File size: 142,391 Bytes
3d89bca |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 |
[2023-02-23 15:11:45,445][00417] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-23 15:11:45,449][00417] Rollout worker 0 uses device cpu [2023-02-23 15:11:45,450][00417] Rollout worker 1 uses device cpu [2023-02-23 15:11:45,452][00417] Rollout worker 2 uses device cpu [2023-02-23 15:11:45,453][00417] Rollout worker 3 uses device cpu [2023-02-23 15:11:45,454][00417] Rollout worker 4 uses device cpu [2023-02-23 15:11:45,456][00417] Rollout worker 5 uses device cpu [2023-02-23 15:11:45,457][00417] Rollout worker 6 uses device cpu [2023-02-23 15:11:45,458][00417] Rollout worker 7 uses device cpu [2023-02-23 15:11:45,655][00417] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:11:45,660][00417] InferenceWorker_p0-w0: min num requests: 2 [2023-02-23 15:11:45,691][00417] Starting all processes... [2023-02-23 15:11:45,693][00417] Starting process learner_proc0 [2023-02-23 15:11:45,751][00417] Starting all processes... [2023-02-23 15:11:45,761][00417] Starting process inference_proc0-0 [2023-02-23 15:11:45,762][00417] Starting process rollout_proc0 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc1 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc2 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc3 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc4 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc5 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc6 [2023-02-23 15:11:45,764][00417] Starting process rollout_proc7 [2023-02-23 15:11:52,642][00417] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 417], exiting... [2023-02-23 15:11:52,649][00417] Runner profile tree view: main_loop: 6.9587 [2023-02-23 15:11:52,660][00417] Collected {}, FPS: 0.0 [2023-02-23 15:11:53,956][00417] Environment doom_basic already registered, overwriting... [2023-02-23 15:11:53,960][00417] Environment doom_two_colors_easy already registered, overwriting... [2023-02-23 15:11:53,961][00417] Environment doom_two_colors_hard already registered, overwriting... [2023-02-23 15:11:53,965][00417] Environment doom_dm already registered, overwriting... [2023-02-23 15:11:53,967][00417] Environment doom_dwango5 already registered, overwriting... [2023-02-23 15:11:53,969][00417] Environment doom_my_way_home_flat_actions already registered, overwriting... [2023-02-23 15:11:53,970][00417] Environment doom_defend_the_center_flat_actions already registered, overwriting... [2023-02-23 15:11:53,971][00417] Environment doom_my_way_home already registered, overwriting... [2023-02-23 15:11:53,973][00417] Environment doom_deadly_corridor already registered, overwriting... [2023-02-23 15:11:53,976][00417] Environment doom_defend_the_center already registered, overwriting... [2023-02-23 15:11:53,978][00417] Environment doom_defend_the_line already registered, overwriting... [2023-02-23 15:11:53,990][00417] Environment doom_health_gathering already registered, overwriting... [2023-02-23 15:11:53,991][00417] Environment doom_health_gathering_supreme already registered, overwriting... [2023-02-23 15:11:53,996][00417] Environment doom_battle already registered, overwriting... [2023-02-23 15:11:53,998][00417] Environment doom_battle2 already registered, overwriting... [2023-02-23 15:11:54,002][00417] Environment doom_duel_bots already registered, overwriting... [2023-02-23 15:11:54,006][00417] Environment doom_deathmatch_bots already registered, overwriting... [2023-02-23 15:11:54,008][00417] Environment doom_duel already registered, overwriting... [2023-02-23 15:11:54,009][00417] Environment doom_deathmatch_full already registered, overwriting... [2023-02-23 15:11:54,010][00417] Environment doom_benchmark already registered, overwriting... [2023-02-23 15:11:54,012][00417] register_encoder_factory: <function make_vizdoom_encoder at 0x7fe011dce4c0> [2023-02-23 15:11:54,027][00417] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-23 15:11:54,035][00417] Experiment dir /content/train_dir/default_experiment already exists! [2023-02-23 15:11:54,038][00417] Resuming existing experiment from /content/train_dir/default_experiment... [2023-02-23 15:11:54,040][00417] Weights and Biases integration disabled [2023-02-23 15:11:54,046][00417] Environment var CUDA_VISIBLE_DEVICES is 0 [2023-02-23 15:12:24,016][11317] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-23 15:12:24,022][11317] Rollout worker 0 uses device cpu [2023-02-23 15:12:24,024][11317] Rollout worker 1 uses device cpu [2023-02-23 15:12:24,027][11317] Rollout worker 2 uses device cpu [2023-02-23 15:12:24,030][11317] Rollout worker 3 uses device cpu [2023-02-23 15:12:24,031][11317] Rollout worker 4 uses device cpu [2023-02-23 15:12:24,032][11317] Rollout worker 5 uses device cpu [2023-02-23 15:12:24,034][11317] Rollout worker 6 uses device cpu [2023-02-23 15:12:24,035][11317] Rollout worker 7 uses device cpu [2023-02-23 15:12:24,170][11317] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:12:24,172][11317] InferenceWorker_p0-w0: min num requests: 2 [2023-02-23 15:12:24,203][11317] Starting all processes... [2023-02-23 15:12:24,204][11317] Starting process learner_proc0 [2023-02-23 15:12:24,258][11317] Starting all processes... [2023-02-23 15:12:24,267][11317] Starting process inference_proc0-0 [2023-02-23 15:12:24,268][11317] Starting process rollout_proc0 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc1 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc2 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc3 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc4 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc5 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc6 [2023-02-23 15:12:24,270][11317] Starting process rollout_proc7 [2023-02-23 15:12:34,932][11456] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:12:34,933][11456] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-23 15:12:35,401][11477] Worker 6 uses CPU cores [0] [2023-02-23 15:12:35,499][11473] Worker 3 uses CPU cores [1] [2023-02-23 15:12:35,783][11471] Worker 0 uses CPU cores [0] [2023-02-23 15:12:35,932][11478] Worker 7 uses CPU cores [1] [2023-02-23 15:12:36,002][11476] Worker 5 uses CPU cores [1] [2023-02-23 15:12:36,007][11470] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:12:36,008][11470] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-23 15:12:36,086][11475] Worker 2 uses CPU cores [0] [2023-02-23 15:12:36,141][11474] Worker 4 uses CPU cores [0] [2023-02-23 15:12:36,230][11472] Worker 1 uses CPU cores [1] [2023-02-23 15:12:36,335][11470] Num visible devices: 1 [2023-02-23 15:12:36,335][11456] Num visible devices: 1 [2023-02-23 15:12:36,353][11456] Starting seed is not provided [2023-02-23 15:12:36,353][11456] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:12:36,354][11456] Initializing actor-critic model on device cuda:0 [2023-02-23 15:12:36,355][11456] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:12:36,357][11456] RunningMeanStd input shape: (1,) [2023-02-23 15:12:36,368][11456] ConvEncoder: input_channels=3 [2023-02-23 15:12:36,657][11456] Conv encoder output size: 512 [2023-02-23 15:12:36,658][11456] Policy head output size: 512 [2023-02-23 15:12:36,709][11456] Created Actor Critic model with architecture: [2023-02-23 15:12:36,709][11456] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-02-23 15:12:44,128][11456] Using optimizer <class 'torch.optim.adam.Adam'> [2023-02-23 15:12:44,129][11456] No checkpoints found [2023-02-23 15:12:44,129][11456] Did not load from checkpoint, starting from scratch! [2023-02-23 15:12:44,129][11456] Initialized policy 0 weights for model version 0 [2023-02-23 15:12:44,134][11456] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:12:44,145][11456] LearnerWorker_p0 finished initialization! [2023-02-23 15:12:44,167][11317] Heartbeat connected on LearnerWorker_p0 [2023-02-23 15:12:44,220][11317] Heartbeat connected on RolloutWorker_w0 [2023-02-23 15:12:44,224][11317] Heartbeat connected on RolloutWorker_w2 [2023-02-23 15:12:44,227][11317] Heartbeat connected on RolloutWorker_w4 [2023-02-23 15:12:44,231][11317] Heartbeat connected on RolloutWorker_w6 [2023-02-23 15:12:44,269][11317] Heartbeat connected on RolloutWorker_w1 [2023-02-23 15:12:44,270][11317] Heartbeat connected on RolloutWorker_w7 [2023-02-23 15:12:44,271][11317] Heartbeat connected on RolloutWorker_w5 [2023-02-23 15:12:44,273][11317] Heartbeat connected on RolloutWorker_w3 [2023-02-23 15:12:44,329][11317] Heartbeat connected on Batcher_0 [2023-02-23 15:12:44,384][11470] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:12:44,385][11470] RunningMeanStd input shape: (1,) [2023-02-23 15:12:44,399][11470] ConvEncoder: input_channels=3 [2023-02-23 15:12:44,501][11470] Conv encoder output size: 512 [2023-02-23 15:12:44,502][11470] Policy head output size: 512 [2023-02-23 15:12:45,912][11317] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:12:47,348][11317] Inference worker 0-0 is ready! [2023-02-23 15:12:47,351][11317] All inference workers are ready! Signal rollout workers to start! [2023-02-23 15:12:47,352][11317] Heartbeat connected on InferenceWorker_p0-w0 [2023-02-23 15:12:47,522][11476] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,533][11477] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,539][11474] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,542][11471] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,544][11472] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,573][11478] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,571][11475] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:47,619][11473] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:12:48,452][11478] Decorrelating experience for 0 frames... [2023-02-23 15:12:48,896][11474] Decorrelating experience for 0 frames... [2023-02-23 15:12:48,901][11477] Decorrelating experience for 0 frames... [2023-02-23 15:12:48,918][11475] Decorrelating experience for 0 frames... [2023-02-23 15:12:49,499][11478] Decorrelating experience for 32 frames... [2023-02-23 15:12:50,055][11471] Decorrelating experience for 0 frames... [2023-02-23 15:12:50,058][11474] Decorrelating experience for 32 frames... [2023-02-23 15:12:50,068][11475] Decorrelating experience for 32 frames... [2023-02-23 15:12:50,188][11476] Decorrelating experience for 0 frames... [2023-02-23 15:12:50,801][11478] Decorrelating experience for 64 frames... [2023-02-23 15:12:50,912][11317] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:12:51,088][11473] Decorrelating experience for 0 frames... [2023-02-23 15:12:51,210][11471] Decorrelating experience for 32 frames... [2023-02-23 15:12:51,213][11477] Decorrelating experience for 32 frames... [2023-02-23 15:12:51,407][11474] Decorrelating experience for 64 frames... [2023-02-23 15:12:52,040][11478] Decorrelating experience for 96 frames... [2023-02-23 15:12:52,124][11477] Decorrelating experience for 64 frames... [2023-02-23 15:12:52,196][11474] Decorrelating experience for 96 frames... [2023-02-23 15:12:52,393][11473] Decorrelating experience for 32 frames... [2023-02-23 15:12:52,408][11472] Decorrelating experience for 0 frames... [2023-02-23 15:12:52,542][11476] Decorrelating experience for 32 frames... [2023-02-23 15:12:53,507][11471] Decorrelating experience for 64 frames... [2023-02-23 15:12:53,538][11477] Decorrelating experience for 96 frames... [2023-02-23 15:12:53,556][11472] Decorrelating experience for 32 frames... [2023-02-23 15:12:53,733][11475] Decorrelating experience for 64 frames... [2023-02-23 15:12:53,793][11473] Decorrelating experience for 64 frames... [2023-02-23 15:12:54,498][11475] Decorrelating experience for 96 frames... [2023-02-23 15:12:54,497][11471] Decorrelating experience for 96 frames... [2023-02-23 15:12:54,795][11476] Decorrelating experience for 64 frames... [2023-02-23 15:12:54,984][11473] Decorrelating experience for 96 frames... [2023-02-23 15:12:55,421][11472] Decorrelating experience for 64 frames... [2023-02-23 15:12:55,630][11476] Decorrelating experience for 96 frames... [2023-02-23 15:12:55,912][11317] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:12:56,187][11472] Decorrelating experience for 96 frames... [2023-02-23 15:12:58,653][11317] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 11317], exiting... [2023-02-23 15:12:58,660][11456] Stopping Batcher_0... [2023-02-23 15:12:58,661][11456] Loop batcher_evt_loop terminating... [2023-02-23 15:12:58,659][11317] Runner profile tree view: main_loop: 34.4556 [2023-02-23 15:12:58,663][11317] Collected {0: 0}, FPS: 0.0 [2023-02-23 15:12:58,691][11471] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance0'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,642][11475] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance2'), args=(0, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,728][11470] Weights refcount: 2 0 [2023-02-23 15:12:58,727][11478] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance7'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,706][11474] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance4'), args=(0, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,735][11470] Stopping InferenceWorker_p0-w0... [2023-02-23 15:12:58,736][11470] Loop inference_proc0-0_evt_loop terminating... [2023-02-23 15:12:58,737][11471] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop [2023-02-23 15:12:58,694][11472] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance1'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,739][11472] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc1_evt_loop [2023-02-23 15:12:58,730][11475] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc2_evt_loop [2023-02-23 15:12:58,681][11476] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance5'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,755][11476] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop [2023-02-23 15:12:58,731][11474] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop [2023-02-23 15:12:58,739][11477] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance6'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,787][11477] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop [2023-02-23 15:12:58,697][11473] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance3'), args=(1, 0) Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts new_obs, rewards, terminated, truncated, infos = e.step(actions) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 319, in step return self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-02-23 15:12:58,790][11473] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc3_evt_loop [2023-02-23 15:12:58,728][11478] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc7_evt_loop [2023-02-23 15:13:03,759][11456] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000001_4096.pth... [2023-02-23 15:13:03,826][11456] Stopping LearnerWorker_p0... [2023-02-23 15:13:03,826][11456] Loop learner_proc0_evt_loop terminating... [2023-02-23 15:17:18,614][14252] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-23 15:17:18,617][14252] Rollout worker 0 uses device cpu [2023-02-23 15:17:18,621][14252] Rollout worker 1 uses device cpu [2023-02-23 15:17:18,624][14252] Rollout worker 2 uses device cpu [2023-02-23 15:17:18,626][14252] Rollout worker 3 uses device cpu [2023-02-23 15:17:18,630][14252] Rollout worker 4 uses device cpu [2023-02-23 15:17:18,635][14252] Rollout worker 5 uses device cpu [2023-02-23 15:17:18,636][14252] Rollout worker 6 uses device cpu [2023-02-23 15:17:18,639][14252] Rollout worker 7 uses device cpu [2023-02-23 15:17:18,791][14252] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:17:18,793][14252] InferenceWorker_p0-w0: min num requests: 2 [2023-02-23 15:17:18,827][14252] Starting all processes... [2023-02-23 15:17:18,830][14252] Starting process learner_proc0 [2023-02-23 15:17:18,890][14252] Starting all processes... [2023-02-23 15:17:18,901][14252] Starting process inference_proc0-0 [2023-02-23 15:17:18,902][14252] Starting process rollout_proc0 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc1 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc2 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc3 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc4 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc5 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc6 [2023-02-23 15:17:18,904][14252] Starting process rollout_proc7 [2023-02-23 15:17:30,288][15287] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:17:30,292][15287] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-23 15:17:30,461][15302] Worker 0 uses CPU cores [0] [2023-02-23 15:17:30,721][15308] Worker 6 uses CPU cores [0] [2023-02-23 15:17:30,725][15306] Worker 4 uses CPU cores [0] [2023-02-23 15:17:30,737][15301] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:17:30,738][15301] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-23 15:17:30,876][15309] Worker 7 uses CPU cores [1] [2023-02-23 15:17:30,880][15303] Worker 1 uses CPU cores [1] [2023-02-23 15:17:30,907][15307] Worker 5 uses CPU cores [1] [2023-02-23 15:17:30,924][15305] Worker 3 uses CPU cores [1] [2023-02-23 15:17:30,944][15304] Worker 2 uses CPU cores [0] [2023-02-23 15:17:31,382][15301] Num visible devices: 1 [2023-02-23 15:17:31,381][15287] Num visible devices: 1 [2023-02-23 15:17:31,391][15287] Starting seed is not provided [2023-02-23 15:17:31,391][15287] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:17:31,392][15287] Initializing actor-critic model on device cuda:0 [2023-02-23 15:17:31,393][15287] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:17:31,394][15287] RunningMeanStd input shape: (1,) [2023-02-23 15:17:31,411][15287] ConvEncoder: input_channels=3 [2023-02-23 15:17:31,542][15287] Conv encoder output size: 512 [2023-02-23 15:17:31,543][15287] Policy head output size: 512 [2023-02-23 15:17:31,558][15287] Created Actor Critic model with architecture: [2023-02-23 15:17:31,558][15287] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-02-23 15:17:33,992][15287] Using optimizer <class 'torch.optim.adam.Adam'> [2023-02-23 15:17:33,993][15287] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000001_4096.pth... [2023-02-23 15:17:34,025][15287] Loading model from checkpoint [2023-02-23 15:17:34,029][15287] Loaded experiment state at self.train_step=1, self.env_steps=4096 [2023-02-23 15:17:34,030][15287] Initialized policy 0 weights for model version 1 [2023-02-23 15:17:34,034][15287] LearnerWorker_p0 finished initialization! [2023-02-23 15:17:34,035][15287] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-23 15:17:34,242][15301] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:17:34,245][15301] RunningMeanStd input shape: (1,) [2023-02-23 15:17:34,257][15301] ConvEncoder: input_channels=3 [2023-02-23 15:17:34,354][15301] Conv encoder output size: 512 [2023-02-23 15:17:34,355][15301] Policy head output size: 512 [2023-02-23 15:17:35,449][14252] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4096. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:17:36,551][14252] Inference worker 0-0 is ready! [2023-02-23 15:17:36,553][14252] All inference workers are ready! Signal rollout workers to start! [2023-02-23 15:17:36,649][15309] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,651][15303] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,657][15306] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,654][15302] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,659][15304] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,658][15308] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,663][15305] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:36,655][15307] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:17:37,451][15309] Decorrelating experience for 0 frames... [2023-02-23 15:17:37,452][15307] Decorrelating experience for 0 frames... [2023-02-23 15:17:37,819][15307] Decorrelating experience for 32 frames... [2023-02-23 15:17:38,042][15306] Decorrelating experience for 0 frames... [2023-02-23 15:17:38,044][15308] Decorrelating experience for 0 frames... [2023-02-23 15:17:38,047][15302] Decorrelating experience for 0 frames... [2023-02-23 15:17:38,048][15304] Decorrelating experience for 0 frames... [2023-02-23 15:17:38,405][15309] Decorrelating experience for 32 frames... [2023-02-23 15:17:38,783][14252] Heartbeat connected on Batcher_0 [2023-02-23 15:17:38,787][14252] Heartbeat connected on LearnerWorker_p0 [2023-02-23 15:17:38,822][14252] Heartbeat connected on InferenceWorker_p0-w0 [2023-02-23 15:17:39,155][15303] Decorrelating experience for 0 frames... [2023-02-23 15:17:39,665][15302] Decorrelating experience for 32 frames... [2023-02-23 15:17:39,672][15308] Decorrelating experience for 32 frames... [2023-02-23 15:17:39,670][15304] Decorrelating experience for 32 frames... [2023-02-23 15:17:39,676][15306] Decorrelating experience for 32 frames... [2023-02-23 15:17:40,139][15303] Decorrelating experience for 32 frames... [2023-02-23 15:17:40,450][14252] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4096. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:17:41,001][15305] Decorrelating experience for 0 frames... [2023-02-23 15:17:41,462][15303] Decorrelating experience for 64 frames... [2023-02-23 15:17:41,960][15302] Decorrelating experience for 64 frames... [2023-02-23 15:17:41,958][15306] Decorrelating experience for 64 frames... [2023-02-23 15:17:41,962][15304] Decorrelating experience for 64 frames... [2023-02-23 15:17:42,216][15308] Decorrelating experience for 64 frames... [2023-02-23 15:17:42,242][15305] Decorrelating experience for 32 frames... [2023-02-23 15:17:42,278][15307] Decorrelating experience for 64 frames... [2023-02-23 15:17:43,536][15306] Decorrelating experience for 96 frames... [2023-02-23 15:17:43,538][15302] Decorrelating experience for 96 frames... [2023-02-23 15:17:43,753][15309] Decorrelating experience for 64 frames... [2023-02-23 15:17:43,805][14252] Heartbeat connected on RolloutWorker_w4 [2023-02-23 15:17:43,822][14252] Heartbeat connected on RolloutWorker_w0 [2023-02-23 15:17:43,910][15308] Decorrelating experience for 96 frames... [2023-02-23 15:17:44,078][15307] Decorrelating experience for 96 frames... [2023-02-23 15:17:44,318][14252] Heartbeat connected on RolloutWorker_w6 [2023-02-23 15:17:44,678][14252] Heartbeat connected on RolloutWorker_w5 [2023-02-23 15:17:45,160][15304] Decorrelating experience for 96 frames... [2023-02-23 15:17:45,449][14252] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4096. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:17:45,466][14252] Heartbeat connected on RolloutWorker_w2 [2023-02-23 15:17:45,659][15305] Decorrelating experience for 64 frames... [2023-02-23 15:17:47,474][15303] Decorrelating experience for 96 frames... [2023-02-23 15:17:47,790][14252] Heartbeat connected on RolloutWorker_w1 [2023-02-23 15:17:48,103][15309] Decorrelating experience for 96 frames... [2023-02-23 15:17:48,381][15305] Decorrelating experience for 96 frames... [2023-02-23 15:17:48,654][14252] Heartbeat connected on RolloutWorker_w7 [2023-02-23 15:17:48,795][14252] Heartbeat connected on RolloutWorker_w3 [2023-02-23 15:17:49,508][15287] Signal inference workers to stop experience collection... [2023-02-23 15:17:49,514][15301] InferenceWorker_p0-w0: stopping experience collection [2023-02-23 15:17:50,448][14252] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4096. Throughput: 0: 120.7. Samples: 1810. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-23 15:17:50,452][14252] Avg episode reward: [(0, '2.505')] [2023-02-23 15:17:50,759][15287] Signal inference workers to resume experience collection... [2023-02-23 15:17:50,760][15301] InferenceWorker_p0-w0: resuming experience collection [2023-02-23 15:17:55,448][14252] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 28672. Throughput: 0: 292.4. Samples: 5848. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:17:55,457][14252] Avg episode reward: [(0, '3.360')] [2023-02-23 15:17:59,742][15301] Updated weights for policy 0, policy_version 11 (0.0017) [2023-02-23 15:18:00,448][14252] Fps is (10 sec: 4096.0, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 45056. Throughput: 0: 358.5. Samples: 8962. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-23 15:18:00,451][14252] Avg episode reward: [(0, '3.907')] [2023-02-23 15:18:05,449][14252] Fps is (10 sec: 2867.2, 60 sec: 1774.9, 300 sec: 1774.9). Total num frames: 57344. Throughput: 0: 445.6. Samples: 13368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:18:05,455][14252] Avg episode reward: [(0, '4.337')] [2023-02-23 15:18:10,448][14252] Fps is (10 sec: 3686.4, 60 sec: 2223.6, 300 sec: 2223.6). Total num frames: 81920. Throughput: 0: 540.3. Samples: 18910. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:18:10,454][14252] Avg episode reward: [(0, '4.496')] [2023-02-23 15:18:11,415][15301] Updated weights for policy 0, policy_version 21 (0.0021) [2023-02-23 15:18:15,448][14252] Fps is (10 sec: 4505.6, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 102400. Throughput: 0: 560.9. Samples: 22434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:18:15,450][14252] Avg episode reward: [(0, '4.377')] [2023-02-23 15:18:15,465][15287] Saving new best policy, reward=4.377! [2023-02-23 15:18:20,448][14252] Fps is (10 sec: 3686.4, 60 sec: 2548.6, 300 sec: 2548.6). Total num frames: 118784. Throughput: 0: 635.5. Samples: 28596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:18:20,452][14252] Avg episode reward: [(0, '4.542')] [2023-02-23 15:18:20,456][15287] Saving new best policy, reward=4.542! [2023-02-23 15:18:22,247][15301] Updated weights for policy 0, policy_version 31 (0.0019) [2023-02-23 15:18:25,449][14252] Fps is (10 sec: 3276.8, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 135168. Throughput: 0: 733.0. Samples: 32982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:18:25,456][14252] Avg episode reward: [(0, '4.660')] [2023-02-23 15:18:25,467][15287] Saving new best policy, reward=4.660! [2023-02-23 15:18:30,448][14252] Fps is (10 sec: 3686.4, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 155648. Throughput: 0: 785.5. Samples: 35346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:18:30,450][14252] Avg episode reward: [(0, '4.470')] [2023-02-23 15:18:32,874][15301] Updated weights for policy 0, policy_version 41 (0.0017) [2023-02-23 15:18:35,450][14252] Fps is (10 sec: 4095.5, 60 sec: 2867.1, 300 sec: 2867.1). Total num frames: 176128. Throughput: 0: 900.6. Samples: 42340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:18:35,455][14252] Avg episode reward: [(0, '4.446')] [2023-02-23 15:18:40,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3208.6, 300 sec: 2961.7). Total num frames: 196608. Throughput: 0: 941.7. Samples: 48226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:18:40,454][14252] Avg episode reward: [(0, '4.401')] [2023-02-23 15:18:44,334][15301] Updated weights for policy 0, policy_version 51 (0.0016) [2023-02-23 15:18:45,448][14252] Fps is (10 sec: 3277.2, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 208896. Throughput: 0: 922.0. Samples: 50452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:18:45,452][14252] Avg episode reward: [(0, '4.464')] [2023-02-23 15:18:50,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3003.7). Total num frames: 229376. Throughput: 0: 938.1. Samples: 55584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:18:50,451][14252] Avg episode reward: [(0, '4.460')] [2023-02-23 15:18:54,044][15301] Updated weights for policy 0, policy_version 61 (0.0013) [2023-02-23 15:18:55,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3123.2). Total num frames: 253952. Throughput: 0: 970.6. Samples: 62588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:18:55,451][14252] Avg episode reward: [(0, '4.315')] [2023-02-23 15:19:00,454][14252] Fps is (10 sec: 4093.7, 60 sec: 3754.3, 300 sec: 3132.0). Total num frames: 270336. Throughput: 0: 963.3. Samples: 65786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:19:00,457][14252] Avg episode reward: [(0, '4.543')] [2023-02-23 15:19:05,449][14252] Fps is (10 sec: 3276.6, 60 sec: 3822.9, 300 sec: 3140.3). Total num frames: 286720. Throughput: 0: 924.1. Samples: 70180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:19:05,451][14252] Avg episode reward: [(0, '4.613')] [2023-02-23 15:19:06,599][15301] Updated weights for policy 0, policy_version 71 (0.0030) [2023-02-23 15:19:10,448][14252] Fps is (10 sec: 3688.4, 60 sec: 3754.7, 300 sec: 3190.6). Total num frames: 307200. Throughput: 0: 952.5. Samples: 75846. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:19:10,457][14252] Avg episode reward: [(0, '4.490')] [2023-02-23 15:19:15,448][14252] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3235.8). Total num frames: 327680. Throughput: 0: 978.3. Samples: 79370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:19:15,456][14252] Avg episode reward: [(0, '4.392')] [2023-02-23 15:19:15,487][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000081_331776.pth... [2023-02-23 15:19:15,494][15301] Updated weights for policy 0, policy_version 81 (0.0023) [2023-02-23 15:19:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 348160. Throughput: 0: 955.7. Samples: 85346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:19:20,453][14252] Avg episode reward: [(0, '4.379')] [2023-02-23 15:19:25,449][14252] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3239.6). Total num frames: 360448. Throughput: 0: 921.1. Samples: 89678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:19:25,453][14252] Avg episode reward: [(0, '4.315')] [2023-02-23 15:19:28,099][15301] Updated weights for policy 0, policy_version 91 (0.0019) [2023-02-23 15:19:30,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 380928. Throughput: 0: 930.5. Samples: 92324. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:19:30,450][14252] Avg episode reward: [(0, '4.384')] [2023-02-23 15:19:35,448][14252] Fps is (10 sec: 4505.8, 60 sec: 3823.0, 300 sec: 3345.1). Total num frames: 405504. Throughput: 0: 970.1. Samples: 99238. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:19:35,456][14252] Avg episode reward: [(0, '4.644')] [2023-02-23 15:19:36,821][15301] Updated weights for policy 0, policy_version 101 (0.0018) [2023-02-23 15:19:40,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3342.3). Total num frames: 421888. Throughput: 0: 942.9. Samples: 105020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:19:40,457][14252] Avg episode reward: [(0, '4.666')] [2023-02-23 15:19:40,462][15287] Saving new best policy, reward=4.666! [2023-02-23 15:19:45,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3339.8). Total num frames: 438272. Throughput: 0: 917.1. Samples: 107050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:19:45,462][14252] Avg episode reward: [(0, '4.482')] [2023-02-23 15:19:49,313][15301] Updated weights for policy 0, policy_version 111 (0.0030) [2023-02-23 15:19:50,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3367.8). Total num frames: 458752. Throughput: 0: 936.6. Samples: 112326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:19:50,456][14252] Avg episode reward: [(0, '4.636')] [2023-02-23 15:19:55,449][14252] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3393.8). Total num frames: 479232. Throughput: 0: 966.6. Samples: 119344. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:19:55,454][14252] Avg episode reward: [(0, '4.722')] [2023-02-23 15:19:55,545][15287] Saving new best policy, reward=4.722! [2023-02-23 15:19:59,069][15301] Updated weights for policy 0, policy_version 121 (0.0014) [2023-02-23 15:20:00,453][14252] Fps is (10 sec: 3684.7, 60 sec: 3754.7, 300 sec: 3389.7). Total num frames: 495616. Throughput: 0: 956.6. Samples: 122420. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:20:00,458][14252] Avg episode reward: [(0, '4.685')] [2023-02-23 15:20:05,450][14252] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3386.0). Total num frames: 512000. Throughput: 0: 921.8. Samples: 126828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:05,454][14252] Avg episode reward: [(0, '4.660')] [2023-02-23 15:20:10,448][14252] Fps is (10 sec: 3688.1, 60 sec: 3754.7, 300 sec: 3408.9). Total num frames: 532480. Throughput: 0: 946.9. Samples: 132288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:10,451][14252] Avg episode reward: [(0, '4.488')] [2023-02-23 15:20:10,760][15301] Updated weights for policy 0, policy_version 131 (0.0024) [2023-02-23 15:20:15,448][14252] Fps is (10 sec: 4506.3, 60 sec: 3822.9, 300 sec: 3456.0). Total num frames: 557056. Throughput: 0: 965.3. Samples: 135764. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:20:15,451][14252] Avg episode reward: [(0, '4.815')] [2023-02-23 15:20:15,474][15287] Saving new best policy, reward=4.815! [2023-02-23 15:20:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3450.6). Total num frames: 573440. Throughput: 0: 950.0. Samples: 141986. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:20:20,451][14252] Avg episode reward: [(0, '4.941')] [2023-02-23 15:20:20,454][15287] Saving new best policy, reward=4.941! [2023-02-23 15:20:21,275][15301] Updated weights for policy 0, policy_version 141 (0.0018) [2023-02-23 15:20:25,449][14252] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3421.4). Total num frames: 585728. Throughput: 0: 917.9. Samples: 146324. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:25,452][14252] Avg episode reward: [(0, '4.751')] [2023-02-23 15:20:30,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3464.0). Total num frames: 610304. Throughput: 0: 930.0. Samples: 148902. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:30,451][14252] Avg episode reward: [(0, '4.574')] [2023-02-23 15:20:31,992][15301] Updated weights for policy 0, policy_version 151 (0.0021) [2023-02-23 15:20:35,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3481.6). Total num frames: 630784. Throughput: 0: 967.4. Samples: 155860. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:20:35,451][14252] Avg episode reward: [(0, '4.500')] [2023-02-23 15:20:40,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3498.2). Total num frames: 651264. Throughput: 0: 943.9. Samples: 161818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:20:40,455][14252] Avg episode reward: [(0, '4.748')] [2023-02-23 15:20:43,004][15301] Updated weights for policy 0, policy_version 161 (0.0013) [2023-02-23 15:20:45,449][14252] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3470.8). Total num frames: 663552. Throughput: 0: 924.8. Samples: 164032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:20:45,460][14252] Avg episode reward: [(0, '4.819')] [2023-02-23 15:20:50,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3486.9). Total num frames: 684032. Throughput: 0: 942.2. Samples: 169224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:50,454][14252] Avg episode reward: [(0, '4.486')] [2023-02-23 15:20:53,186][15301] Updated weights for policy 0, policy_version 171 (0.0013) [2023-02-23 15:20:55,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3522.6). Total num frames: 708608. Throughput: 0: 976.7. Samples: 176238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:20:55,453][14252] Avg episode reward: [(0, '4.421')] [2023-02-23 15:21:00,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3891.5, 300 sec: 3536.5). Total num frames: 729088. Throughput: 0: 973.1. Samples: 179552. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:21:00,455][14252] Avg episode reward: [(0, '4.558')] [2023-02-23 15:21:04,848][15301] Updated weights for policy 0, policy_version 181 (0.0018) [2023-02-23 15:21:05,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3510.9). Total num frames: 741376. Throughput: 0: 931.0. Samples: 183882. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:21:05,452][14252] Avg episode reward: [(0, '4.558')] [2023-02-23 15:21:10,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3524.5). Total num frames: 761856. Throughput: 0: 960.4. Samples: 189544. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:21:10,458][14252] Avg episode reward: [(0, '4.696')] [2023-02-23 15:21:14,337][15301] Updated weights for policy 0, policy_version 191 (0.0012) [2023-02-23 15:21:15,449][14252] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3556.1). Total num frames: 786432. Throughput: 0: 982.3. Samples: 193106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:21:15,452][14252] Avg episode reward: [(0, '4.928')] [2023-02-23 15:21:15,461][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000192_786432.pth... [2023-02-23 15:21:15,589][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000001_4096.pth [2023-02-23 15:21:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3549.9). Total num frames: 802816. Throughput: 0: 966.8. Samples: 199368. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:21:20,453][14252] Avg episode reward: [(0, '5.181')] [2023-02-23 15:21:20,455][15287] Saving new best policy, reward=5.181! [2023-02-23 15:21:25,448][14252] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3526.1). Total num frames: 815104. Throughput: 0: 929.9. Samples: 203662. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:21:25,457][14252] Avg episode reward: [(0, '4.964')] [2023-02-23 15:21:26,696][15301] Updated weights for policy 0, policy_version 201 (0.0020) [2023-02-23 15:21:30,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3555.7). Total num frames: 839680. Throughput: 0: 939.1. Samples: 206292. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:21:30,451][14252] Avg episode reward: [(0, '4.747')] [2023-02-23 15:21:35,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3566.9). Total num frames: 860160. Throughput: 0: 982.7. Samples: 213444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:21:35,456][14252] Avg episode reward: [(0, '4.807')] [2023-02-23 15:21:35,552][15301] Updated weights for policy 0, policy_version 211 (0.0012) [2023-02-23 15:21:40,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3577.7). Total num frames: 880640. Throughput: 0: 954.5. Samples: 219192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:21:40,451][14252] Avg episode reward: [(0, '4.880')] [2023-02-23 15:21:45,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3555.3). Total num frames: 892928. Throughput: 0: 931.2. Samples: 221454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:21:45,454][14252] Avg episode reward: [(0, '5.105')] [2023-02-23 15:21:47,710][15301] Updated weights for policy 0, policy_version 221 (0.0016) [2023-02-23 15:21:50,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3582.0). Total num frames: 917504. Throughput: 0: 954.9. Samples: 226854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:21:50,451][14252] Avg episode reward: [(0, '5.186')] [2023-02-23 15:21:50,457][15287] Saving new best policy, reward=5.186! [2023-02-23 15:21:55,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3591.9). Total num frames: 937984. Throughput: 0: 983.4. Samples: 233798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:21:55,451][14252] Avg episode reward: [(0, '4.596')] [2023-02-23 15:21:56,708][15301] Updated weights for policy 0, policy_version 231 (0.0017) [2023-02-23 15:22:00,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3585.9). Total num frames: 954368. Throughput: 0: 971.5. Samples: 236824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:22:00,457][14252] Avg episode reward: [(0, '4.756')] [2023-02-23 15:22:05,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3580.2). Total num frames: 970752. Throughput: 0: 931.7. Samples: 241296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:22:05,450][14252] Avg episode reward: [(0, '5.073')] [2023-02-23 15:22:08,917][15301] Updated weights for policy 0, policy_version 241 (0.0023) [2023-02-23 15:22:10,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3589.6). Total num frames: 991232. Throughput: 0: 967.2. Samples: 247186. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:22:10,451][14252] Avg episode reward: [(0, '5.340')] [2023-02-23 15:22:10,456][15287] Saving new best policy, reward=5.340! [2023-02-23 15:22:15,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3613.3). Total num frames: 1015808. Throughput: 0: 986.2. Samples: 250670. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:22:15,457][14252] Avg episode reward: [(0, '5.479')] [2023-02-23 15:22:15,471][15287] Saving new best policy, reward=5.479! [2023-02-23 15:22:18,280][15301] Updated weights for policy 0, policy_version 251 (0.0023) [2023-02-23 15:22:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3607.4). Total num frames: 1032192. Throughput: 0: 961.9. Samples: 256728. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:22:20,455][14252] Avg episode reward: [(0, '5.678')] [2023-02-23 15:22:20,458][15287] Saving new best policy, reward=5.678! [2023-02-23 15:22:25,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3601.7). Total num frames: 1048576. Throughput: 0: 933.2. Samples: 261184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:22:25,453][14252] Avg episode reward: [(0, '5.678')] [2023-02-23 15:22:29,863][15301] Updated weights for policy 0, policy_version 261 (0.0023) [2023-02-23 15:22:30,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3610.0). Total num frames: 1069056. Throughput: 0: 944.0. Samples: 263934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:22:30,454][14252] Avg episode reward: [(0, '5.838')] [2023-02-23 15:22:30,458][15287] Saving new best policy, reward=5.838! [2023-02-23 15:22:35,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3693.4). Total num frames: 1093632. Throughput: 0: 981.0. Samples: 270998. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:22:35,452][14252] Avg episode reward: [(0, '5.844')] [2023-02-23 15:22:35,464][15287] Saving new best policy, reward=5.844! [2023-02-23 15:22:40,181][15301] Updated weights for policy 0, policy_version 271 (0.0013) [2023-02-23 15:22:40,450][14252] Fps is (10 sec: 4095.3, 60 sec: 3822.8, 300 sec: 3748.9). Total num frames: 1110016. Throughput: 0: 951.4. Samples: 276614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:22:40,453][14252] Avg episode reward: [(0, '6.024')] [2023-02-23 15:22:40,454][15287] Saving new best policy, reward=6.024! [2023-02-23 15:22:45,449][14252] Fps is (10 sec: 2867.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1122304. Throughput: 0: 933.9. Samples: 278848. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-23 15:22:45,451][14252] Avg episode reward: [(0, '6.245')] [2023-02-23 15:22:45,470][15287] Saving new best policy, reward=6.245! [2023-02-23 15:22:50,448][14252] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1146880. Throughput: 0: 955.4. Samples: 284288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:22:50,455][14252] Avg episode reward: [(0, '6.428')] [2023-02-23 15:22:50,464][15287] Saving new best policy, reward=6.428! [2023-02-23 15:22:51,176][15301] Updated weights for policy 0, policy_version 281 (0.0027) [2023-02-23 15:22:55,448][14252] Fps is (10 sec: 4915.5, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1171456. Throughput: 0: 982.8. Samples: 291414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:22:55,455][14252] Avg episode reward: [(0, '6.566')] [2023-02-23 15:22:55,469][15287] Saving new best policy, reward=6.566! [2023-02-23 15:23:00,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1187840. Throughput: 0: 972.0. Samples: 294408. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-23 15:23:00,451][14252] Avg episode reward: [(0, '7.006')] [2023-02-23 15:23:00,456][15287] Saving new best policy, reward=7.006! [2023-02-23 15:23:01,600][15301] Updated weights for policy 0, policy_version 291 (0.0015) [2023-02-23 15:23:05,449][14252] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1200128. Throughput: 0: 936.4. Samples: 298866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:23:05,451][14252] Avg episode reward: [(0, '6.681')] [2023-02-23 15:23:10,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 1224704. Throughput: 0: 971.1. Samples: 304882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:23:10,456][14252] Avg episode reward: [(0, '6.374')] [2023-02-23 15:23:12,034][15301] Updated weights for policy 0, policy_version 301 (0.0026) [2023-02-23 15:23:15,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1245184. Throughput: 0: 988.4. Samples: 308414. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:23:15,451][14252] Avg episode reward: [(0, '6.767')] [2023-02-23 15:23:15,514][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000305_1249280.pth... [2023-02-23 15:23:15,628][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000081_331776.pth [2023-02-23 15:23:20,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1261568. Throughput: 0: 964.5. Samples: 314400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:23:20,451][14252] Avg episode reward: [(0, '6.916')] [2023-02-23 15:23:23,496][15301] Updated weights for policy 0, policy_version 311 (0.0014) [2023-02-23 15:23:25,449][14252] Fps is (10 sec: 3276.6, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1277952. Throughput: 0: 939.8. Samples: 318906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:23:25,452][14252] Avg episode reward: [(0, '7.100')] [2023-02-23 15:23:25,465][15287] Saving new best policy, reward=7.100! [2023-02-23 15:23:30,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1302528. Throughput: 0: 956.9. Samples: 321908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:23:30,451][14252] Avg episode reward: [(0, '7.083')] [2023-02-23 15:23:32,938][15301] Updated weights for policy 0, policy_version 321 (0.0023) [2023-02-23 15:23:35,448][14252] Fps is (10 sec: 4505.9, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1323008. Throughput: 0: 995.4. Samples: 329080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:23:35,451][14252] Avg episode reward: [(0, '7.584')] [2023-02-23 15:23:35,533][15287] Saving new best policy, reward=7.584! [2023-02-23 15:23:40,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 1339392. Throughput: 0: 956.9. Samples: 334474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:23:40,455][14252] Avg episode reward: [(0, '8.474')] [2023-02-23 15:23:40,458][15287] Saving new best policy, reward=8.474! [2023-02-23 15:23:44,802][15301] Updated weights for policy 0, policy_version 331 (0.0028) [2023-02-23 15:23:45,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1355776. Throughput: 0: 940.1. Samples: 336714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:23:45,455][14252] Avg episode reward: [(0, '8.647')] [2023-02-23 15:23:45,482][15287] Saving new best policy, reward=8.647! [2023-02-23 15:23:50,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1380352. Throughput: 0: 971.2. Samples: 342570. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:23:50,454][14252] Avg episode reward: [(0, '9.196')] [2023-02-23 15:23:50,457][15287] Saving new best policy, reward=9.196! [2023-02-23 15:23:53,902][15301] Updated weights for policy 0, policy_version 341 (0.0012) [2023-02-23 15:23:55,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3832.3). Total num frames: 1400832. Throughput: 0: 994.2. Samples: 349620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:23:55,457][14252] Avg episode reward: [(0, '8.705')] [2023-02-23 15:24:00,449][14252] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1417216. Throughput: 0: 977.7. Samples: 352412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:24:00,455][14252] Avg episode reward: [(0, '8.476')] [2023-02-23 15:24:05,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1433600. Throughput: 0: 946.8. Samples: 357008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:24:05,453][14252] Avg episode reward: [(0, '9.109')] [2023-02-23 15:24:06,173][15301] Updated weights for policy 0, policy_version 351 (0.0013) [2023-02-23 15:24:10,448][14252] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 1458176. Throughput: 0: 983.8. Samples: 363176. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:24:10,453][14252] Avg episode reward: [(0, '9.138')] [2023-02-23 15:24:14,602][15301] Updated weights for policy 0, policy_version 361 (0.0021) [2023-02-23 15:24:15,448][14252] Fps is (10 sec: 4915.3, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 1482752. Throughput: 0: 998.2. Samples: 366828. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:24:15,457][14252] Avg episode reward: [(0, '10.321')] [2023-02-23 15:24:15,465][15287] Saving new best policy, reward=10.321! [2023-02-23 15:24:20,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1495040. Throughput: 0: 969.5. Samples: 372706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:24:20,451][14252] Avg episode reward: [(0, '10.876')] [2023-02-23 15:24:20,454][15287] Saving new best policy, reward=10.876! [2023-02-23 15:24:25,450][14252] Fps is (10 sec: 2866.7, 60 sec: 3891.1, 300 sec: 3832.2). Total num frames: 1511424. Throughput: 0: 946.6. Samples: 377074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:24:25,455][14252] Avg episode reward: [(0, '11.253')] [2023-02-23 15:24:25,469][15287] Saving new best policy, reward=11.253! [2023-02-23 15:24:27,050][15301] Updated weights for policy 0, policy_version 371 (0.0013) [2023-02-23 15:24:30,450][14252] Fps is (10 sec: 4095.3, 60 sec: 3891.1, 300 sec: 3832.2). Total num frames: 1536000. Throughput: 0: 965.0. Samples: 380140. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:24:30,453][14252] Avg episode reward: [(0, '11.627')] [2023-02-23 15:24:30,461][15287] Saving new best policy, reward=11.627! [2023-02-23 15:24:35,448][14252] Fps is (10 sec: 4506.3, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1556480. Throughput: 0: 987.9. Samples: 387024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:24:35,451][14252] Avg episode reward: [(0, '11.964')] [2023-02-23 15:24:35,464][15287] Saving new best policy, reward=11.964! [2023-02-23 15:24:35,855][15301] Updated weights for policy 0, policy_version 381 (0.0014) [2023-02-23 15:24:40,448][14252] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1572864. Throughput: 0: 948.9. Samples: 392322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:24:40,453][14252] Avg episode reward: [(0, '11.292')] [2023-02-23 15:24:45,449][14252] Fps is (10 sec: 2867.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 1585152. Throughput: 0: 936.9. Samples: 394572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:24:45,456][14252] Avg episode reward: [(0, '11.170')] [2023-02-23 15:24:48,088][15301] Updated weights for policy 0, policy_version 391 (0.0022) [2023-02-23 15:24:50,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1609728. Throughput: 0: 965.6. Samples: 400458. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:24:50,453][14252] Avg episode reward: [(0, '9.943')] [2023-02-23 15:24:55,448][14252] Fps is (10 sec: 4915.5, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1634304. Throughput: 0: 985.8. Samples: 407536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:24:55,451][14252] Avg episode reward: [(0, '9.766')] [2023-02-23 15:24:57,504][15301] Updated weights for policy 0, policy_version 401 (0.0013) [2023-02-23 15:25:00,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1650688. Throughput: 0: 963.8. Samples: 410198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:25:00,453][14252] Avg episode reward: [(0, '9.388')] [2023-02-23 15:25:05,449][14252] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1662976. Throughput: 0: 934.5. Samples: 414758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:25:05,453][14252] Avg episode reward: [(0, '9.105')] [2023-02-23 15:25:09,057][15301] Updated weights for policy 0, policy_version 411 (0.0019) [2023-02-23 15:25:10,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1687552. Throughput: 0: 976.4. Samples: 421012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:25:10,455][14252] Avg episode reward: [(0, '9.705')] [2023-02-23 15:25:15,448][14252] Fps is (10 sec: 4915.3, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1712128. Throughput: 0: 987.2. Samples: 424560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:25:15,451][14252] Avg episode reward: [(0, '10.413')] [2023-02-23 15:25:15,465][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_1712128.pth... [2023-02-23 15:25:15,618][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000192_786432.pth [2023-02-23 15:25:19,024][15301] Updated weights for policy 0, policy_version 421 (0.0012) [2023-02-23 15:25:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1728512. Throughput: 0: 961.3. Samples: 430282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:25:20,453][14252] Avg episode reward: [(0, '10.961')] [2023-02-23 15:25:25,449][14252] Fps is (10 sec: 2867.1, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 1740800. Throughput: 0: 942.9. Samples: 434752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:25:25,451][14252] Avg episode reward: [(0, '11.855')] [2023-02-23 15:25:30,021][15301] Updated weights for policy 0, policy_version 431 (0.0024) [2023-02-23 15:25:30,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3846.1). Total num frames: 1765376. Throughput: 0: 965.7. Samples: 438030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:25:30,451][14252] Avg episode reward: [(0, '12.125')] [2023-02-23 15:25:30,457][15287] Saving new best policy, reward=12.125! [2023-02-23 15:25:35,448][14252] Fps is (10 sec: 4915.4, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1789952. Throughput: 0: 991.4. Samples: 445070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:25:35,455][14252] Avg episode reward: [(0, '12.379')] [2023-02-23 15:25:35,470][15287] Saving new best policy, reward=12.379! [2023-02-23 15:25:40,450][14252] Fps is (10 sec: 3685.8, 60 sec: 3822.8, 300 sec: 3859.9). Total num frames: 1802240. Throughput: 0: 946.7. Samples: 450140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:25:40,454][14252] Avg episode reward: [(0, '12.229')] [2023-02-23 15:25:40,982][15301] Updated weights for policy 0, policy_version 441 (0.0014) [2023-02-23 15:25:45,448][14252] Fps is (10 sec: 2867.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1818624. Throughput: 0: 935.8. Samples: 452310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:25:45,451][14252] Avg episode reward: [(0, '12.514')] [2023-02-23 15:25:45,462][15287] Saving new best policy, reward=12.514! [2023-02-23 15:25:50,448][14252] Fps is (10 sec: 4096.6, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1843200. Throughput: 0: 968.1. Samples: 458324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:25:50,456][14252] Avg episode reward: [(0, '12.573')] [2023-02-23 15:25:50,462][15287] Saving new best policy, reward=12.573! [2023-02-23 15:25:51,224][15301] Updated weights for policy 0, policy_version 451 (0.0012) [2023-02-23 15:25:55,450][14252] Fps is (10 sec: 4504.9, 60 sec: 3822.8, 300 sec: 3846.1). Total num frames: 1863680. Throughput: 0: 984.9. Samples: 465332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:25:55,457][14252] Avg episode reward: [(0, '13.030')] [2023-02-23 15:25:55,474][15287] Saving new best policy, reward=13.030! [2023-02-23 15:26:00,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1880064. Throughput: 0: 958.8. Samples: 467706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:00,452][14252] Avg episode reward: [(0, '14.522')] [2023-02-23 15:26:00,460][15287] Saving new best policy, reward=14.522! [2023-02-23 15:26:02,815][15301] Updated weights for policy 0, policy_version 461 (0.0023) [2023-02-23 15:26:05,448][14252] Fps is (10 sec: 3277.3, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1896448. Throughput: 0: 932.2. Samples: 472230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:05,453][14252] Avg episode reward: [(0, '14.546')] [2023-02-23 15:26:05,475][15287] Saving new best policy, reward=14.546! [2023-02-23 15:26:10,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 1916928. Throughput: 0: 974.8. Samples: 478616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:26:10,454][14252] Avg episode reward: [(0, '15.032')] [2023-02-23 15:26:10,459][15287] Saving new best policy, reward=15.032! [2023-02-23 15:26:12,328][15301] Updated weights for policy 0, policy_version 471 (0.0018) [2023-02-23 15:26:15,453][14252] Fps is (10 sec: 4503.7, 60 sec: 3822.7, 300 sec: 3859.9). Total num frames: 1941504. Throughput: 0: 979.2. Samples: 482096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:15,460][14252] Avg episode reward: [(0, '17.052')] [2023-02-23 15:26:15,479][15287] Saving new best policy, reward=17.052! [2023-02-23 15:26:20,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1957888. Throughput: 0: 948.0. Samples: 487732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:20,451][14252] Avg episode reward: [(0, '17.260')] [2023-02-23 15:26:20,459][15287] Saving new best policy, reward=17.260! [2023-02-23 15:26:24,350][15301] Updated weights for policy 0, policy_version 481 (0.0019) [2023-02-23 15:26:25,448][14252] Fps is (10 sec: 3278.