) = (State-A, 1, True) 14750predict error 0 14751dir: dir isL 14752--- END Output Phase --- 14753-/|--- Input Phase --- 14754=>WM: (13994: I2 ^dir L) 14755=>WM: (13993: I2 ^reward 1) 14756=>WM: (13992: I2 ^see 1) 14757=>WM: (13991: N998 ^status complete) 14758<=WM: (13980: I2 ^dir L) 14759<=WM: (13979: I2 ^reward 1) 14760<=WM: (13978: I2 ^see 0) 14761=>WM: (13995: I2 ^level-1 L1-root) 14762<=WM: (13981: I2 ^level-1 R0-root) 14763 14764--- END Input Phase --- 14765 14766--- Proposal Phase --- 14767 14768--- Inner Elaboration Phase, active level 1 (S1) --- 14769Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 14770 --> 14771 (S1 ^operator O1995 = -0.3470159027404986) 14772Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 14773 --> 14774 (S1 ^operator O1996 = 0.686145215235081) 14775Firing prefer*rvt*predict-no*H0*2*v1*H1 14776 --> 14777Firing prefer*rvt*predict-yes*H0*1*v1*H1 14778 --> 14779Firing elaborate*copy-see-to-output-link 14780 --> 14781 (I3 ^see 1 +) 14782Firing elaborate*reward*based*on*reward 14783 --> 14784 (R1002 ^value 1 +) 14785 (R1 ^reward R1002 +) 14786Firing propose*predict-yes 14787 --> 14788 (O1997 ^name predict-yes +) 14789 (S1 ^operator O1997 +) 14790Firing propose*predict-no 14791 --> 14792 (O1998 ^name predict-no +) 14793 (S1 ^operator O1998 +) 14794Firing rl*prefer*rvt*predict-no*H0*2 14795 --> 14796 (S1 ^operator O1996 = 0.3140233963466647) 14797Firing rl*prefer*rvt*predict-yes*H0*1 14798 --> 14799 (S1 ^operator O1995 = 0.380415072318069) 14800Firing prefer*rvt*predict-yes*H0 14801 --> 14802Firing prefer*rvt*predict-no*H0 14803 --> 14804Firing elaborate*copy-dir-to-output-link 14805 --> 14806 (I3 ^dir L +) 14807 inner elaboration loop at bottom goal. 14808Retracting elaborate*copy-see-to-output-link 14809 --> 14810 (I3 ^see 0 +) 14811Retracting propose*predict-no 14812 --> 14813 (O1996 ^name predict-no +) 14814 (S1 ^operator O1996 +) 14815Retracting propose*predict-yes 14816 --> 14817 (O1995 ^name predict-yes +) 14818 (S1 ^operator O1995 +) 14819Retracting elaborate*reward*based*on*reward 14820 --> 14821 (R1001 ^value 1 +) 14822 (R1 ^reward R1001 +) 14823Retracting elaborate*copy-dir-to-output-link 14824 --> 14825 (I3 ^dir L +) 14826Retracting rl*prefer*rvt*predict-no*H0*2 14827 --> 14828 (S1 ^operator O1996 = 0.3140233963466647) 14829Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*34 14830 --> 14831 (S1 ^operator O1996 = -0.2190661556260421) 14832Retracting rl*prefer*rvt*predict-yes*H0*1 14833 --> 14834 (S1 ^operator O1995 = 0.380415072318069) 14835Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 14836 --> 14837 (S1 ^operator O1995 = 0.6195669380621123) 14838=>WM: (14002: S1 ^operator O1998 +) 14839=>WM: (14001: S1 ^operator O1997 +) 14840=>WM: (14000: O1998 ^name predict-no) 14841=>WM: (13999: O1997 ^name predict-yes) 14842=>WM: (13998: R1002 ^value 1) 14843=>WM: (13997: R1 ^reward R1002) 14844=>WM: (13996: I3 ^see 1) 14845<=WM: (13987: S1 ^operator O1995 +) 14846<=WM: (13989: S1 ^operator O1995) 14847<=WM: (13988: S1 ^operator O1996 +) 14848<=WM: (13982: R1 ^reward R1001) 14849<=WM: (13954: I3 ^see 0) 14850<=WM: (13985: O1996 ^name predict-no) 14851<=WM: (13984: O1995 ^name predict-yes) 14852<=WM: (13983: R1001 ^value 1) 14853 14854--- Inner Elaboration Phase, active level 1 (S1) --- 14855Firing prefer*rvt*predict-yes*H0 14856 --> 14857Firing rl*prefer*rvt*predict-yes*H0*1 14858 --> 14859 (S1 ^operator O1997 = 0.380415072318069) 14860Firing prefer*rvt*predict-yes*H0*1*v1*H1 14861 --> 14862Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 14863 --> 14864 (S1 ^operator O1997 = -0.3470159027404986) 14865Firing prefer*rvt*predict-no*H0 14866 --> 14867Firing rl*prefer*rvt*predict-no*H0*2 14868 --> 14869 (S1 ^operator O1998 = 0.3140233963466647) 14870Firing prefer*rvt*predict-no*H0*2*v1*H1 14871 --> 14872Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 14873 --> 14874 (S1 ^operator O1998 = 0.686145215235081) 14875 inner elaboration loop at bottom goal. 14876Retracting rl*prefer*rvt*predict-no*H0*2 14877 --> 14878 (S1 ^operator O1996 = 0.3140233963466647) 14879Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 14880 --> 14881 (S1 ^operator O1996 = 0.686145215235081) 14882Retracting rl*prefer*rvt*predict-yes*H0*1 14883 --> 14884 (S1 ^operator O1995 = 0.380415072318069) 14885Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 14886 --> 14887 (S1 ^operator O1995 = -0.3470159027404986) 14888 14889--- END Proposal Phase --- 14890 14891--- Decision Phase --- 14892RL update rl*prefer*rvt*predict-yes*H0*1 0.521345 -0.14093 0.380415 -> 0.521347 -0.14093 0.380417(R,m,v=1,0.830303,0.141759) 14893RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*35 0.478635 0.140932 0.619567 -> 0.478637 0.140932 0.619569(R,m,v=1,1,0) 14894=>WM: (14003: S1 ^operator O1998) 14895 14896 999: O: O1998 (predict-no) 14897--- END Decision Phase --- 14898 14899--- Application Phase --- 14900 --- Firing Productions (PE) For State At Depth 1 --- 14901 14902--- Inner Elaboration Phase, active level 1 (S1) --- 14903Firing apply*operator 14904 --> 14905 (I3 ^predict-no N999 + :O ) 14906Firing apply*operator*complete 14907 --> 14908 (I3 ^predict-yes N998 - :O ) 14909 inner elaboration loop at bottom goal. 14910 --- Change Working Memory (PE) --- 14911=>WM: (14004: I3 ^predict-no N999) 14912<=WM: (13991: N998 ^status complete) 14913<=WM: (13990: I3 ^predict-yes N998) 14914 --- Firing Productions (IE) For State At Depth 1 --- 14915 14916--- Inner Elaboration Phase, active level 1 (S1) --- 14917Firing monitor*world 14918 --> 14919 14920I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 14921 --- Change Working Memory (IE) --- 14922 14923--- END Application Phase --- 14924--- Output Phase --- 14925ENV: Agent did: predict-no for direction L in state State-A 14926In State-A moving L 14927ENV: (next state, see, prediction correct?) = (State-A, 0, True) 14928predict error 0 14929dir: dir isU 14930--- END Output Phase --- 14931\-/--- Input Phase --- 14932=>WM: (14008: I2 ^dir U) 14933=>WM: (14007: I2 ^reward 1) 14934=>WM: (14006: I2 ^see 0) 14935=>WM: (14005: N999 ^status complete) 14936<=WM: (13994: I2 ^dir L) 14937<=WM: (13993: I2 ^reward 1) 14938<=WM: (13992: I2 ^see 1) 14939=>WM: (14009: I2 ^level-1 L0-root) 14940<=WM: (13995: I2 ^level-1 L1-root) 14941 14942--- END Input Phase --- 14943 14944--- Proposal Phase --- 14945 14946--- Inner Elaboration Phase, active level 1 (S1) --- 14947Firing elaborate*copy-see-to-output-link 14948 --> 14949 (I3 ^see 0 +) 14950Firing elaborate*reward*based*on*reward 14951 --> 14952 (R1003 ^value 1 +) 14953 (R1 ^reward R1003 +) 14954Firing propose*predict-yes 14955 --> 14956 (O1999 ^name predict-yes +) 14957 (S1 ^operator O1999 +) 14958Firing propose*predict-no 14959 --> 14960 (O2000 ^name predict-no +) 14961 (S1 ^operator O2000 +) 14962Firing rl*prefer*rvt*predict-no*H0*4 14963 --> 14964 (S1 ^operator O1998 = 1.) 