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 1974272. Throughput: 0: 935.9. Samples: 492256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:25,451][14252] Avg episode reward: [(0, '18.028')] [2023-02-23 15:26:25,461][15287] Saving new best policy, reward=18.028! [2023-02-23 15:26:30,454][14252] Fps is (10 sec: 3684.4, 60 sec: 3822.6, 300 sec: 3846.0). Total num frames: 1994752. Throughput: 0: 959.8. Samples: 495508. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:30,456][14252] Avg episode reward: [(0, '19.636')] [2023-02-23 15:26:30,468][15287] Saving new best policy, reward=19.636! [2023-02-23 15:26:33,402][15301] Updated weights for policy 0, policy_version 491 (0.0012) [2023-02-23 15:26:35,451][14252] Fps is (10 sec: 4504.5, 60 sec: 3822.8, 300 sec: 3859.9). Total num frames: 2019328. Throughput: 0: 983.1. Samples: 502564. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:26:35,460][14252] Avg episode reward: [(0, '18.011')] [2023-02-23 15:26:40,449][14252] Fps is (10 sec: 3688.4, 60 sec: 3823.0, 300 sec: 3860.0). Total num frames: 2031616. Throughput: 0: 940.5. Samples: 507654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:26:40,452][14252] Avg episode reward: [(0, '18.535')] [2023-02-23 15:26:45,448][14252] Fps is (10 sec: 2867.9, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2048000. Throughput: 0: 935.8. Samples: 509816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:26:45,453][14252] Avg episode reward: [(0, '18.757')] [2023-02-23 15:26:45,709][15301] Updated weights for policy 0, policy_version 501 (0.0012) [2023-02-23 15:26:50,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2072576. Throughput: 0: 973.5. Samples: 516036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:26:50,451][14252] Avg episode reward: [(0, '18.635')] [2023-02-23 15:26:54,273][15301] Updated weights for policy 0, policy_version 511 (0.0013) [2023-02-23 15:26:55,448][14252] Fps is (10 sec: 4915.2, 60 sec: 3891.3, 300 sec: 3873.8). Total num frames: 2097152. Throughput: 0: 991.3. Samples: 523224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:26:55,455][14252] Avg episode reward: [(0, '19.653')] [2023-02-23 15:26:55,470][15287] Saving new best policy, reward=19.653! [2023-02-23 15:27:00,450][14252] Fps is (10 sec: 3685.7, 60 sec: 3822.8, 300 sec: 3859.9). Total num frames: 2109440. Throughput: 0: 965.1. Samples: 525524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:27:00,453][14252] Avg episode reward: [(0, '20.280')] [2023-02-23 15:27:00,456][15287] Saving new best policy, reward=20.280! [2023-02-23 15:27:05,448][14252] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2125824. Throughput: 0: 938.9. Samples: 529984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:27:05,451][14252] Avg episode reward: [(0, '21.781')] [2023-02-23 15:27:05,465][15287] Saving new best policy, reward=21.781! [2023-02-23 15:27:06,671][15301] Updated weights for policy 0, policy_version 521 (0.0029) [2023-02-23 15:27:10,448][14252] Fps is (10 sec: 4096.8, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2150400. Throughput: 0: 984.7. Samples: 536568. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:27:10,451][14252] Avg episode reward: [(0, '20.821')] [2023-02-23 15:27:15,447][15301] Updated weights for policy 0, policy_version 531 (0.0012) [2023-02-23 15:27:15,452][14252] Fps is (10 sec: 4913.5, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 2174976. Throughput: 0: 990.5. Samples: 540080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:27:15,466][14252] Avg episode reward: [(0, '20.319')] [2023-02-23 15:27:15,480][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000531_2174976.pth... [2023-02-23 15:27:15,653][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000305_1249280.pth [2023-02-23 15:27:20,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2187264. Throughput: 0: 950.8. Samples: 545350. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:27:20,455][14252] Avg episode reward: [(0, '20.089')] [2023-02-23 15:27:25,448][14252] Fps is (10 sec: 2868.2, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2203648. Throughput: 0: 939.9. Samples: 549950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:27:25,450][14252] Avg episode reward: [(0, '19.768')] [2023-02-23 15:27:27,542][15301] Updated weights for policy 0, policy_version 541 (0.0016) [2023-02-23 15:27:30,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.6, 300 sec: 3846.1). Total num frames: 2228224. Throughput: 0: 969.6. Samples: 553448. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:27:30,456][14252] Avg episode reward: [(0, '18.928')] [2023-02-23 15:27:35,454][14252] Fps is (10 sec: 4503.1, 60 sec: 3822.7, 300 sec: 3859.9). Total num frames: 2248704. Throughput: 0: 992.8. Samples: 560718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:27:35,457][14252] Avg episode reward: [(0, '19.602')] [2023-02-23 15:27:37,019][15301] Updated weights for policy 0, policy_version 551 (0.0020) [2023-02-23 15:27:40,456][14252] Fps is (10 sec: 3683.6, 60 sec: 3890.7, 300 sec: 3873.8). Total num frames: 2265088. Throughput: 0: 942.1. Samples: 565628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:27:40,459][14252] Avg episode reward: [(0, '21.022')] [2023-02-23 15:27:45,448][14252] Fps is (10 sec: 3278.6, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2281472. Throughput: 0: 938.9. Samples: 567772. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-23 15:27:45,454][14252] Avg episode reward: [(0, '22.111')] [2023-02-23 15:27:45,468][15287] Saving new best policy, reward=22.111! [2023-02-23 15:27:48,526][15301] Updated weights for policy 0, policy_version 561 (0.0018) [2023-02-23 15:27:50,448][14252] Fps is (10 sec: 4099.2, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2306048. Throughput: 0: 977.5. Samples: 573970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:27:50,451][14252] Avg episode reward: [(0, '21.952')] [2023-02-23 15:27:55,449][14252] Fps is (10 sec: 4505.3, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2326528. Throughput: 0: 993.4. Samples: 581272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:27:55,456][14252] Avg episode reward: [(0, '21.804')] [2023-02-23 15:27:58,374][15301] Updated weights for policy 0, policy_version 571 (0.0022) [2023-02-23 15:28:00,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3873.8). Total num frames: 2342912. Throughput: 0: 967.0. Samples: 583592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:28:00,451][14252] Avg episode reward: [(0, '20.670')] [2023-02-23 15:28:05,448][14252] Fps is (10 sec: 3277.0, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2359296. Throughput: 0: 948.4. Samples: 588026. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:28:05,457][14252] Avg episode reward: [(0, '19.990')] [2023-02-23 15:28:09,455][15301] Updated weights for policy 0, policy_version 581 (0.0015) [2023-02-23 15:28:10,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 2383872. Throughput: 0: 991.6. Samples: 594570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:28:10,451][14252] Avg episode reward: [(0, '19.808')] [2023-02-23 15:28:15,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3823.2, 300 sec: 3873.8). Total num frames: 2404352. Throughput: 0: 991.6. Samples: 598070. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:28:15,456][14252] Avg episode reward: [(0, '19.816')] [2023-02-23 15:28:20,227][15301] Updated weights for policy 0, policy_version 591 (0.0016) [2023-02-23 15:28:20,450][14252] Fps is (10 sec: 3685.8, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 2420736. Throughput: 0: 949.5. Samples: 603440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:28:20,453][14252] Avg episode reward: [(0, '20.385')] [2023-02-23 15:28:25,448][14252] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2433024. Throughput: 0: 937.4. Samples: 607802. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:28:25,452][14252] Avg episode reward: [(0, '20.841')] [2023-02-23 15:28:30,448][14252] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2457600. Throughput: 0: 964.9. Samples: 611194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:28:30,451][14252] Avg episode reward: [(0, '21.531')] [2023-02-23 15:28:31,070][15301] Updated weights for policy 0, policy_version 601 (0.0030) [2023-02-23 15:28:35,449][14252] Fps is (10 sec: 4505.6, 60 sec: 3823.3, 300 sec: 3860.0). Total num frames: 2478080. Throughput: 0: 980.6. Samples: 618096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:28:35,455][14252] Avg episode reward: [(0, '22.390')] [2023-02-23 15:28:35,467][15287] Saving new best policy, reward=22.390! [2023-02-23 15:28:40,451][14252] Fps is (10 sec: 3685.5, 60 sec: 3823.3, 300 sec: 3859.9). Total num frames: 2494464. Throughput: 0: 922.8. Samples: 622800. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-23 15:28:40,456][14252] Avg episode reward: [(0, '20.951')] [2023-02-23 15:28:43,122][15301] Updated weights for policy 0, policy_version 611 (0.0014) [2023-02-23 15:28:45,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2510848. Throughput: 0: 920.8. Samples: 625028. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:28:45,454][14252] Avg episode reward: [(0, '20.423')] [2023-02-23 15:28:50,448][14252] Fps is (10 sec: 4097.0, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2535424. Throughput: 0: 968.4. Samples: 631604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:28:50,455][14252] Avg episode reward: [(0, '20.206')] [2023-02-23 15:28:51,833][15301] Updated weights for policy 0, policy_version 621 (0.0012) [2023-02-23 15:28:55,450][14252] Fps is (10 sec: 4505.2, 60 sec: 3822.9, 300 sec: 3859.9). Total num frames: 2555904. Throughput: 0: 981.5. Samples: 638738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-23 15:28:55,454][14252] Avg episode reward: [(0, '21.306')] [2023-02-23 15:29:00,449][14252] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2572288. Throughput: 0: 953.4. Samples: 640974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:29:00,450][14252] Avg episode reward: [(0, '21.304')] [2023-02-23 15:29:04,052][15301] Updated weights for policy 0, policy_version 631 (0.0014) [2023-02-23 15:29:05,448][14252] Fps is (10 sec: 3277.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2588672. Throughput: 0: 933.2. Samples: 645434. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:29:05,452][14252] Avg episode reward: [(0, '21.609')] [2023-02-23 15:29:10,451][14252] Fps is (10 sec: 4095.1, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 2613248. Throughput: 0: 987.8. Samples: 652256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:10,457][14252] Avg episode reward: [(0, '22.252')] [2023-02-23 15:29:12,691][15301] Updated weights for policy 0, policy_version 641 (0.0011) [2023-02-23 15:29:15,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2633728. Throughput: 0: 989.3. Samples: 655712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:15,456][14252] Avg episode reward: [(0, '23.526')] [2023-02-23 15:29:15,465][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000643_2633728.pth... [2023-02-23 15:29:15,603][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_1712128.pth [2023-02-23 15:29:15,634][15287] Saving new best policy, reward=23.526! [2023-02-23 15:29:20,448][14252] Fps is (10 sec: 3277.6, 60 sec: 3754.8, 300 sec: 3846.1). Total num frames: 2646016. Throughput: 0: 944.0. Samples: 660574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:20,453][14252] Avg episode reward: [(0, '23.802')] [2023-02-23 15:29:20,459][15287] Saving new best policy, reward=23.802! [2023-02-23 15:29:25,228][15301] Updated weights for policy 0, policy_version 651 (0.0021) [2023-02-23 15:29:25,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2666496. Throughput: 0: 944.5. Samples: 665298. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:25,456][14252] Avg episode reward: [(0, '22.421')] [2023-02-23 15:29:30,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2686976. Throughput: 0: 973.8. Samples: 668848. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:29:30,451][14252] Avg episode reward: [(0, '22.582')] [2023-02-23 15:29:34,058][15301] Updated weights for policy 0, policy_version 661 (0.0020) [2023-02-23 15:29:35,451][14252] Fps is (10 sec: 4095.0, 60 sec: 3822.8, 300 sec: 3846.0). Total num frames: 2707456. Throughput: 0: 981.7. Samples: 675782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:35,454][14252] Avg episode reward: [(0, '22.472')] [2023-02-23 15:29:40,452][14252] Fps is (10 sec: 3685.2, 60 sec: 3822.9, 300 sec: 3859.9). Total num frames: 2723840. Throughput: 0: 926.2. Samples: 680420. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:29:40,456][14252] Avg episode reward: [(0, '24.322')] [2023-02-23 15:29:40,460][15287] Saving new best policy, reward=24.322! [2023-02-23 15:29:45,448][14252] Fps is (10 sec: 3277.6, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 2740224. Throughput: 0: 925.8. Samples: 682636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:29:45,451][14252] Avg episode reward: [(0, '23.811')] [2023-02-23 15:29:46,475][15301] Updated weights for policy 0, policy_version 671 (0.0032) [2023-02-23 15:29:50,448][14252] Fps is (10 sec: 4097.3, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2764800. Throughput: 0: 973.0. Samples: 689220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:29:50,455][14252] Avg episode reward: [(0, '23.797')] [2023-02-23 15:29:55,449][14252] Fps is (10 sec: 4505.4, 60 sec: 3823.0, 300 sec: 3846.1). Total num frames: 2785280. Throughput: 0: 970.2. Samples: 695914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:29:55,455][14252] Avg episode reward: [(0, '24.199')] [2023-02-23 15:29:56,023][15301] Updated weights for policy 0, policy_version 681 (0.0030) [2023-02-23 15:30:00,449][14252] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2801664. Throughput: 0: 941.3. Samples: 698072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:00,451][14252] Avg episode reward: [(0, '24.201')] [2023-02-23 15:30:05,448][14252] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2818048. Throughput: 0: 930.7. Samples: 702456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:30:05,453][14252] Avg episode reward: [(0, '24.388')] [2023-02-23 15:30:05,467][15287] Saving new best policy, reward=24.388! [2023-02-23 15:30:07,738][15301] Updated weights for policy 0, policy_version 691 (0.0025) [2023-02-23 15:30:10,448][14252] Fps is (10 sec: 4096.1, 60 sec: 3823.1, 300 sec: 3832.2). Total num frames: 2842624. Throughput: 0: 979.4. Samples: 709370. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:30:10,451][14252] Avg episode reward: [(0, '22.743')] [2023-02-23 15:30:15,451][14252] Fps is (10 sec: 4504.6, 60 sec: 3822.8, 300 sec: 3846.0). Total num frames: 2863104. Throughput: 0: 980.0. Samples: 712950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:15,455][14252] Avg episode reward: [(0, '23.450')] [2023-02-23 15:30:18,076][15301] Updated weights for policy 0, policy_version 701 (0.0032) [2023-02-23 15:30:20,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2875392. Throughput: 0: 934.9. Samples: 717850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:20,451][14252] Avg episode reward: [(0, '24.661')] [2023-02-23 15:30:20,456][15287] Saving new best policy, reward=24.661! [2023-02-23 15:30:25,448][14252] Fps is (10 sec: 3277.5, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2895872. Throughput: 0: 944.2. Samples: 722904. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:30:25,453][14252] Avg episode reward: [(0, '24.530')] [2023-02-23 15:30:28,640][15301] Updated weights for policy 0, policy_version 711 (0.0011) [2023-02-23 15:30:30,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2920448. Throughput: 0: 973.7. Samples: 726454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:30,451][14252] Avg episode reward: [(0, '27.185')] [2023-02-23 15:30:30,455][15287] Saving new best policy, reward=27.185! [2023-02-23 15:30:35,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3846.1). Total num frames: 2936832. Throughput: 0: 981.6. Samples: 733392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:35,455][14252] Avg episode reward: [(0, '27.592')] [2023-02-23 15:30:35,493][15287] Saving new best policy, reward=27.592! [2023-02-23 15:30:39,585][15301] Updated weights for policy 0, policy_version 721 (0.0016) [2023-02-23 15:30:40,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3846.1). Total num frames: 2953216. Throughput: 0: 930.3. Samples: 737778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:30:40,452][14252] Avg episode reward: [(0, '27.149')] [2023-02-23 15:30:45,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 2973696. Throughput: 0: 931.2. Samples: 739974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:30:45,452][14252] Avg episode reward: [(0, '27.865')] [2023-02-23 15:30:45,462][15287] Saving new best policy, reward=27.865! [2023-02-23 15:30:49,778][15301] Updated weights for policy 0, policy_version 731 (0.0032) [2023-02-23 15:30:50,449][14252] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2994176. Throughput: 0: 982.8. Samples: 746684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:30:50,452][14252] Avg episode reward: [(0, '28.729')] [2023-02-23 15:30:50,453][15287] Saving new best policy, reward=28.729! [2023-02-23 15:30:55,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3846.1). Total num frames: 3014656. Throughput: 0: 969.8. Samples: 753012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:30:55,452][14252] Avg episode reward: [(0, '29.258')] [2023-02-23 15:30:55,469][15287] Saving new best policy, reward=29.258! [2023-02-23 15:31:00,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3026944. Throughput: 0: 936.8. Samples: 755106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:31:00,455][14252] Avg episode reward: [(0, '28.948')] [2023-02-23 15:31:02,064][15301] Updated weights for policy 0, policy_version 741 (0.0014) [2023-02-23 15:31:05,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3047424. Throughput: 0: 926.9. Samples: 759562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:31:05,457][14252] Avg episode reward: [(0, '27.728')] [2023-02-23 15:31:10,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3818.4). Total num frames: 3067904. Throughput: 0: 965.7. Samples: 766362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:31:10,451][14252] Avg episode reward: [(0, '28.506')] [2023-02-23 15:31:11,612][15301] Updated weights for policy 0, policy_version 751 (0.0025) [2023-02-23 15:31:15,450][14252] Fps is (10 sec: 4095.3, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3088384. Throughput: 0: 962.4. Samples: 769762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:31:15,453][14252] Avg episode reward: [(0, '28.257')] [2023-02-23 15:31:15,474][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000754_3088384.pth... [2023-02-23 15:31:15,639][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000531_2174976.pth [2023-02-23 15:31:20,450][14252] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3818.3). Total num frames: 3100672. Throughput: 0: 908.9. Samples: 774292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:31:20,455][14252] Avg episode reward: [(0, '27.264')] [2023-02-23 15:31:24,111][15301] Updated weights for policy 0, policy_version 761 (0.0011) [2023-02-23 15:31:25,448][14252] Fps is (10 sec: 3277.4, 60 sec: 3754.7, 300 sec: 3818.4). Total num frames: 3121152. Throughput: 0: 925.1. Samples: 779406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:31:25,456][14252] Avg episode reward: [(0, '25.810')] [2023-02-23 15:31:30,448][14252] Fps is (10 sec: 4506.3, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 3145728. Throughput: 0: 954.8. Samples: 782938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:31:30,455][14252] Avg episode reward: [(0, '23.947')] [2023-02-23 15:31:32,821][15301] Updated weights for policy 0, policy_version 771 (0.0014) [2023-02-23 15:31:35,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 3166208. Throughput: 0: 959.1. Samples: 789844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:31:35,455][14252] Avg episode reward: [(0, '24.050')] [2023-02-23 15:31:40,452][14252] Fps is (10 sec: 3275.7, 60 sec: 3754.5, 300 sec: 3832.1). Total num frames: 3178496. Throughput: 0: 914.3. Samples: 794158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:31:40,456][14252] Avg episode reward: [(0, '22.190')] [2023-02-23 15:31:45,096][15301] Updated weights for policy 0, policy_version 781 (0.0022) [2023-02-23 15:31:45,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 3198976. Throughput: 0: 918.2. Samples: 796424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:31:45,456][14252] Avg episode reward: [(0, '21.929')] [2023-02-23 15:31:50,448][14252] Fps is (10 sec: 4507.2, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3223552. Throughput: 0: 973.0. Samples: 803346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:31:50,451][14252] Avg episode reward: [(0, '22.969')] [2023-02-23 15:31:54,283][15301] Updated weights for policy 0, policy_version 791 (0.0021) [2023-02-23 15:31:55,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3239936. Throughput: 0: 964.1. Samples: 809746. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:31:55,451][14252] Avg episode reward: [(0, '23.241')] [2023-02-23 15:32:00,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3256320. Throughput: 0: 938.6. Samples: 811996. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:32:00,454][14252] Avg episode reward: [(0, '24.888')] [2023-02-23 15:32:05,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3276800. Throughput: 0: 944.9. Samples: 816812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:32:05,451][14252] Avg episode reward: [(0, '25.580')] [2023-02-23 15:32:06,185][15301] Updated weights for policy 0, policy_version 801 (0.0020) [2023-02-23 15:32:10,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3818.4). Total num frames: 3301376. Throughput: 0: 987.2. Samples: 823830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:32:10,456][14252] Avg episode reward: [(0, '25.716')] [2023-02-23 15:32:15,450][14252] Fps is (10 sec: 4095.3, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3317760. Throughput: 0: 987.1. Samples: 827358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:32:15,457][14252] Avg episode reward: [(0, '26.350')] [2023-02-23 15:32:16,106][15301] Updated weights for policy 0, policy_version 811 (0.0027) [2023-02-23 15:32:20,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3891.3, 300 sec: 3832.2). Total num frames: 3334144. Throughput: 0: 933.9. Samples: 831870. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:32:20,452][14252] Avg episode reward: [(0, '26.334')] [2023-02-23 15:32:25,448][14252] Fps is (10 sec: 3277.4, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3350528. Throughput: 0: 954.7. Samples: 837114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:32:25,457][14252] Avg episode reward: [(0, '25.119')] [2023-02-23 15:32:27,252][15301] Updated weights for policy 0, policy_version 821 (0.0012) [2023-02-23 15:32:30,448][14252] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3818.4). Total num frames: 3375104. Throughput: 0: 981.6. Samples: 840598. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:32:30,456][14252] Avg episode reward: [(0, '24.194')] [2023-02-23 15:32:35,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3832.3). Total num frames: 3395584. Throughput: 0: 978.2. Samples: 847364. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:32:35,453][14252] Avg episode reward: [(0, '25.447')] [2023-02-23 15:32:37,720][15301] Updated weights for policy 0, policy_version 831 (0.0014) [2023-02-23 15:32:40,449][14252] Fps is (10 sec: 3686.1, 60 sec: 3891.4, 300 sec: 3832.2). Total num frames: 3411968. Throughput: 0: 934.3. Samples: 851790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:32:40,456][14252] Avg episode reward: [(0, '26.321')] [2023-02-23 15:32:45,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3428352. Throughput: 0: 936.4. Samples: 854136. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:32:45,452][14252] Avg episode reward: [(0, '24.337')] [2023-02-23 15:32:48,291][15301] Updated weights for policy 0, policy_version 841 (0.0015) [2023-02-23 15:32:50,448][14252] Fps is (10 sec: 4096.3, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3452928. Throughput: 0: 983.6. Samples: 861074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:32:50,450][14252] Avg episode reward: [(0, '24.045')] [2023-02-23 15:32:55,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3473408. Throughput: 0: 968.7. Samples: 867420. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:32:55,453][14252] Avg episode reward: [(0, '25.343')] [2023-02-23 15:32:59,351][15301] Updated weights for policy 0, policy_version 851 (0.0029) [2023-02-23 15:33:00,452][14252] Fps is (10 sec: 3275.6, 60 sec: 3822.7, 300 sec: 3818.3). Total num frames: 3485696. Throughput: 0: 939.6. Samples: 869642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:33:00,456][14252] Avg episode reward: [(0, '26.033')] [2023-02-23 15:33:05,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3506176. Throughput: 0: 949.2. Samples: 874586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:33:05,454][14252] Avg episode reward: [(0, '26.062')] [2023-02-23 15:33:09,335][15301] Updated weights for policy 0, policy_version 861 (0.0012) [2023-02-23 15:33:10,448][14252] Fps is (10 sec: 4507.2, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3530752. Throughput: 0: 989.8. Samples: 881656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:33:10,457][14252] Avg episode reward: [(0, '26.435')] [2023-02-23 15:33:15,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3818.3). Total num frames: 3547136. Throughput: 0: 991.8. Samples: 885228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:33:15,455][14252] Avg episode reward: [(0, '26.231')] [2023-02-23 15:33:15,468][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000866_3547136.pth... [2023-02-23 15:33:15,617][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000643_2633728.pth [2023-02-23 15:33:20,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3563520. Throughput: 0: 938.1. Samples: 889578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:33:20,451][14252] Avg episode reward: [(0, '26.717')] [2023-02-23 15:33:21,036][15301] Updated weights for policy 0, policy_version 871 (0.0025) [2023-02-23 15:33:25,450][14252] Fps is (10 sec: 3685.8, 60 sec: 3891.1, 300 sec: 3818.3). Total num frames: 3584000. Throughput: 0: 963.4. Samples: 895142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:33:25,456][14252] Avg episode reward: [(0, '27.168')] [2023-02-23 15:33:30,210][15301] Updated weights for policy 0, policy_version 881 (0.0014) [2023-02-23 15:33:30,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3608576. Throughput: 0: 989.2. Samples: 898648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:33:30,451][14252] Avg episode reward: [(0, '25.425')] [2023-02-23 15:33:35,454][14252] Fps is (10 sec: 4094.4, 60 sec: 3822.6, 300 sec: 3832.1). Total num frames: 3624960. Throughput: 0: 980.3. Samples: 905192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:33:35,457][14252] Avg episode reward: [(0, '25.969')] [2023-02-23 15:33:40,449][14252] Fps is (10 sec: 3276.7, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 3641344. Throughput: 0: 937.8. Samples: 909622. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:33:40,454][14252] Avg episode reward: [(0, '25.230')] [2023-02-23 15:33:42,687][15301] Updated weights for policy 0, policy_version 891 (0.0033) [2023-02-23 15:33:45,448][14252] Fps is (10 sec: 3688.5, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3661824. Throughput: 0: 941.1. Samples: 911990. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-23 15:33:45,454][14252] Avg episode reward: [(0, '26.890')] [2023-02-23 15:33:50,448][14252] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3686400. Throughput: 0: 988.5. Samples: 919070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:33:50,451][14252] Avg episode reward: [(0, '26.763')] [2023-02-23 15:33:51,092][15301] Updated weights for policy 0, policy_version 901 (0.0021) [2023-02-23 15:33:55,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3702784. Throughput: 0: 967.2. Samples: 925182. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:33:55,451][14252] Avg episode reward: [(0, '26.948')] [2023-02-23 15:34:00,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3891.4, 300 sec: 3832.2). Total num frames: 3719168. Throughput: 0: 936.0. Samples: 927348. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:34:00,455][14252] Avg episode reward: [(0, '27.841')] [2023-02-23 15:34:03,601][15301] Updated weights for policy 0, policy_version 911 (0.0015) [2023-02-23 15:34:05,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3739648. Throughput: 0: 953.7. Samples: 932496. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-23 15:34:05,456][14252] Avg episode reward: [(0, '27.685')] [2023-02-23 15:34:10,448][14252] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3760128. Throughput: 0: 987.0. Samples: 939554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-23 15:34:10,451][14252] Avg episode reward: [(0, '26.982')] [2023-02-23 15:34:12,451][15301] Updated weights for policy 0, policy_version 921 (0.0017) [2023-02-23 15:34:15,449][14252] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 3780608. Throughput: 0: 980.8. Samples: 942782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:34:15,459][14252] Avg episode reward: [(0, '26.515')] [2023-02-23 15:34:20,448][14252] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3792896. Throughput: 0: 933.3. Samples: 947184. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:34:20,451][14252] Avg episode reward: [(0, '26.085')] [2023-02-23 15:34:24,585][15301] Updated weights for policy 0, policy_version 931 (0.0036) [2023-02-23 15:34:25,449][14252] Fps is (10 sec: 3686.1, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3817472. Throughput: 0: 963.3. Samples: 952970. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:34:25,456][14252] Avg episode reward: [(0, '24.158')] [2023-02-23 15:34:30,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3837952. Throughput: 0: 988.1. Samples: 956454. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-23 15:34:30,457][14252] Avg episode reward: [(0, '24.301')] [2023-02-23 15:34:34,118][15301] Updated weights for policy 0, policy_version 941 (0.0013) [2023-02-23 15:34:35,448][14252] Fps is (10 sec: 3686.7, 60 sec: 3823.3, 300 sec: 3832.2). Total num frames: 3854336. Throughput: 0: 967.0. Samples: 962586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:34:35,455][14252] Avg episode reward: [(0, '24.058')] [2023-02-23 15:34:40,452][14252] Fps is (10 sec: 3275.5, 60 sec: 3822.7, 300 sec: 3832.1). Total num frames: 3870720. Throughput: 0: 928.2. Samples: 966954. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-23 15:34:40,455][14252] Avg episode reward: [(0, '24.679')] [2023-02-23 15:34:45,448][14252] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3891200. Throughput: 0: 940.4. Samples: 969668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-23 15:34:45,453][14252] Avg episode reward: [(0, '25.359')] [2023-02-23 15:34:45,763][15301] Updated weights for policy 0, policy_version 951 (0.0018) [2023-02-23 15:34:50,449][14252] Fps is (10 sec: 4507.2, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3915776. Throughput: 0: 984.2. Samples: 976786. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-23 15:34:50,456][14252] Avg episode reward: [(0, '25.452')] [2023-02-23 15:34:55,450][14252] Fps is (10 sec: 4095.4, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 3932160. Throughput: 0: 955.3. Samples: 982546. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-23 15:34:55,457][14252] Avg episode reward: [(0, '26.563')] [2023-02-23 15:34:55,784][15301] Updated weights for policy 0, policy_version 961 (0.0017) [2023-02-23 15:35:00,448][14252] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3948544. Throughput: 0: 932.4. Samples: 984740. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-23 15:35:00,451][14252] Avg episode reward: [(0, '26.253')] [2023-02-23 15:35:05,448][14252] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3969024. Throughput: 0: 956.2. Samples: 990212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:35:05,455][14252] Avg episode reward: [(0, '25.363')] [2023-02-23 15:35:06,690][15301] Updated weights for policy 0, policy_version 971 (0.0029) [2023-02-23 15:35:10,448][14252] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3993600. Throughput: 0: 983.5. Samples: 997226. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-23 15:35:10,454][14252] Avg episode reward: [(0, '25.358')] [2023-02-23 15:35:13,676][15287] Stopping Batcher_0... [2023-02-23 15:35:13,677][15287] Loop batcher_evt_loop terminating... [2023-02-23 15:35:13,678][14252] Component Batcher_0 stopped! [2023-02-23 15:35:13,679][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-23 15:35:13,761][15301] Weights refcount: 2 0 [2023-02-23 15:35:13,767][14252] Component RolloutWorker_w1 stopped! [2023-02-23 15:35:13,771][15303] Stopping RolloutWorker_w1... [2023-02-23 15:35:13,778][14252] Component InferenceWorker_p0-w0 stopped! [2023-02-23 15:35:13,780][15301] Stopping InferenceWorker_p0-w0... [2023-02-23 15:35:13,784][15301] Loop inference_proc0-0_evt_loop terminating... [2023-02-23 15:35:13,786][15303] Loop rollout_proc1_evt_loop terminating... [2023-02-23 15:35:13,816][14252] Component RolloutWorker_w5 stopped! [2023-02-23 15:35:13,824][15307] Stopping RolloutWorker_w5... [2023-02-23 15:35:13,824][15307] Loop rollout_proc5_evt_loop terminating... [2023-02-23 15:35:13,842][15302] Stopping RolloutWorker_w0... [2023-02-23 15:35:13,843][15302] Loop rollout_proc0_evt_loop terminating... [2023-02-23 15:35:13,839][14252] Component RolloutWorker_w3 stopped! [2023-02-23 15:35:13,844][14252] Component RolloutWorker_w0 stopped! [2023-02-23 15:35:13,849][15305] Stopping RolloutWorker_w3... [2023-02-23 15:35:13,850][15305] Loop rollout_proc3_evt_loop terminating... [2023-02-23 15:35:13,865][14252] Component RolloutWorker_w4 stopped! [2023-02-23 15:35:13,865][15306] Stopping RolloutWorker_w4... [2023-02-23 15:35:13,874][15306] Loop rollout_proc4_evt_loop terminating... [2023-02-23 15:35:13,883][15309] Stopping RolloutWorker_w7... [2023-02-23 15:35:13,884][15309] Loop rollout_proc7_evt_loop terminating... [2023-02-23 15:35:13,886][15308] Stopping RolloutWorker_w6... [2023-02-23 15:35:13,892][15304] Stopping RolloutWorker_w2... [2023-02-23 15:35:13,892][15304] Loop rollout_proc2_evt_loop terminating... [2023-02-23 15:35:13,883][14252] Component RolloutWorker_w7 stopped! [2023-02-23 15:35:13,896][14252] Component RolloutWorker_w6 stopped! [2023-02-23 15:35:13,897][14252] Component RolloutWorker_w2 stopped! [2023-02-23 15:35:13,887][15308] Loop rollout_proc6_evt_loop terminating... [2023-02-23 15:35:13,953][15287] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000754_3088384.pth [2023-02-23 15:35:13,973][15287] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-23 15:35:14,190][14252] Component LearnerWorker_p0 stopped! [2023-02-23 15:35:14,192][14252] Waiting for process learner_proc0 to stop... [2023-02-23 15:35:14,194][15287] Stopping LearnerWorker_p0... [2023-02-23 15:35:14,197][15287] Loop learner_proc0_evt_loop terminating... [2023-02-23 15:35:16,320][14252] Waiting for process inference_proc0-0 to join... [2023-02-23 15:35:17,175][14252] Waiting for process rollout_proc0 to join... [2023-02-23 15:35:18,023][14252] Waiting for process rollout_proc1 to join... [2023-02-23 15:35:18,028][14252] Waiting for process rollout_proc2 to join... [2023-02-23 15:35:18,030][14252] Waiting for process rollout_proc3 to join... [2023-02-23 15:35:18,032][14252] Waiting for process rollout_proc4 to join... [2023-02-23 15:35:18,033][14252] Waiting for process rollout_proc5 to join... [2023-02-23 15:35:18,035][14252] Waiting for process rollout_proc6 to join... [2023-02-23 15:35:18,036][14252] Waiting for process rollout_proc7 to join... [2023-02-23 15:35:18,037][14252] Batcher 0 profile tree view: batching: 25.4059, releasing_batches: 0.0342 [2023-02-23 15:35:18,038][14252] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0099 wait_policy_total: 514.9866 update_model: 7.3590 weight_update: 0.0018 one_step: 0.0021 handle_policy_step: 494.7788 deserialize: 14.7049, stack: 2.9275, obs_to_device_normalize: 112.7425, forward: 234.8439, send_messages: 25.3925 prepare_outputs: 79.0665 to_cpu: 48.5471 [2023-02-23 15:35:18,040][14252] Learner 0 profile tree view: misc: 0.0053, prepare_batch: 15.2338 train: 79.3040 epoch_init: 0.0061, minibatch_init: 0.0097, losses_postprocess: 0.6127, kl_divergence: 0.5486, after_optimizer: 3.8811 calculate_losses: 26.1793 losses_init: 0.0033, forward_head: 1.7274, bptt_initial: 17.3315, tail: 1.0478, advantages_returns: 0.2927, losses: 3.4118 bptt: 2.0135 bptt_forward_core: 1.9285 update: 47.2798 clip: 1.3897 [2023-02-23 15:35:18,042][14252] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.3290, enqueue_policy_requests: 136.3886, env_step: 798.8956, overhead: 19.2139, complete_rollouts: 6.7458 save_policy_outputs: 19.2426 split_output_tensors: 9.4486 [2023-02-23 15:35:18,043][14252] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.3455, enqueue_policy_requests: 138.5361, env_step: 793.1275, overhead: 19.8811, complete_rollouts: 7.3809 save_policy_outputs: 19.5137 split_output_tensors: 9.4712 [2023-02-23 15:35:18,045][14252] Loop Runner_EvtLoop terminating... [2023-02-23 15:35:18,046][14252] Runner profile tree view: main_loop: 1079.2194 [2023-02-23 15:35:18,048][14252] Collected {0: 4005888}, FPS: 3708.0 [2023-02-23 15:35:55,139][14252] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-23 15:35:55,144][14252] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-23 15:35:55,149][14252] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-23 15:35:55,151][14252] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-23 15:35:55,155][14252] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-23 15:35:55,157][14252] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-23 15:35:55,162][14252] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-02-23 15:35:55,163][14252] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-23 15:35:55,164][14252] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-02-23 15:35:55,165][14252] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-02-23 15:35:55,167][14252] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-23 15:35:55,171][14252] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-23 15:35:55,172][14252] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-23 15:35:55,173][14252] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-23 15:35:55,174][14252] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-23 15:35:55,214][14252] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-23 15:35:55,217][14252] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:35:55,219][14252] RunningMeanStd input shape: (1,) [2023-02-23 15:35:55,237][14252] ConvEncoder: input_channels=3 [2023-02-23 15:35:55,942][14252] Conv encoder output size: 512 [2023-02-23 15:35:55,944][14252] Policy head output size: 512 [2023-02-23 15:35:58,321][14252] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-23 15:35:59,597][14252] Num frames 100... [2023-02-23 15:35:59,721][14252] Num frames 200... [2023-02-23 15:35:59,836][14252] Num frames 300... [2023-02-23 15:35:59,956][14252] Num frames 400... [2023-02-23 15:36:00,061][14252] Avg episode rewards: #0: 11.430, true rewards: #0: 4.430 [2023-02-23 15:36:00,063][14252] Avg episode reward: 11.430, avg true_objective: 4.430 [2023-02-23 15:36:00,127][14252] Num frames 500... [2023-02-23 15:36:00,246][14252] Num frames 600... [2023-02-23 15:36:00,364][14252] Num frames 700... [2023-02-23 15:36:00,484][14252] Num frames 800... [2023-02-23 15:36:00,603][14252] Num frames 900... [2023-02-23 15:36:00,725][14252] Num frames 1000... [2023-02-23 15:36:00,856][14252] Num frames 1100... [2023-02-23 15:36:00,972][14252] Num frames 1200... [2023-02-23 15:36:01,087][14252] Num frames 1300... [2023-02-23 15:36:01,198][14252] Num frames 1400... [2023-02-23 15:36:01,311][14252] Num frames 1500... [2023-02-23 15:36:01,429][14252] Num frames 1600... [2023-02-23 15:36:01,544][14252] Num frames 1700... [2023-02-23 15:36:01,661][14252] Num frames 1800... [2023-02-23 15:36:01,784][14252] Num frames 1900... [2023-02-23 15:36:01,892][14252] Avg episode rewards: #0: 22.235, true rewards: #0: 9.735 [2023-02-23 15:36:01,894][14252] Avg episode reward: 22.235, avg true_objective: 9.735 [2023-02-23 15:36:01,961][14252] Num frames 2000... [2023-02-23 15:36:02,076][14252] Num frames 2100... [2023-02-23 15:36:02,194][14252] Num frames 2200... [2023-02-23 15:36:02,317][14252] Num frames 2300... [2023-02-23 15:36:02,443][14252] Num frames 2400... [2023-02-23 15:36:02,562][14252] Num frames 2500... [2023-02-23 15:36:02,679][14252] Num frames 2600... [2023-02-23 15:36:02,804][14252] Num frames 2700... [2023-02-23 15:36:02,926][14252] Num frames 2800... [2023-02-23 15:36:03,002][14252] Avg episode rewards: #0: 20.703, true rewards: #0: 9.370 [2023-02-23 15:36:03,004][14252] Avg episode reward: 20.703, avg true_objective: 9.370 [2023-02-23 15:36:03,105][14252] Num frames 2900... [2023-02-23 15:36:03,217][14252] Num frames 3000... [2023-02-23 15:36:03,336][14252] Num frames 3100... [2023-02-23 15:36:03,448][14252] Num frames 3200... [2023-02-23 15:36:03,557][14252] Num frames 3300... [2023-02-23 15:36:03,676][14252] Num frames 3400... [2023-02-23 15:36:03,802][14252] Num frames 3500... [2023-02-23 15:36:03,920][14252] Num frames 3600... [2023-02-23 15:36:04,040][14252] Num