14965Firing rl*prefer*rvt*predict-yes*H0*3 14966 --> 14967 (S1 ^operator O1997 = 0.) 14968Firing prefer*rvt*predict-yes*H0 14969 --> 14970Firing prefer*rvt*predict-no*H0 14971 --> 14972Firing elaborate*copy-dir-to-output-link 14973 --> 14974 (I3 ^dir U +) 14975 inner elaboration loop at bottom goal. 14976Retracting elaborate*copy-see-to-output-link 14977 --> 14978 (I3 ^see 1 +) 14979Retracting propose*predict-no 14980 --> 14981 (O1998 ^name predict-no +) 14982 (S1 ^operator O1998 +) 14983Retracting propose*predict-yes 14984 --> 14985 (O1997 ^name predict-yes +) 14986 (S1 ^operator O1997 +) 14987Retracting elaborate*reward*based*on*reward 14988 --> 14989 (R1002 ^value 1 +) 14990 (R1 ^reward R1002 +) 14991Retracting elaborate*copy-dir-to-output-link 14992 --> 14993 (I3 ^dir L +) 14994Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 14995 --> 14996 (S1 ^operator O1998 = 0.686145215235081) 14997Retracting rl*prefer*rvt*predict-no*H0*2 14998 --> 14999 (S1 ^operator O1998 = 0.3140233963466647) 15000Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 15001 --> 15002 (S1 ^operator O1997 = -0.3470159027404986) 15003Retracting rl*prefer*rvt*predict-yes*H0*1 15004 --> 15005 (S1 ^operator O1997 = 0.3804165454412648) 15006=>WM: (14017: S1 ^operator O2000 +) 15007=>WM: (14016: S1 ^operator O1999 +) 15008=>WM: (14015: I3 ^dir U) 15009=>WM: (14014: O2000 ^name predict-no) 15010=>WM: (14013: O1999 ^name predict-yes) 15011=>WM: (14012: R1003 ^value 1) 15012=>WM: (14011: R1 ^reward R1003) 15013=>WM: (14010: I3 ^see 0) 15014<=WM: (14001: S1 ^operator O1997 +) 15015<=WM: (14002: S1 ^operator O1998 +) 15016<=WM: (14003: S1 ^operator O1998) 15017<=WM: (13986: I3 ^dir L) 15018<=WM: (13997: R1 ^reward R1002) 15019<=WM: (13996: I3 ^see 1) 15020<=WM: (14000: O1998 ^name predict-no) 15021<=WM: (13999: O1997 ^name predict-yes) 15022<=WM: (13998: R1002 ^value 1) 15023 15024--- Inner Elaboration Phase, active level 1 (S1) --- 15025Firing prefer*rvt*predict-yes*H0 15026 --> 15027Firing rl*prefer*rvt*predict-yes*H0*3 15028 --> 15029 (S1 ^operator O1999 = 0.) 15030Firing prefer*rvt*predict-no*H0 15031 --> 15032Firing rl*prefer*rvt*predict-no*H0*4 15033 --> 15034 (S1 ^operator O2000 = 1.) 15035 inner elaboration loop at bottom goal. 15036Retracting rl*prefer*rvt*predict-no*H0*4 15037 --> 15038 (S1 ^operator O1998 = 1.) 15039Retracting rl*prefer*rvt*predict-yes*H0*3 15040 --> 15041 (S1 ^operator O1997 = 0.) 15042 15043--- END Proposal Phase --- 15044 15045--- Decision Phase --- 15046RL update rl*prefer*rvt*predict-no*H0*2 0.485033 -0.171009 0.314023 -> 0.485022 -0.171012 0.314009(R,m,v=1,0.860927,0.12053) 15047RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*36 0.5151 0.171045 0.686145 -> 0.515087 0.171042 0.686129(R,m,v=1,1,0) 15048=>WM: (14018: S1 ^operator O2000) 15049 15050 1000: O: O2000 (predict-no) 15051--- END Decision Phase --- 15052 15053--- Application Phase --- 15054 --- Firing Productions (PE) For State At Depth 1 --- 15055 15056--- Inner Elaboration Phase, active level 1 (S1) --- 15057Firing apply*operator 15058 --> 15059 (I3 ^predict-no N1000 + :O ) 15060Firing apply*operator*complete 15061 --> 15062 (I3 ^predict-no N999 - :O ) 15063 inner elaboration loop at bottom goal. 15064 --- Change Working Memory (PE) --- 15065=>WM: (14019: I3 ^predict-no N1000) 15066<=WM: (14005: N999 ^status complete) 15067<=WM: (14004: I3 ^predict-no N999) 15068 --- Firing Productions (IE) For State At Depth 1 --- 15069 15070--- Inner Elaboration Phase, active level 1 (S1) --- 15071Firing monitor*world 15072 --> 15073 15074I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 15075 --- Change Working Memory (IE) --- 15076 15077--- END Application Phase --- 15078--- Output Phase --- 15079ENV: Agent did: predict-no for direction U in state State-A 15080In State-A moving U 15081ENV: (next state, see, prediction correct?) = (State-A, 0, True) 15082predict error 0 15083dir: dir isR 15084--- END Output Phase --- 15085|\-/|\-/|\--- Input Phase --- 15086=>WM: (14023: I2 ^dir R) 15087=>WM: (14022: I2 ^reward 1) 15088=>WM: (14021: I2 ^see 0) 15089=>WM: (14020: N1000 ^status complete) 15090<=WM: (14008: I2 ^dir U) 15091<=WM: (14007: I2 ^reward 1) 15092<=WM: (14006: I2 ^see 0) 15093=>WM: (14024: I2 ^level-1 L0-root) 15094<=WM: (14009: I2 ^level-1 L0-root) 15095 15096--- END Input Phase --- 15097 15098--- Proposal Phase --- 15099 15100--- Inner Elaboration Phase, active level 1 (S1) --- 15101Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15102 --> 15103 (S1 ^operator O1999 = 0.7055034804752064) 15104Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15105 --> 15106 (S1 ^operator O2000 = -0.2023211881870005) 15107Firing prefer*rvt*predict-no*H0*6*v1*H1 15108 --> 15109Firing prefer*rvt*predict-yes*H0*5*v1*H1 15110 --> 15111Firing elaborate*copy-see-to-output-link 15112 --> 15113 (I3 ^see 0 +) 15114Firing elaborate*reward*based*on*reward 15115 --> 15116 (R1004 ^value 1 +) 15117 (R1 ^reward R1004 +) 15118Firing propose*predict-yes 15119 --> 15120 (O2001 ^name predict-yes +) 15121 (S1 ^operator O2001 +) 15122Firing propose*predict-no 15123 --> 15124 (O2002 ^name predict-no +) 15125 (S1 ^operator O2002 +) 15126Firing rl*prefer*rvt*predict-no*H0*6 15127 --> 15128 (S1 ^operator O2000 = 0.229854902707684) 15129Firing rl*prefer*rvt*predict-yes*H0*5 15130 --> 15131 (S1 ^operator O1999 = 0.2938705117203769) 15132Firing prefer*rvt*predict-yes*H0 15133 --> 15134Firing prefer*rvt*predict-no*H0 15135 --> 15136Firing elaborate*copy-dir-to-output-link 15137 --> 15138 (I3 ^dir R +) 15139 inner elaboration loop at bottom goal. 15140Retracting elaborate*copy-see-to-output-link 15141 --> 15142 (I3 ^see 0 +) 15143Retracting propose*predict-no 15144 --> 15145 (O2000 ^name predict-no +) 15146 (S1 ^operator O2000 +) 15147Retracting propose*predict-yes 15148 --> 15149 (O1999 ^name predict-yes +) 15150 (S1 ^operator O1999 +) 15151Retracting elaborate*reward*based*on*reward 15152 --> 15153 (R1003 ^value 1 +) 15154 (R1 ^reward R1003 +) 15155Retracting elaborate*copy-dir-to-output-link 15156 --> 15157 (I3 ^dir U +) 15158Retracting rl*prefer*rvt*predict-no*H0*4 15159 --> 15160 (S1 ^operator O2000 = 1.) 15161Retracting rl*prefer*rvt*predict-yes*H0*3 15162 --> 15163 (S1 ^operator O1999 = 0.) 15164=>WM: (14031: S1 ^operator O2002 +) 15165=>WM: (14030: S1 ^operator O2001 +) 15166=>WM: (14029: I3 ^dir R) 15167=>WM: (14028: O2002 ^name predict-no) 15168=>WM: (14027: O2001 ^name predict-yes) 15169=>WM: (14026: R1004 ^value 1) 15170=>WM: (14025: R1 ^reward R1004) 15171<=WM: (14016: S1 ^operator O1999 +) 15172<=WM: (14017: S1 ^operator O2000 +) 15173<=WM: (14018: S1 ^operator O2000) 15174<=WM: (14015: I3 ^dir U) 15175<=WM: (14011: R1 ^reward R1003) 15176<=WM: (14014: O2000 ^name predict-no) 15177<=WM: (14013: O1999 ^name predict-yes) 15178<=WM: (14012: R1003 ^value 1) 15179 15180--- Inner Elaboration Phase, active level 1 (S1) --- 15181Firing prefer*rvt*predict-yes*H0 15182 --> 15183Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15184 --> 15185 (S1 ^operator O2001 = 0.7055034804752064) 15186Firing rl*prefer*rvt*predict-yes*H0*5 15187 --> 15188 (S1 ^operator O2001 = 0.2938705117203769) 15189Firing prefer*rvt*predict-yes*H0*5*v1*H1 15190 --> 15191Firing prefer*rvt*predict-no*H0 15192 --> 15193Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15194 --> 15195 (S1 ^operator O2002 = -0.2023211881870005) 15196Firing rl*prefer*rvt*predict-no*H0*6 15197 --> 15198 (S1 ^operator O2002 = 0.229854902707684) 15199Firing prefer*rvt*predict-no*H0*6*v1*H1 15200 --> 15201 inner elaboration loop at bottom goal. 15202Retracting rl*prefer*rvt*predict-no*H0*6 15203 --> 15204 (S1 ^operator O2000 = 0.229854902707684) 15205Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15206 --> 15207 (S1 ^operator O2000 = -0.2023211881870005) 15208Retracting rl*prefer*rvt*predict-yes*H0*5 15209 --> 15210 (S1 ^operator O1999 = 0.2938705117203769) 15211Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15212 --> 15213 (S1 ^operator O1999 = 0.7055034804752064) 15214 15215--- END Proposal Phase --- 15216 15217--- Decision Phase --- 15218RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 15219=>WM: (14032: S1 ^operator O2001) 15220 15221 1001: O: O2001 (predict-yes) 15222--- END Decision Phase --- 15223 15224--- Application Phase --- 15225 --- Firing Productions (PE) For State At Depth 1 --- 15226 15227--- Inner Elaboration Phase, active level 1 (S1) --- 15228Firing apply*operator 15229 --> 15230 (I3 ^predict-yes N1001 + :O ) 15231Firing apply*operator*complete 15232 --> 15233 (I3 ^predict-no N1000 - :O ) 15234 inner elaboration loop at bottom goal. 15235 --- Change Working Memory (PE) --- 15236=>WM: (14033: I3 ^predict-yes N1001) 15237<=WM: (14020: N1000 ^status complete) 15238<=WM: (14019: I3 ^predict-no N1000) 15239 --- Firing Productions (IE) For State At Depth 1 --- 15240 15241--- Inner Elaboration Phase, active level 1 (S1) --- 15242Firing monitor*world 15243 --> 15244 15245I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 15246 --- Change Working Memory (IE) --- 15247 15248--- END Application Phase --- 15249--- Output Phase --- 15250ENV: Agent did: predict-yes for direction R in state State-A 15251In State-A moving R 15252ENV: (next state, see, prediction correct?) = (State-B, 1, True) 15253predict error 0 15254dir: dir isL 15255--- END Output Phase --- 15256---- Input Phase --- 15257=>WM: (14037: I2 ^dir L) 15258=>WM: (14036: I2 ^reward 1) 15259=>WM: (14035: I2 ^see 1) 15260=>WM: (14034: N1001 ^status complete) 15261<=WM: (14023: I2 ^dir R) 15262<=WM: (14022: I2 ^reward 1) 15263<=WM: (14021: I2 ^see 0) 15264=>WM: (14038: I2 ^level-1 R1-root) 15265<=WM: (14024: I2 ^level-1 L0-root) 15266 15267--- END Input Phase --- 15268 15269--- Proposal Phase --- 15270 15271--- Inner Elaboration Phase, active level 1 (S1) --- 15272Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 15273 --> 15274 (S1 ^operator O2001 = 0.6196100460529347) 15275Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 15276 --> 15277 (S1 ^operator O2002 = -0.1479504104026684) 15278Firing prefer*rvt*predict-no*H0*2*v1*H1 15279 --> 15280Firing prefer*rvt*predict-yes*H0*1*v1*H1 15281 --> 15282Firing elaborate*copy-see-to-output-link 15283 --> 15284 (I3 ^see 1 +) 15285Firing elaborate*reward*based*on*reward 15286 --> 15287 (R1005 ^value 1 +) 15288 (R1 ^reward R1005 +) 15289Firing propose*predict-yes 15290 --> 15291 (O2003 ^name predict-yes +) 15292 (S1 ^operator O2003 +) 15293Firing propose*predict-no 15294 --> 15295 (O2004 ^name predict-no +) 15296 (S1 ^operator O2004 +) 15297Firing rl*prefer*rvt*predict-no*H0*2 15298 --> 15299 (S1 ^operator O2002 = 0.3140093857317092) 15300Firing rl*prefer*rvt*predict-yes*H0*1 15301 --> 15302 (S1 ^operator O2001 = 0.3804165454412648) 15303Firing prefer*rvt*predict-yes*H0 15304 --> 15305Firing prefer*rvt*predict-no*H0 15306 --> 15307Firing elaborate*copy-dir-to-output-link 15308 --> 15309 (I3 ^dir L +) 15310 inner elaboration loop at bottom goal. 15311Retracting elaborate*copy-see-to-output-link 15312 --> 15313 (I3 ^see 0 +) 15314Retracting propose*predict-no 15315 --> 15316 (O2002 ^name predict-no +) 15317 (S1 ^operator O2002 +) 15318Retracting propose*predict-yes 15319 --> 15320 (O2001 ^name predict-yes +) 15321 (S1 ^operator O2001 +) 15322Retracting elaborate*reward*based*on*reward 15323 --> 15324 (R1004 ^value 1 +) 15325 (R1 ^reward R1004 +) 15326Retracting elaborate*copy-dir-to-output-link 15327 --> 15328 (I3 ^dir R +) 15329Retracting rl*prefer*rvt*predict-no*H0*6 15330 --> 15331 (S1 ^operator O2002 = 0.229854902707684) 15332Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15333 --> 15334 (S1 ^operator O2002 = -0.2023211881870005) 15335Retracting rl*prefer*rvt*predict-yes*H0*5 15336 --> 15337 (S1 ^operator O2001 = 0.2938705117203769) 15338Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15339 --> 15340 (S1 ^operator O2001 = 0.7055034804752064) 15341=>WM: (14046: S1 ^operator O2004 +) 15342=>WM: (14045: S1 ^operator O2003 +) 15343=>WM: (14044: I3 ^dir L) 15344=>WM: (14043: O2004 ^name predict-no) 15345=>WM: (14042: O2003 ^name predict-yes) 15346=>WM: (14041: R1005 ^value 1) 15347=>WM: (14040: R1 ^reward R1005) 15348=>WM: (14039: I3 ^see 1) 15349<=WM: (14030: S1 ^operator O2001 +) 15350<=WM: (14032: S1 ^operator O2001) 15351<=WM: (14031: S1 ^operator O2002 +) 15352<=WM: (14029: I3 ^dir R) 15353<=WM: (14025: R1 ^reward R1004) 15354<=WM: (14010: I3 ^see 0) 15355<=WM: (14028: O2002 ^name predict-no) 15356<=WM: (14027: O2001 ^name predict-yes) 15357<=WM: (14026: R1004 ^value 1) 15358 15359--- Inner Elaboration Phase, active level 1 (S1) --- 15360Firing prefer*rvt*predict-yes*H0 15361 --> 15362Firing rl*prefer*rvt*predict-yes*H0*1 15363 --> 15364 (S1 ^operator O2003 = 0.3804165454412648) 15365Firing prefer*rvt*predict-yes*H0*1*v1*H1 15366 --> 15367Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 15368 --> 15369 (S1 ^operator O2003 = 0.6196100460529347) 15370Firing prefer*rvt*predict-no*H0 15371 --> 15372Firing rl*prefer*rvt*predict-no*H0*2 15373 --> 15374 (S1 ^operator O2004 = 0.3140093857317092) 15375Firing prefer*rvt*predict-no*H0*2*v1*H1 15376 --> 15377Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*28 15378 --> 15379 (S1 ^operator O2004 = -0.1479504104026684) 15380 inner elaboration loop at bottom goal. 15381Retracting rl*prefer*rvt*predict-no*H0*2 15382 --> 15383 (S1 ^operator O2002 = 0.3140093857317092) 15384Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 15385 --> 15386 (S1 ^operator O2002 = -0.1479504104026684) 15387Retracting rl*prefer*rvt*predict-yes*H0*1 15388 --> 15389 (S1 ^operator O2001 = 0.3804165454412648) 15390Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 15391 --> 15392 (S1 ^operator O2001 = 0.6196100460529347) 15393 15394--- END Proposal Phase --- 15395 15396--- Decision Phase --- 15397RL update rl*prefer*rvt*predict-yes*H0*5 0.500957 -0.207086 0.293871 -> 0.501003 -0.207081 0.293922(R,m,v=1,0.846154,0.131017) 15398RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.498477 0.207026 0.705503 -> 0.498533 0.207032 0.705565(R,m,v=1,1,0) 15399=>WM: (14047: S1 ^operator O2003) 15400 15401 1002: O: O2003 (predict-yes) 15402--- END Decision Phase --- 15403 15404--- Application Phase --- 15405 --- Firing Productions (PE) For State At Depth 1 --- 15406 15407--- Inner Elaboration Phase, active level 1 (S1) --- 15408Firing apply*operator 15409 --> 15410 (I3 ^predict-yes N1002 + :O ) 15411Firing apply*operator*complete 15412 --> 15413 (I3 ^predict-yes N1001 - :O ) 15414 inner elaboration loop at bottom goal. 15415 --- Change Working Memory (PE) --- 15416=>WM: (14048: I3 ^predict-yes N1002) 15417<=WM: (14034: N1001 ^status complete) 15418<=WM: (14033: I3 ^predict-yes N1001) 15419 --- Firing Productions (IE) For State At Depth 1 --- 15420 15421--- Inner Elaboration Phase, active level 1 (S1) --- 15422Firing monitor*world 15423 --> 15424 15425I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 15426 --- Change Working Memory (IE) --- 15427 15428--- END Application Phase --- 15429--- Output Phase --- 15430ENV: Agent did: predict-yes for direction L in state State-B 15431In State-B moving L 15432ENV: (next state, see, prediction correct?) = (State-A, 1, True) 15433predict error 0 15434dir: dir isL 15435--- END Output Phase --- 15436/|\--- Input Phase --- 15437=>WM: (14052: I2 ^dir L) 15438=>WM: (14051: I2 ^reward 1) 15439=>WM: (14050: I2 ^see 1) 15440=>WM: (14049: N1002 ^status complete) 15441<=WM: (14037: I2 ^dir L) 15442<=WM: (14036: I2 ^reward 1) 15443<=WM: (14035: I2 ^see 1) 15444=>WM: (14053: I2 ^level-1 L1-root) 15445<=WM: (14038: I2 ^level-1 R1-root) 15446 15447--- END Input Phase --- 15448 15449--- Proposal Phase --- 15450 15451--- Inner Elaboration Phase, active level 1 (S1) --- 15452Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 15453 --> 15454 (S1 ^operator O2003 = -0.3470159027404986) 15455Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 15456 --> 15457 (S1 ^operator O2004 = 0.6861287198581429) 15458Firing prefer*rvt*predict-no*H0*2*v1*H1 15459 --> 15460Firing prefer*rvt*predict-yes*H0*1*v1*H1 15461 --> 15462Firing elaborate*copy-see-to-output-link 15463 --> 15464 (I3 ^see 1 +) 15465Firing elaborate*reward*based*on*reward 15466 --> 15467 (R1006 ^value 1 +) 15468 (R1 ^reward R1006 +) 15469Firing propose*predict-yes 15470 --> 15471 (O2005 ^name predict-yes +) 15472 (S1 ^operator O2005 +) 15473Firing propose*predict-no 15474 --> 15475 (O2006 ^name predict-no +) 15476 (S1 ^operator O2006 +) 15477Firing rl*prefer*rvt*predict-no*H0*2 15478 --> 15479 (S1 ^operator O2004 = 0.3140093857317092) 15480Firing rl*prefer*rvt*predict-yes*H0*1 15481 --> 15482 (S1 ^operator O2003 = 0.3804165454412648) 15483Firing prefer*rvt*predict-yes*H0 15484 --> 15485Firing prefer*rvt*predict-no*H0 15486 --> 15487Firing elaborate*copy-dir-to-output-link 15488 --> 15489 (I3 ^dir L +) 15490 inner elaboration loop at bottom goal. 15491Retracting elaborate*copy-see-to-output-link 15492 --> 15493 (I3 ^see 1 +) 15494Retracting propose*predict-no 15495 --> 15496 (O2004 ^name predict-no +) 15497 (S1 ^operator O2004 +) 15498Retracting propose*predict-yes 15499 --> 15500 (O2003 ^name predict-yes +) 15501 (S1 ^operator O2003 +) 15502Retracting elaborate*reward*based*on*reward 15503 --> 15504 (R1005 ^value 1 +) 15505 (R1 ^reward R1005 +) 15506Retracting elaborate*copy-dir-to-output-link 15507 --> 15508 (I3 ^dir L +) 15509Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*28 15510 --> 15511 (S1 ^operator O2004 = -0.1479504104026684) 15512Retracting rl*prefer*rvt*predict-no*H0*2 15513 --> 15514 (S1 ^operator O2004 = 0.3140093857317092) 15515Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 15516 --> 15517 (S1 ^operator O2003 = 0.6196100460529347) 15518Retracting rl*prefer*rvt*predict-yes*H0*1 15519 --> 15520 (S1 ^operator O2003 = 0.3804165454412648) 15521=>WM: (14059: S1 ^operator O2006 +) 15522=>WM: (14058: S1 ^operator O2005 +) 15523=>WM: (14057: O2006 ^name predict-no) 15524=>WM: (14056: O2005 ^name predict-yes) 15525=>WM: (14055: R1006 ^value 1) 15526=>WM: (14054: R1 ^reward R1006) 15527<=WM: (14045: S1 ^operator O2003 +) 15528<=WM: (14047: S1 ^operator O2003) 15529<=WM: (14046: S1 ^operator O2004 +) 15530<=WM: (14040: R1 ^reward R1005) 15531<=WM: (14043: O2004 ^name predict-no) 15532<=WM: (14042: O2003 ^name predict-yes) 15533<=WM: (14041: R1005 ^value 1) 15534 15535--- Inner Elaboration Phase, active level 1 (S1) --- 15536Firing prefer*rvt*predict-yes*H0 15537 --> 15538Firing rl*prefer*rvt*predict-yes*H0*1 15539 --> 15540 (S1 ^operator O2005 = 0.3804165454412648) 15541Firing prefer*rvt*predict-yes*H0*1*v1*H1 15542 --> 15543Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 15544 --> 15545 (S1 ^operator O2005 = -0.3470159027404986) 15546Firing prefer*rvt*predict-no*H0 15547 --> 15548Firing rl*prefer*rvt*predict-no*H0*2 15549 --> 15550 (S1 ^operator O2006 = 0.3140093857317092) 15551Firing prefer*rvt*predict-no*H0*2*v1*H1 15552 --> 15553Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*36 15554 --> 15555 (S1 ^operator O2006 = 0.6861287198581429) 15556 inner elaboration loop at bottom goal. 15557Retracting rl*prefer*rvt*predict-no*H0*2 15558 --> 15559 (S1 ^operator O2004 = 0.3140093857317092) 15560Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 15561 --> 15562 (S1 ^operator O2004 = 0.6861287198581429) 15563Retracting rl*prefer*rvt*predict-yes*H0*1 15564 --> 15565 (S1 ^operator O2003 = 0.3804165454412648) 15566Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 15567 --> 15568 (S1 ^operator O2003 = -0.3470159027404986) 15569 15570--- END Proposal Phase --- 15571 15572--- Decision Phase --- 15573RL update rl*prefer*rvt*predict-yes*H0*1 0.521347 -0.14093 0.380417 -> 0.521344 -0.14093 0.380414(R,m,v=1,0.831325,0.141073) 15574RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*29 0.478682 0.140928 0.61961 -> 0.47868 0.140928 0.619607(R,m,v=1,1,0) 15575=>WM: (14060: S1 ^operator O2006) 15576 15577 1003: O: O2006 (predict-no) 15578--- END Decision Phase --- 15579 15580--- Application Phase --- 15581 --- Firing Productions (PE) For State At Depth 1 --- 15582 15583--- Inner Elaboration Phase, active level 1 (S1) --- 15584Firing apply*operator 15585 --> 15586 (I3 ^predict-no N1003 + :O ) 15587Firing apply*operator*complete 15588 --> 15589 (I3 ^predict-yes N1002 - :O ) 15590 inner elaboration loop at bottom goal. 15591 --- Change Working Memory (PE) --- 15592=>WM: (14061: I3 ^predict-no N1003) 15593<=WM: (14049: N1002 ^status complete) 15594<=WM: (14048: I3 ^predict-yes N1002) 15595 --- Firing Productions (IE) For State At Depth 1 --- 15596 15597--- Inner Elaboration Phase, active level 1 (S1) --- 15598Firing monitor*world 15599 --> 15600 15601I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 15602 --- Change Working Memory (IE) --- 15603 15604--- END Application Phase --- 15605--- Output Phase --- 15606ENV: Agent did: predict-no for direction L in state State-A 15607In State-A moving L 15608ENV: (next state, see, prediction correct?) = (State-A, 0, True) 15609predict error 0 15610dir: dir isR 15611--- END Output Phase --- 15612-/--- Input Phase --- 15613=>WM: (14065: I2 ^dir R) 15614=>WM: (14064: I2 ^reward 1) 15615=>WM: (14063: I2 ^see 0) 15616=>WM: (14062: N1003 ^status complete) 15617<=WM: (14052: I2 ^dir L) 15618<=WM: (14051: I2 ^reward 1) 15619<=WM: (14050: I2 ^see 1) 15620=>WM: (14066: I2 ^level-1 L0-root) 15621<=WM: (14053: I2 ^level-1 L1-root) 15622 15623--- END Input Phase --- 15624 15625--- Proposal Phase --- 15626 15627--- Inner Elaboration Phase, active level 1 (S1) --- 15628Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15629 --> 15630 (S1 ^operator O2005 = 0.7055651252992311) 15631Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15632 --> 15633 (S1 ^operator O2006 = -0.2023211881870005) 15634Firing prefer*rvt*predict-no*H0*6*v1*H1 15635 --> 15636Firing prefer*rvt*predict-yes*H0*5*v1*H1 15637 --> 15638Firing elaborate*copy-see-to-output-link 15639 --> 15640 (I3 ^see 0 +) 15641Firing elaborate*reward*based*on*reward 15642 --> 15643 (R1007 ^value 1 +) 15644 (R1 ^reward R1007 +) 15645Firing propose*predict-yes 15646 --> 15647 (O2007 ^name predict-yes +) 15648 (S1 ^operator O2007 +) 15649Firing propose*predict-no 15650 --> 15651 (O2008 ^name predict-no +) 15652 (S1 ^operator O2008 +) 15653Firing rl*prefer*rvt*predict-no*H0*6 15654 --> 15655 (S1 ^operator O2006 = 0.229854902707684) 15656Firing rl*prefer*rvt*predict-yes*H0*5 15657 --> 15658 (S1 ^operator O2005 = 0.2939222491339341) 15659Firing prefer*rvt*predict-yes*H0 15660 --> 15661Firing prefer*rvt*predict-no*H0 15662 --> 15663Firing elaborate*copy-dir-to-output-link 15664 --> 15665 (I3 ^dir R +) 15666 inner elaboration loop at bottom goal. 15667Retracting elaborate*copy-see-to-output-link 15668 --> 15669 (I3 ^see 1 +) 15670Retracting propose*predict-no 15671 --> 15672 (O2006 ^name predict-no +) 15673 (S1 ^operator O2006 +) 15674Retracting propose*predict-yes 15675 --> 15676 (O2005 ^name predict-yes +) 15677 (S1 ^operator O2005 +) 15678Retracting elaborate*reward*based*on*reward 15679 --> 15680 (R1006 ^value 1 +) 15681 (R1 ^reward R1006 +) 15682Retracting elaborate*copy-dir-to-output-link 15683 --> 15684 (I3 ^dir L +) 15685Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*36 15686 --> 15687 (S1 ^operator O2006 = 0.6861287198581429) 15688Retracting rl*prefer*rvt*predict-no*H0*2 15689 --> 15690 (S1 ^operator O2006 = 0.3140093857317092) 15691Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*37 15692 --> 15693 (S1 ^operator O2005 = -0.3470159027404986) 15694Retracting rl*prefer*rvt*predict-yes*H0*1 15695 --> 15696 (S1 ^operator O2005 = 0.380414370085626) 15697=>WM: (14074: S1 ^operator O2008 +) 15698=>WM: (14073: S1 ^operator O2007 +) 15699=>WM: (14072: I3 ^dir R) 15700=>WM: (14071: O2008 ^name predict-no) 15701=>WM: (14070: O2007 ^name predict-yes) 15702=>WM: (14069: R1007 ^value 1) 15703=>WM: (14068: R1 ^reward R1007) 15704=>WM: (14067: I3 ^see 0) 15705<=WM: (14058: S1 ^operator O2005 +) 15706<=WM: (14059: S1 ^operator O2006 +) 15707<=WM: (14060: S1 ^operator O2006) 15708<=WM: (14044: I3 ^dir L) 15709<=WM: (14054: R1 ^reward R1006) 15710<=WM: (14039: I3 ^see 1) 15711<=WM: (14057: O2006 ^name predict-no) 15712<=WM: (14056: O2005 ^name predict-yes) 15713<=WM: (14055: R1006 ^value 1) 15714 15715--- Inner Elaboration Phase, active level 1 (S1) --- 15716Firing prefer*rvt*predict-yes*H0 15717 --> 15718Firing rl*prefer*rvt*predict-yes*H0*5 15719 --> 15720 (S1 ^operator O2007 = 0.2939222491339341) 15721Firing prefer*rvt*predict-yes*H0*5*v1*H1 15722 --> 15723Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15724 --> 15725 (S1 ^operator O2007 = 0.7055651252992311) 15726Firing prefer*rvt*predict-no*H0 15727 --> 15728Firing rl*prefer*rvt*predict-no*H0*6 15729 --> 15730 (S1 ^operator O2008 = 0.229854902707684) 15731Firing prefer*rvt*predict-no*H0*6*v1*H1 15732 --> 15733Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15734 --> 15735 (S1 ^operator O2008 = -0.2023211881870005) 15736 inner elaboration loop at bottom goal. 15737Retracting rl*prefer*rvt*predict-no*H0*6 15738 --> 15739 (S1 ^operator O2006 = 0.229854902707684) 15740Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15741 --> 15742 (S1 ^operator O2006 = -0.2023211881870005) 15743Retracting rl*prefer*rvt*predict-yes*H0*5 15744 --> 15745 (S1 ^operator O2005 = 0.2939222491339341) 15746Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15747 --> 15748 (S1 ^operator O2005 = 0.7055651252992311) 15749 15750--- END Proposal Phase --- 15751 15752--- Decision Phase --- 15753RL update rl*prefer*rvt*predict-no*H0*2 0.485022 -0.171012 0.314009 -> 0.485013 -0.171015 0.313998(R,m,v=1,0.861842,0.119859) 15754RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*36 0.515087 0.171042 0.686129 -> 0.515077 0.171039 0.686115(R,m,v=1,1,0) 15755=>WM: (14075: S1 ^operator O2007) 15756 15757 1004: O: O2007 (predict-yes) 15758--- END Decision Phase --- 15759 15760--- Application Phase --- 15761 --- Firing Productions (PE) For State At Depth 1 --- 15762 15763--- Inner Elaboration Phase, active level 1 (S1) --- 15764Firing apply*operator 15765 --> 15766 (I3 ^predict-yes N1004 + :O ) 15767Firing apply*operator*complete 15768 --> 15769 (I3 ^predict-no N1003 - :O ) 15770 inner elaboration loop at bottom goal. 15771 --- Change Working Memory (PE) --- 15772=>WM: (14076: I3 ^predict-yes N1004) 15773<=WM: (14062: N1003 ^status complete) 15774<=WM: (14061: I3 ^predict-no N1003) 15775 --- Firing Productions (IE) For State At Depth 1 --- 15776 15777--- Inner Elaboration Phase, active level 1 (S1) --- 15778Firing monitor*world 15779 --> 15780 15781I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal. 15782 --- Change Working Memory (IE) --- 15783 15784--- END Application Phase --- 15785--- Output Phase --- 15786ENV: Agent did: predict-yes for direction R in state State-A 15787In State-A moving R 15788ENV: (next state, see, prediction correct?) = (State-B, 1, True) 15789predict error 0 15790dir: dir isR 15791--- END Output Phase --- 15792|\---- Input Phase --- 15793=>WM: (14080: I2 ^dir R) 15794=>WM: (14079: I2 ^reward 1) 15795=>WM: (14078: I2 ^see 1) 15796=>WM: (14077: N1004 ^status complete) 15797<=WM: (14065: I2 ^dir R) 15798<=WM: (14064: I2 ^reward 1) 15799<=WM: (14063: I2 ^see 0) 15800=>WM: (14081: I2 ^level-1 R1-root) 15801<=WM: (14066: I2 ^level-1 L0-root) 15802 15803--- END Input Phase --- 15804 15805--- Proposal