frames 3700... [2023-02-23 15:36:04,161][14252] Num frames 3800... [2023-02-23 15:36:04,270][14252] Num frames 3900... [2023-02-23 15:36:04,386][14252] Num frames 4000... [2023-02-23 15:36:04,507][14252] Num frames 4100... [2023-02-23 15:36:04,565][14252] Avg episode rewards: #0: 23.253, true rewards: #0: 10.252 [2023-02-23 15:36:04,567][14252] Avg episode reward: 23.253, avg true_objective: 10.252 [2023-02-23 15:36:04,684][14252] Num frames 4200... [2023-02-23 15:36:04,801][14252] Num frames 4300... [2023-02-23 15:36:04,914][14252] Num frames 4400... [2023-02-23 15:36:05,030][14252] Avg episode rewards: #0: 20.106, true rewards: #0: 8.906 [2023-02-23 15:36:05,032][14252] Avg episode reward: 20.106, avg true_objective: 8.906 [2023-02-23 15:36:05,091][14252] Num frames 4500... [2023-02-23 15:36:05,202][14252] Num frames 4600... [2023-02-23 15:36:05,360][14252] Num frames 4700... [2023-02-23 15:36:05,522][14252] Num frames 4800... [2023-02-23 15:36:05,680][14252] Num frames 4900... [2023-02-23 15:36:05,850][14252] Num frames 5000... [2023-02-23 15:36:06,015][14252] Num frames 5100... [2023-02-23 15:36:06,175][14252] Num frames 5200... [2023-02-23 15:36:06,342][14252] Num frames 5300... [2023-02-23 15:36:06,500][14252] Num frames 5400... [2023-02-23 15:36:06,656][14252] Num frames 5500... [2023-02-23 15:36:06,812][14252] Num frames 5600... [2023-02-23 15:36:06,979][14252] Num frames 5700... [2023-02-23 15:36:07,141][14252] Num frames 5800... [2023-02-23 15:36:07,309][14252] Num frames 5900... [2023-02-23 15:36:07,468][14252] Num frames 6000... [2023-02-23 15:36:07,637][14252] Num frames 6100... [2023-02-23 15:36:07,803][14252] Num frames 6200... [2023-02-23 15:36:07,969][14252] Num frames 6300... [2023-02-23 15:36:08,136][14252] Num frames 6400... [2023-02-23 15:36:08,310][14252] Num frames 6500... [2023-02-23 15:36:08,460][14252] Avg episode rewards: #0: 25.755, true rewards: #0: 10.922 [2023-02-23 15:36:08,463][14252] Avg episode reward: 25.755, avg true_objective: 10.922 [2023-02-23 15:36:08,554][14252] Num frames 6600... [2023-02-23 15:36:08,731][14252] Num frames 6700... [2023-02-23 15:36:08,880][14252] Num frames 6800... [2023-02-23 15:36:09,002][14252] Num frames 6900... [2023-02-23 15:36:09,127][14252] Num frames 7000... [2023-02-23 15:36:09,240][14252] Num frames 7100... [2023-02-23 15:36:09,361][14252] Num frames 7200... [2023-02-23 15:36:09,463][14252] Avg episode rewards: #0: 24.201, true rewards: #0: 10.344 [2023-02-23 15:36:09,464][14252] Avg episode reward: 24.201, avg true_objective: 10.344 [2023-02-23 15:36:09,533][14252] Num frames 7300... [2023-02-23 15:36:09,650][14252] Num frames 7400... [2023-02-23 15:36:09,766][14252] Num frames 7500... [2023-02-23 15:36:09,877][14252] Num frames 7600... [2023-02-23 15:36:09,998][14252] Num frames 7700... [2023-02-23 15:36:10,120][14252] Num frames 7800... [2023-02-23 15:36:10,239][14252] Num frames 7900... [2023-02-23 15:36:10,364][14252] Num frames 8000... [2023-02-23 15:36:10,487][14252] Num frames 8100... [2023-02-23 15:36:10,611][14252] Num frames 8200... [2023-02-23 15:36:10,734][14252] Num frames 8300... [2023-02-23 15:36:10,867][14252] Num frames 8400... [2023-02-23 15:36:10,995][14252] Num frames 8500... [2023-02-23 15:36:11,107][14252] Avg episode rewards: #0: 25.434, true rewards: #0: 10.684 [2023-02-23 15:36:11,108][14252] Avg episode reward: 25.434, avg true_objective: 10.684 [2023-02-23 15:36:11,176][14252] Num frames 8600... [2023-02-23 15:36:11,292][14252] Num frames 8700... [2023-02-23 15:36:11,412][14252] Num frames 8800... [2023-02-23 15:36:11,528][14252] Num frames 8900... [2023-02-23 15:36:11,629][14252] Avg episode rewards: #0: 23.368, true rewards: #0: 9.923 [2023-02-23 15:36:11,632][14252] Avg episode reward: 23.368, avg true_objective: 9.923 [2023-02-23 15:36:11,711][14252] Num frames 9000... [2023-02-23 15:36:11,822][14252] Num frames 9100... [2023-02-23 15:36:11,935][14252] Num frames 9200... [2023-02-23 15:36:12,056][14252] Num frames 9300... [2023-02-23 15:36:12,172][14252] Num frames 9400... [2023-02-23 15:36:12,285][14252] Num frames 9500... [2023-02-23 15:36:12,406][14252] Num frames 9600... [2023-02-23 15:36:12,527][14252] Num frames 9700... [2023-02-23 15:36:12,604][14252] Avg episode rewards: #0: 22.512, true rewards: #0: 9.712 [2023-02-23 15:36:12,605][14252] Avg episode reward: 22.512, avg true_objective: 9.712 [2023-02-23 15:37:09,989][14252] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2023-02-23 15:39:08,475][14252] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-23 15:39:08,478][14252] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-23 15:39:08,483][14252] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-23 15:39:08,486][14252] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-23 15:39:08,487][14252] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-23 15:39:08,491][14252] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-23 15:39:08,492][14252] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-02-23 15:39:08,493][14252] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-23 15:39:08,494][14252] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-02-23 15:39:08,495][14252] Adding new argument 'hf_repository'='SuburbanLion/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2023-02-23 15:39:08,499][14252] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-23 15:39:08,500][14252] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-23 15:39:08,501][14252] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-23 15:39:08,503][14252] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-23 15:39:08,504][14252] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-23 15:39:08,541][14252] RunningMeanStd input shape: (3, 72, 128) [2023-02-23 15:39:08,544][14252] RunningMeanStd input shape: (1,) [2023-02-23 15:39:08,562][14252] ConvEncoder: input_channels=3 [2023-02-23 15:39:08,622][14252] Conv encoder output size: 512 [2023-02-23 15:39:08,624][14252] Policy head output size: 512 [2023-02-23 15:39:08,651][14252] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-23 15:39:09,349][14252] Num frames 100... [2023-02-23 15:39:09,512][14252] Num frames 200... [2023-02-23 15:39:09,678][14252] Num frames 300... [2023-02-23 15:39:09,834][14252] Num frames 400... [2023-02-23 15:39:09,990][14252] Num frames 500... [2023-02-23 15:39:10,147][14252] Num frames 600... [2023-02-23 15:39:10,313][14252] Num frames 700... [2023-02-23 15:39:10,469][14252] Num frames 800... [2023-02-23 15:39:10,631][14252] Num frames 900... [2023-02-23 15:39:10,795][14252] Num frames 1000... [2023-02-23 15:39:10,968][14252] Num frames 1100... [2023-02-23 15:39:11,134][14252] Num frames 1200... [2023-02-23 15:39:11,305][14252] Num frames 1300... [2023-02-23 15:39:11,397][14252] Avg episode rewards: #0: 32.210, true rewards: #0: 13.210 [2023-02-23 15:39:11,398][14252] Avg episode reward: 32.210, avg true_objective: 13.210 [2023-02-23 15:39:11,524][14252] Num frames 1400... [2023-02-23 15:39:11,700][14252] Num frames 1500... [2023-02-23 15:39:11,847][14252] Num frames 1600... [2023-02-23 15:39:11,963][14252] Num frames 1700... [2023-02-23 15:39:12,079][14252] Num frames 1800... [2023-02-23 15:39:12,248][14252] Avg episode rewards: #0: 20.985, true rewards: #0: 9.485 [2023-02-23 15:39:12,251][14252] Avg episode reward: 20.985, avg true_objective: 9.485 [2023-02-23 15:39:12,258][14252] Num frames 1900... [2023-02-23 15:39:12,384][14252] Num frames 2000... [2023-02-23 15:39:12,501][14252] Num frames 2100... [2023-02-23 15:39:12,621][14252] Num frames 2200... [2023-02-23 15:39:12,737][14252] Num frames 2300... [2023-02-23 15:39:12,848][14252] Num frames 2400... [2023-02-23 15:39:12,965][14252] Num frames 2500... [2023-02-23 15:39:13,082][14252] Num frames 2600... [2023-02-23 15:39:13,195][14252] Num frames 2700... [2023-02-23 15:39:13,317][14252] Num frames 2800... [2023-02-23 15:39:13,461][14252] Num frames 2900... [2023-02-23 15:39:13,575][14252] Num frames 3000... [2023-02-23 15:39:13,685][14252] Num frames 3100... [2023-02-23 15:39:13,805][14252] Num frames 3200... [2023-02-23 15:39:13,917][14252] Num frames 3300... [2023-02-23 15:39:14,028][14252] Num frames 3400... [2023-02-23 15:39:14,140][14252] Num frames 3500... [2023-02-23 15:39:14,299][14252] Avg episode rewards: #0: 28.643, true rewards: #0: 11.977 [2023-02-23 15:39:14,301][14252] Avg episode reward: 28.643, avg true_objective: 11.977 [2023-02-23 15:39:14,313][14252] Num frames 3600... [2023-02-23 15:39:14,438][14252] Num frames 3700... [2023-02-23 15:39:14,558][14252] Num frames 3800... [2023-02-23 15:39:14,672][14252] Num frames 3900... [2023-02-23 15:39:14,790][14252] Num frames 4000... [2023-02-23 15:39:14,908][14252] Num frames 4100... [2023-02-23 15:39:15,026][14252] Num frames 4200... [2023-02-23 15:39:15,148][14252] Num frames 4300... [2023-02-23 15:39:15,267][14252] Num frames 4400... [2023-02-23 15:39:15,385][14252] Avg episode rewards: #0: 26.392, true rewards: #0: 11.142 [2023-02-23 15:39:15,387][14252] Avg episode reward: 26.392, avg true_objective: 11.142 [2023-02-23 15:39:15,439][14252] Num frames 4500... [2023-02-23 15:39:15,555][14252] Num frames 4600... [2023-02-23 15:39:15,666][14252] Num frames 4700... [2023-02-23 15:39:15,788][14252] Num frames 4800... [2023-02-23 15:39:15,905][14252] Num frames 4900... [2023-02-23 15:39:16,003][14252] Avg episode rewards: #0: 23.274, true rewards: #0: 9.874 [2023-02-23 15:39:16,008][14252] Avg episode reward: 23.274, avg true_objective: 9.874 [2023-02-23 15:39:16,081][14252] Num frames 5000... [2023-02-23 15:39:16,193][14252] Num frames 5100... [2023-02-23 15:39:16,310][14252] Num frames 5200... [2023-02-23 15:39:16,434][14252] Num frames 5300... [2023-02-23 15:39:16,555][14252] Num frames 5400... [2023-02-23 15:39:16,677][14252] Num frames 5500... [2023-02-23 15:39:16,794][14252] Num frames 5600... [2023-02-23 15:39:16,912][14252] Num frames 5700... [2023-02-23 15:39:17,025][14252] Num frames 5800... [2023-02-23 15:39:17,144][14252] Num frames 5900... [2023-02-23 15:39:17,263][14252] Num frames 6000... [2023-02-23 15:39:17,380][14252] Num frames 6100... [2023-02-23 15:39:17,500][14252] Num frames 6200... [2023-02-23 15:39:17,626][14252] Num frames 6300... [2023-02-23 15:39:17,751][14252] Num frames 6400... [2023-02-23 15:39:17,862][14252] Num frames 6500... [2023-02-23 15:39:17,962][14252] Avg episode rewards: #0: 25.728, true rewards: #0: 10.895 [2023-02-23 15:39:17,964][14252] Avg episode reward: 25.728, avg true_objective: 10.895 [2023-02-23 15:39:18,037][14252] Num frames 6600... [2023-02-23 15:39:18,148][14252] Num frames 6700... [2023-02-23 15:39:18,259][14252] Num frames 6800... [2023-02-23 15:39:18,373][14252] Num frames 6900... [2023-02-23 15:39:18,495][14252] Num frames 7000... [2023-02-23 15:39:18,615][14252] Num frames 7100... [2023-02-23 15:39:18,730][14252] Num frames 7200... [2023-02-23 15:39:18,845][14252] Num frames 7300... [2023-02-23 15:39:18,981][14252] Num frames 7400... [2023-02-23 15:39:19,094][14252] Num frames 7500... [2023-02-23 15:39:19,205][14252] Num frames 7600... [2023-02-23 15:39:19,330][14252] Num frames 7700... [2023-02-23 15:39:19,452][14252] Num frames 7800... [2023-02-23 15:39:19,577][14252] Num frames 7900... [2023-02-23 15:39:19,701][14252] Num frames 8000... [2023-02-23 15:39:19,822][14252] Num frames 8100... [2023-02-23 15:39:19,935][14252] Num frames 8200... [2023-02-23 15:39:20,050][14252] Num frames 8300... [2023-02-23 15:39:20,162][14252] Num frames 8400... [2023-02-23 15:39:20,276][14252] Num frames 8500... [2023-02-23 15:39:20,392][14252] Num frames 8600... [2023-02-23 15:39:20,491][14252] Avg episode rewards: #0: 30.053, true rewards: #0: 12.339 [2023-02-23 15:39:20,493][14252] Avg episode reward: 30.053, avg true_objective: 12.339 [2023-02-23 15:39:20,576][14252] Num frames 8700... [2023-02-23 15:39:20,688][14252] Num frames 8800... [2023-02-23 15:39:20,812][14252] Num frames 8900... [2023-02-23 15:39:20,933][14252] Num frames 9000... [2023-02-23 15:39:21,051][14252] Num frames 9100... [2023-02-23 15:39:21,171][14252] Num frames 9200... [2023-02-23 15:39:21,243][14252] Avg episode rewards: #0: 27.516, true rewards: #0: 11.516 [2023-02-23 15:39:21,245][14252] Avg episode reward: 27.516, avg true_objective: 11.516 [2023-02-23 15:39:21,350][14252] Num frames 9300... [2023-02-23 15:39:21,474][14252] Num frames 9400... [2023-02-23 15:39:21,592][14252] Num frames 9500... [2023-02-23 15:39:21,715][14252] Num frames 9600... [2023-02-23 15:39:21,853][14252] Num frames 9700... [2023-02-23 15:39:22,017][14252] Num frames 9800... [2023-02-23 15:39:22,179][14252] Num frames 9900... [2023-02-23 15:39:22,359][14252] Avg episode rewards: #0: 26.308, true rewards: #0: 11.086 [2023-02-23 15:39:22,362][14252] Avg episode reward: 26.308, avg true_objective: 11.086 [2023-02-23 15:39:22,417][14252] Num frames 10000... [2023-02-23 15:39:22,583][14252] Num frames 10100... [2023-02-23 15:39:22,756][14252] Num frames 10200... [2023-02-23 15:39:22,919][14252] Num frames 10300... [2023-02-23 15:39:23,082][14252] Num frames 10400... [2023-02-23 15:39:23,243][14252] Num frames 10500... [2023-02-23 15:39:23,406][14252] Num frames 10600... [2023-02-23 15:39:23,567][14252] Num frames 10700... [2023-02-23 15:39:23,738][14252] Num frames 10800... [2023-02-23 15:39:23,910][14252] Num frames 10900... [2023-02-23 15:39:24,081][14252] Num frames 11000... [2023-02-23 15:39:24,253][14252] Num frames 11100... [2023-02-23 15:39:24,426][14252] Num frames 11200... [2023-02-23 15:39:24,606][14252] Num frames 11300... [2023-02-23 15:39:24,775][14252] Num frames 11400... [2023-02-23 15:39:24,941][14252] Num frames 11500... [2023-02-23 15:39:25,104][14252] Num frames 11600... [2023-02-23 15:39:25,268][14252] Num frames 11700... [2023-02-23 15:39:25,420][14252] Num frames 11800... [2023-02-23 15:39:25,545][14252] Num frames 11900... [2023-02-23 15:39:25,675][14252] Num frames 12000... [2023-02-23 15:39:25,735][14252] Avg episode rewards: #0: 29.402, true rewards: #0: 12.002 [2023-02-23 15:39:25,736][14252] Avg episode reward: 29.402, avg true_objective: 12.002 [2023-02-23 15:40:37,283][14252] Replay video saved to /content/train_dir/default_experiment/replay.mp4! |