Phase --- 15806 15807--- Inner Elaboration Phase, active level 1 (S1) --- 15808Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 15809 --> 15810 (S1 ^operator O2007 = -0.252585164213872) 15811Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 15812 --> 15813 (S1 ^operator O2008 = 0.7701760437619466) 15814Firing prefer*rvt*predict-no*H0*6*v1*H1 15815 --> 15816Firing prefer*rvt*predict-yes*H0*5*v1*H1 15817 --> 15818Firing elaborate*copy-see-to-output-link 15819 --> 15820 (I3 ^see 1 +) 15821Firing elaborate*reward*based*on*reward 15822 --> 15823 (R1008 ^value 1 +) 15824 (R1 ^reward R1008 +) 15825Firing propose*predict-yes 15826 --> 15827 (O2009 ^name predict-yes +) 15828 (S1 ^operator O2009 +) 15829Firing propose*predict-no 15830 --> 15831 (O2010 ^name predict-no +) 15832 (S1 ^operator O2010 +) 15833Firing rl*prefer*rvt*predict-no*H0*6 15834 --> 15835 (S1 ^operator O2008 = 0.229854902707684) 15836Firing rl*prefer*rvt*predict-yes*H0*5 15837 --> 15838 (S1 ^operator O2007 = 0.2939222491339341) 15839Firing prefer*rvt*predict-yes*H0 15840 --> 15841Firing prefer*rvt*predict-no*H0 15842 --> 15843Firing elaborate*copy-dir-to-output-link 15844 --> 15845 (I3 ^dir R +) 15846 inner elaboration loop at bottom goal. 15847Retracting elaborate*copy-see-to-output-link 15848 --> 15849 (I3 ^see 0 +) 15850Retracting propose*predict-no 15851 --> 15852 (O2008 ^name predict-no +) 15853 (S1 ^operator O2008 +) 15854Retracting propose*predict-yes 15855 --> 15856 (O2007 ^name predict-yes +) 15857 (S1 ^operator O2007 +) 15858Retracting elaborate*reward*based*on*reward 15859 --> 15860 (R1007 ^value 1 +) 15861 (R1 ^reward R1007 +) 15862Retracting elaborate*copy-dir-to-output-link 15863 --> 15864 (I3 ^dir R +) 15865Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*40 15866 --> 15867 (S1 ^operator O2008 = -0.2023211881870005) 15868Retracting rl*prefer*rvt*predict-no*H0*6 15869 --> 15870 (S1 ^operator O2008 = 0.229854902707684) 15871Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 15872 --> 15873 (S1 ^operator O2007 = 0.7055651252992311) 15874Retracting rl*prefer*rvt*predict-yes*H0*5 15875 --> 15876 (S1 ^operator O2007 = 0.2939222491339341) 15877=>WM: (14088: S1 ^operator O2010 +) 15878=>WM: (14087: S1 ^operator O2009 +) 15879=>WM: (14086: O2010 ^name predict-no) 15880=>WM: (14085: O2009 ^name predict-yes) 15881=>WM: (14084: R1008 ^value 1) 15882=>WM: (14083: R1 ^reward R1008) 15883=>WM: (14082: I3 ^see 1) 15884<=WM: (14073: S1 ^operator O2007 +) 15885<=WM: (14075: S1 ^operator O2007) 15886<=WM: (14074: S1 ^operator O2008 +) 15887<=WM: (14068: R1 ^reward R1007) 15888<=WM: (14067: I3 ^see 0) 15889<=WM: (14071: O2008 ^name predict-no) 15890<=WM: (14070: O2007 ^name predict-yes) 15891<=WM: (14069: R1007 ^value 1) 15892 15893--- Inner Elaboration Phase, active level 1 (S1) --- 15894Firing prefer*rvt*predict-yes*H0 15895 --> 15896Firing rl*prefer*rvt*predict-yes*H0*5 15897 --> 15898 (S1 ^operator O2009 = 0.2939222491339341) 15899Firing prefer*rvt*predict-yes*H0*5*v1*H1 15900 --> 15901Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 15902 --> 15903 (S1 ^operator O2009 = -0.252585164213872) 15904Firing prefer*rvt*predict-no*H0 15905 --> 15906Firing rl*prefer*rvt*predict-no*H0*6 15907 --> 15908 (S1 ^operator O2010 = 0.229854902707684) 15909Firing prefer*rvt*predict-no*H0*6*v1*H1 15910 --> 15911Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*30 15912 --> 15913 (S1 ^operator O2010 = 0.7701760437619466) 15914 inner elaboration loop at bottom goal. 15915Retracting rl*prefer*rvt*predict-no*H0*6 15916 --> 15917 (S1 ^operator O2008 = 0.229854902707684) 15918Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 15919 --> 15920 (S1 ^operator O2008 = 0.7701760437619466) 15921Retracting rl*prefer*rvt*predict-yes*H0*5 15922 --> 15923 (S1 ^operator O2007 = 0.2939222491339341) 15924Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 15925 --> 15926 (S1 ^operator O2007 = -0.252585164213872) 15927 15928--- END Proposal Phase --- 15929 15930--- Decision Phase --- 15931RL update rl*prefer*rvt*predict-yes*H0*5 0.501003 -0.207081 0.293922 -> 0.501042 -0.207077 0.293965(R,m,v=1,0.847134,0.130328) 15932RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.498533 0.207032 0.705565 -> 0.498578 0.207037 0.705615(R,m,v=1,1,0) 15933=>WM: (14089: S1 ^operator O2010) 15934 15935 1005: O: O2010 (predict-no) 15936--- END Decision Phase --- 15937 15938--- Application Phase --- 15939 --- Firing Productions (PE) For State At Depth 1 --- 15940 15941--- Inner Elaboration Phase, active level 1 (S1) --- 15942Firing apply*operator 15943 --> 15944 (I3 ^predict-no N1005 + :O ) 15945Firing apply*operator*complete 15946 --> 15947 (I3 ^predict-yes N1004 - :O ) 15948 inner elaboration loop at bottom goal. 15949 --- Change Working Memory (PE) --- 15950=>WM: (14090: I3 ^predict-no N1005) 15951<=WM: (14077: N1004 ^status complete) 15952<=WM: (14076: I3 ^predict-yes N1004) 15953 --- Firing Productions (IE) For State At Depth 1 --- 15954 15955--- Inner Elaboration Phase, active level 1 (S1) --- 15956Firing monitor*world 15957 --> 15958 15959I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 15960 --- Change Working Memory (IE) --- 15961 15962--- END Application Phase --- 15963--- Output Phase --- 15964ENV: Agent did: predict-no for direction R in state State-B 15965In State-B moving R 15966ENV: (next state, see, prediction correct?) = (State-B, 0, True) 15967predict error 0 15968dir: dir isU 15969--- END Output Phase --- 15970/|--- Input Phase --- 15971=>WM: (14094: I2 ^dir U) 15972=>WM: (14093: I2 ^reward 1) 15973=>WM: (14092: I2 ^see 0) 15974=>WM: (14091: N1005 ^status complete) 15975<=WM: (14080: I2 ^dir R) 15976<=WM: (14079: I2 ^reward 1) 15977<=WM: (14078: I2 ^see 1) 15978=>WM: (14095: I2 ^level-1 R0-root) 15979<=WM: (14081: I2 ^level-1 R1-root) 15980 15981--- END Input Phase --- 15982 15983--- Proposal Phase --- 15984 15985--- Inner Elaboration Phase, active level 1 (S1) --- 15986Firing elaborate*copy-see-to-output-link 15987 --> 15988 (I3 ^see 0 +) 15989Firing elaborate*reward*based*on*reward 15990 --> 15991 (R1009 ^value 1 +) 15992 (R1 ^reward R1009 +) 15993Firing propose*predict-yes 15994 --> 15995 (O2011 ^name predict-yes +) 15996 (S1 ^operator O2011 +) 15997Firing propose*predict-no 15998 --> 15999 (O2012 ^name predict-no +) 16000 (S1 ^operator O2012 +) 16001Firing rl*prefer*rvt*predict-no*H0*4 16002 --> 16003 (S1 ^operator O2010 = 1.) 16004Firing rl*prefer*rvt*predict-yes*H0*3 16005 --> 16006 (S1 ^operator O2009 = 0.) 16007Firing prefer*rvt*predict-yes*H0 16008 --> 16009Firing prefer*rvt*predict-no*H0 16010 --> 16011Firing elaborate*copy-dir-to-output-link 16012 --> 16013 (I3 ^dir U +) 16014 inner elaboration loop at bottom goal. 16015Retracting elaborate*copy-see-to-output-link 16016 --> 16017 (I3 ^see 1 +) 16018Retracting propose*predict-no 16019 --> 16020 (O2010 ^name predict-no +) 16021 (S1 ^operator O2010 +) 16022Retracting propose*predict-yes 16023 --> 16024 (O2009 ^name predict-yes +) 16025 (S1 ^operator O2009 +) 16026Retracting elaborate*reward*based*on*reward 16027 --> 16028 (R1008 ^value 1 +) 16029 (R1 ^reward R1008 +) 16030Retracting elaborate*copy-dir-to-output-link 16031 --> 16032 (I3 ^dir R +) 16033Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*30 16034 --> 16035 (S1 ^operator O2010 = 0.7701760437619466) 16036Retracting rl*prefer*rvt*predict-no*H0*6 16037 --> 16038 (S1 ^operator O2010 = 0.229854902707684) 16039Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31 16040 --> 16041 (S1 ^operator O2009 = -0.252585164213872) 16042Retracting rl*prefer*rvt*predict-yes*H0*5 16043 --> 16044 (S1 ^operator O2009 = 0.2939645711914686) 16045=>WM: (14103: S1 ^operator O2012 +) 16046=>WM: (14102: S1 ^operator O2011 +) 16047=>WM: (14101: I3 ^dir U) 16048=>WM: (14100: O2012 ^name predict-no) 16049=>WM: (14099: O2011 ^name predict-yes) 16050=>WM: (14098: R1009 ^value 1) 16051=>WM: (14097: R1 ^reward R1009) 16052=>WM: (14096: I3 ^see 0) 16053<=WM: (14087: S1 ^operator O2009 +) 16054<=WM: (14088: S1 ^operator O2010 +) 16055<=WM: (14089: S1 ^operator O2010) 16056<=WM: (14072: I3 ^dir R) 16057<=WM: (14083: R1 ^reward R1008) 16058<=WM: (14082: I3 ^see 1) 16059<=WM: (14086: O2010 ^name predict-no) 16060<=WM: (14085: O2009 ^name predict-yes) 16061<=WM: (14084: R1008 ^value 1) 16062 16063--- Inner Elaboration Phase, active level 1 (S1) --- 16064Firing prefer*rvt*predict-yes*H0 16065 --> 16066Firing rl*prefer*rvt*predict-yes*H0*3 16067 --> 16068 (S1 ^operator O2011 = 0.) 16069Firing prefer*rvt*predict-no*H0 16070 --> 16071Firing rl*prefer*rvt*predict-no*H0*4 16072 --> 16073 (S1 ^operator O2012 = 1.) 16074 inner elaboration loop at bottom goal. 16075Retracting rl*prefer*rvt*predict-no*H0*4 16076 --> 16077 (S1 ^operator O2010 = 1.) 16078Retracting rl*prefer*rvt*predict-yes*H0*3 16079 --> 16080 (S1 ^operator O2009 = 0.) 16081 16082--- END Proposal Phase --- 16083 16084--- Decision Phase --- 16085RL update rl*prefer*rvt*predict-no*H0*6 0.611908 -0.382053 0.229855 -> 0.611906 -0.382053 0.229852(R,m,v=1,0.846591,0.130617) 16086RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*30 0.388117 0.382059 0.770176 -> 0.388115 0.382058 0.770173(R,m,v=1,1,0) 16087=>WM: (14104: S1 ^operator O2012) 16088 16089 1006: O: O2012 (predict-no) 16090--- END Decision Phase --- 16091 16092--- Application Phase --- 16093 --- Firing Productions (PE) For State At Depth 1 --- 16094 16095--- Inner Elaboration Phase, active level 1 (S1) --- 16096Firing apply*operator 16097 --> 16098 (I3 ^predict-no N1006 + :O ) 16099Firing apply*operator*complete 16100 --> 16101 (I3 ^predict-no N1005 - :O ) 16102 inner elaboration loop at bottom goal. 16103 --- Change Working Memory (PE) --- 16104=>WM: (14105: I3 ^predict-no N1006) 16105<=WM: (14091: N1005 ^status complete) 16106<=WM: (14090: I3 ^predict-no N1005) 16107 --- Firing Productions (IE) For State At Depth 1 --- 16108 16109--- Inner Elaboration Phase, active level 1 (S1) --- 16110Firing monitor*world 16111 --> 16112 16113I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 16114 --- Change Working Memory (IE) --- 16115 16116--- END Application Phase --- 16117--- Output Phase --- 16118ENV: Agent did: predict-no for direction U in state State-B 16119In State-B moving U 16120ENV: (next state, see, prediction correct?) = (State-B, 0, True) 16121predict error 0 16122dir: dir isR 16123--- END Output Phase --- 16124\-/--- Input Phase --- 16125=>WM: (14109: I2 ^dir R) 16126=>WM: (14108: I2 ^reward 1) 16127=>WM: (14107: I2 ^see 0) 16128=>WM: (14106: N1006 ^status complete) 16129<=WM: (14094: I2 ^dir U) 16130<=WM: (14093: I2 ^reward 1) 16131<=WM: (14092: I2 ^see 0) 16132=>WM: (14110: I2 ^level-1 R0-root) 16133<=WM: (14095: I2 ^level-1 R0-root) 16134 16135--- END Input Phase --- 16136 16137--- Proposal Phase --- 16138 16139--- Inner Elaboration Phase, active level 1 (S1) --- 16140Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16141 --> 16142 (S1 ^operator O2011 = -0.1254042659579056) 16143Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16144 --> 16145 (S1 ^operator O2012 = 0.7700907188039023) 16146Firing prefer*rvt*predict-no*H0*6*v1*H1 16147 --> 16148Firing prefer*rvt*predict-yes*H0*5*v1*H1 16149 --> 16150Firing elaborate*copy-see-to-output-link 16151 --> 16152 (I3 ^see 0 +) 16153Firing elaborate*reward*based*on*reward 16154 --> 16155 (R1010 ^value 1 +) 16156 (R1 ^reward R1010 +) 16157Firing propose*predict-yes 16158 --> 16159 (O2013 ^name predict-yes +) 16160 (S1 ^operator O2013 +) 16161Firing propose*predict-no 16162 --> 16163 (O2014 ^name predict-no +) 16164 (S1 ^operator O2014 +) 16165Firing rl*prefer*rvt*predict-no*H0*6 16166 --> 16167 (S1 ^operator O2012 = 0.2298523950867538) 16168Firing rl*prefer*rvt*predict-yes*H0*5 16169 --> 16170 (S1 ^operator O2011 = 0.2939645711914686) 16171Firing prefer*rvt*predict-yes*H0 16172 --> 16173Firing prefer*rvt*predict-no*H0 16174 --> 16175Firing elaborate*copy-dir-to-output-link 16176 --> 16177 (I3 ^dir R +) 16178 inner elaboration loop at bottom goal. 16179Retracting elaborate*copy-see-to-output-link 16180 --> 16181 (I3 ^see 0 +) 16182Retracting propose*predict-no 16183 --> 16184 (O2012 ^name predict-no +) 16185 (S1 ^operator O2012 +) 16186Retracting propose*predict-yes 16187 --> 16188 (O2011 ^name predict-yes +) 16189 (S1 ^operator O2011 +) 16190Retracting elaborate*reward*based*on*reward 16191 --> 16192 (R1009 ^value 1 +) 16193 (R1 ^reward R1009 +) 16194Retracting elaborate*copy-dir-to-output-link 16195 --> 16196 (I3 ^dir U +) 16197Retracting rl*prefer*rvt*predict-no*H0*4 16198 --> 16199 (S1 ^operator O2012 = 1.) 16200Retracting rl*prefer*rvt*predict-yes*H0*3 16201 --> 16202 (S1 ^operator O2011 = 0.) 16203=>WM: (14117: S1 ^operator O2014 +) 16204=>WM: (14116: S1 ^operator O2013 +) 16205=>WM: (14115: I3 ^dir R) 16206=>WM: (14114: O2014 ^name predict-no) 16207=>WM: (14113: O2013 ^name predict-yes) 16208=>WM: (14112: R1010 ^value 1) 16209=>WM: (14111: R1 ^reward R1010) 16210<=WM: (14102: S1 ^operator O2011 +) 16211<=WM: (14103: S1 ^operator O2012 +) 16212<=WM: (14104: S1 ^operator O2012) 16213<=WM: (14101: I3 ^dir U) 16214<=WM: (14097: R1 ^reward R1009) 16215<=WM: (14100: O2012 ^name predict-no) 16216<=WM: (14099: O2011 ^name predict-yes) 16217<=WM: (14098: R1009 ^value 1) 16218 16219--- Inner Elaboration Phase, active level 1 (S1) --- 16220Firing prefer*rvt*predict-yes*H0 16221 --> 16222Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16223 --> 16224 (S1 ^operator O2013 = -0.1254042659579056) 16225Firing rl*prefer*rvt*predict-yes*H0*5 16226 --> 16227 (S1 ^operator O2013 = 0.2939645711914686) 16228Firing prefer*rvt*predict-yes*H0*5*v1*H1 16229 --> 16230Firing prefer*rvt*predict-no*H0 16231 --> 16232Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16233 --> 16234 (S1 ^operator O2014 = 0.7700907188039023) 16235Firing rl*prefer*rvt*predict-no*H0*6 16236 --> 16237 (S1 ^operator O2014 = 0.2298523950867538) 16238Firing prefer*rvt*predict-no*H0*6*v1*H1 16239 --> 16240 inner elaboration loop at bottom goal. 16241Retracting rl*prefer*rvt*predict-no*H0*6 16242 --> 16243 (S1 ^operator O2012 = 0.2298523950867538) 16244Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16245 --> 16246 (S1 ^operator O2012 = 0.7700907188039023) 16247Retracting rl*prefer*rvt*predict-yes*H0*5 16248 --> 16249 (S1 ^operator O2011 = 0.2939645711914686) 16250Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16251 --> 16252 (S1 ^operator O2011 = -0.1254042659579056) 16253 16254--- END Proposal Phase --- 16255 16256--- Decision Phase --- 16257RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0) 16258=>WM: (14118: S1 ^operator O2014) 16259 16260 1007: O: O2014 (predict-no) 16261--- END Decision Phase --- 16262 16263--- Application Phase --- 16264 --- Firing Productions (PE) For State At Depth 1 --- 16265 16266--- Inner Elaboration Phase, active level 1 (S1) --- 16267Firing apply*operator 16268 --> 16269 (I3 ^predict-no N1007 + :O ) 16270Firing apply*operator*complete 16271 --> 16272 (I3 ^predict-no N1006 - :O ) 16273 inner elaboration loop at bottom goal. 16274 --- Change Working Memory (PE) --- 16275=>WM: (14119: I3 ^predict-no N1007) 16276<=WM: (14106: N1006 ^status complete) 16277<=WM: (14105: I3 ^predict-no N1006) 16278 --- Firing Productions (IE) For State At Depth 1 --- 16279 16280--- Inner Elaboration Phase, active level 1 (S1) --- 16281Firing monitor*world 16282 --> 16283 16284I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal. 16285 --- Change Working Memory (IE) --- 16286 16287--- END Application Phase --- 16288--- Output Phase --- 16289ENV: Agent did: predict-no for direction R in state State-B 16290In State-B moving R 16291ENV: (next state, see, prediction correct?) = (State-B, 0, True) 16292predict error 0 16293dir: dir isR 16294--- END Output Phase --- 16295|\---- Input Phase --- 16296=>WM: (14123: I2 ^dir R) 16297=>WM: (14122: I2 ^reward 1) 16298=>WM: (14121: I2 ^see 0) 16299=>WM: (14120: N1007 ^status complete) 16300<=WM: (14109: I2 ^dir R) 16301<=WM: (14108: I2 ^reward 1) 16302<=WM: (14107: I2 ^see 0) 16303=>WM: (14124: I2 ^level-1 R0-root) 16304<=WM: (14110: I2 ^level-1 R0-root) 16305 16306--- END Input Phase --- 16307 16308--- Proposal Phase --- 16309 16310--- Inner Elaboration Phase, active level 1 (S1) --- 16311Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16312 --> 16313 (S1 ^operator O2013 = -0.1254042659579056) 16314Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16315 --> 16316 (S1 ^operator O2014 = 0.7700907188039023) 16317Firing prefer*rvt*predict-no*H0*6*v1*H1 16318 --> 16319Firing prefer*rvt*predict-yes*H0*5*v1*H1 16320 --> 16321Firing elaborate*copy-see-to-output-link 16322 --> 16323 (I3 ^see 0 +) 16324Firing elaborate*reward*based*on*reward 16325 --> 16326 (R1011 ^value 1 +) 16327 (R1 ^reward R1011 +) 16328Firing propose*predict-yes 16329 --> 16330 (O2015 ^name predict-yes +) 16331 (S1 ^operator O2015 +) 16332Firing propose*predict-no 16333 --> 16334 (O2016 ^name predict-no +) 16335 (S1 ^operator O2016 +) 16336Firing rl*prefer*rvt*predict-no*H0*6 16337 --> 16338 (S1 ^operator O2014 = 0.2298523950867538) 16339Firing rl*prefer*rvt*predict-yes*H0*5 16340 --> 16341 (S1 ^operator O2013 = 0.2939645711914686) 16342Firing prefer*rvt*predict-yes*H0 16343 --> 16344Firing prefer*rvt*predict-no*H0 16345 --> 16346Firing elaborate*copy-dir-to-output-link 16347 --> 16348 (I3 ^dir R +) 16349 inner elaboration loop at bottom goal. 16350Retracting elaborate*copy-see-to-output-link 16351 --> 16352 (I3 ^see 0 +) 16353Retracting propose*predict-no 16354 --> 16355 (O2014 ^name predict-no +) 16356 (S1 ^operator O2014 +) 16357Retracting propose*predict-yes 16358 --> 16359 (O2013 ^name predict-yes +) 16360 (S1 ^operator O2013 +) 16361Retracting elaborate*reward*based*on*reward 16362 --> 16363 (R1010 ^value 1 +) 16364 (R1 ^reward R1010 +) 16365Retracting elaborate*copy-dir-to-output-link 16366 --> 16367 (I3 ^dir R +) 16368Retracting rl*prefer*rvt*predict-no*H0*6 16369 --> 16370 (S1 ^operator O2014 = 0.2298523950867538) 16371Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16372 --> 16373 (S1 ^operator O2014 = 0.7700907188039023) 16374Retracting rl*prefer*rvt*predict-yes*H0*5 16375 --> 16376 (S1 ^operator O2013 = 0.2939645711914686) 16377Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16378 --> 16379 (S1 ^operator O2013 = -0.1254042659579056) 16380=>WM: (14130: S1 ^operator O2016 +) 16381=>WM: (14129: S1 ^operator O2015 +) 16382=>WM: (14128: O2016 ^name predict-no) 16383=>WM: (14127: O2015 ^name predict-yes) 16384=>WM: (14126: R1011 ^value 1) 16385=>WM: (14125: R1 ^reward R1011) 16386<=WM: (14116: S1 ^operator O2013 +) 16387<=WM: (14117: S1 ^operator O2014 +) 16388<=WM: (14118: S1 ^operator O2014) 16389<=WM: (14111: R1 ^reward R1010) 16390<=WM: (14114: O2014 ^name predict-no) 16391<=WM: (14113: O2013 ^name predict-yes) 16392<=WM: (14112: R1010 ^value 1) 16393 16394--- Inner Elaboration Phase, active level 1 (S1) --- 16395Firing prefer*rvt*predict-yes*H0 16396 --> 16397Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16398 --> 16399 (S1 ^operator O2015 = -0.1254042659579056) 16400Firing rl*prefer*rvt*predict-yes*H0*5 16401 --> 16402 (S1 ^operator O2015 = 0.2939645711914686) 16403Firing prefer*rvt*predict-yes*H0*5*v1*H1 16404 --> 16405Firing prefer*rvt*predict-no*H0 16406 --> 16407Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16408 --> 16409 (S1 ^operator O2016 = 0.7700907188039023) 16410Firing rl*prefer*rvt*predict-no*H0*6 16411 --> 16412 (S1 ^operator O2016 = 0.2298523950867538) 16413Firing prefer*rvt*predict-no*H0*6*v1*H1 16414 --> 16415 inner elaboration loop at bottom goal. 16416Retracting rl*prefer*rvt*predict-no*H0*6 16417 --> 16418 (S1 ^operator O2014 = 0.2298523950867538) 16419Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*32 16420 --> 16421 (S1 ^operator O2014 = 0.7700907188039023) 16422Retracting rl*prefer*rvt*predict-yes*H0*5 16423 --> 16424 (S1 ^operator O2013 = 0.2939645711914686) 16425Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*33 16426 --> 16427 (S1 ^operator O2013 = -0.1254042659579056) 16428 16429--- END Proposal Phase --- 16430 16431--- Decision Phase --- 16432RL update rl*prefer*rvt*predict-no*H0*6 0.611906 -0.382053 0.229852 -> 0.61191 -0.382053 0.229857(R,m,v=1,0.847458,0.130008) 16433RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*32 0.388048 0.382043 0.770091 -> 0.388052 0.382044 0.770096(R,m,v=1,1,0) 16434=>WM: (14131: S1 ^operator O2016) 16435 16436 1008: O: O2016 (predict-no) 16437--- END Decision Phase --- 16438 16439--- Application Phase --- 16440 --- Firing Productions (PE) For State At Depth 1 ---