File size: 99,429 Bytes
e94cea0 |
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 |
[2023-02-25 03:12:16,593][00684] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-25 03:12:16,597][00684] Rollout worker 0 uses device cpu [2023-02-25 03:12:16,599][00684] Rollout worker 1 uses device cpu [2023-02-25 03:12:16,600][00684] Rollout worker 2 uses device cpu [2023-02-25 03:12:16,601][00684] Rollout worker 3 uses device cpu [2023-02-25 03:12:16,603][00684] Rollout worker 4 uses device cpu [2023-02-25 03:12:16,605][00684] Rollout worker 5 uses device cpu [2023-02-25 03:12:16,606][00684] Rollout worker 6 uses device cpu [2023-02-25 03:12:16,608][00684] Rollout worker 7 uses device cpu [2023-02-25 03:12:16,876][00684] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-25 03:12:16,879][00684] InferenceWorker_p0-w0: min num requests: 2 [2023-02-25 03:12:16,931][00684] Starting all processes... [2023-02-25 03:12:16,934][00684] Starting process learner_proc0 [2023-02-25 03:12:17,035][00684] Starting all processes... [2023-02-25 03:12:17,068][00684] Starting process inference_proc0-0 [2023-02-25 03:12:17,069][00684] Starting process rollout_proc0 [2023-02-25 03:12:17,072][00684] Starting process rollout_proc1 [2023-02-25 03:12:17,101][00684] Starting process rollout_proc2 [2023-02-25 03:12:17,101][00684] Starting process rollout_proc3 [2023-02-25 03:12:17,101][00684] Starting process rollout_proc4 [2023-02-25 03:12:17,101][00684] Starting process rollout_proc5 [2023-02-25 03:12:17,102][00684] Starting process rollout_proc6 [2023-02-25 03:12:17,102][00684] Starting process rollout_proc7 [2023-02-25 03:12:29,112][10724] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-25 03:12:29,114][10724] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-25 03:12:29,528][10739] Worker 0 uses CPU cores [0] [2023-02-25 03:12:29,558][10745] Worker 2 uses CPU cores [0] [2023-02-25 03:12:29,614][10749] Worker 5 uses CPU cores [1] [2023-02-25 03:12:29,772][10740] Worker 1 uses CPU cores [1] [2023-02-25 03:12:29,830][10738] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-25 03:12:29,832][10738] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-25 03:12:29,841][10747] Worker 3 uses CPU cores [1] [2023-02-25 03:12:29,876][10746] Worker 4 uses CPU cores [0] [2023-02-25 03:12:29,896][10750] Worker 7 uses CPU cores [1] [2023-02-25 03:12:30,041][10748] Worker 6 uses CPU cores [0] [2023-02-25 03:12:30,366][10738] Num visible devices: 1 [2023-02-25 03:12:30,368][10724] Num visible devices: 1 [2023-02-25 03:12:30,370][10724] Starting seed is not provided [2023-02-25 03:12:30,370][10724] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-25 03:12:30,370][10724] Initializing actor-critic model on device cuda:0 [2023-02-25 03:12:30,370][10724] RunningMeanStd input shape: (3, 72, 128) [2023-02-25 03:12:30,372][10724] RunningMeanStd input shape: (1,) [2023-02-25 03:12:30,394][10724] ConvEncoder: input_channels=3 [2023-02-25 03:12:30,728][10724] Conv encoder output size: 512 [2023-02-25 03:12:30,728][10724] Policy head output size: 512 [2023-02-25 03:12:30,782][10724] Created Actor Critic model with architecture: [2023-02-25 03:12:30,782][10724] 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) ) ) [2023-02-25 03:12:36,864][00684] Heartbeat connected on Batcher_0 [2023-02-25 03:12:36,877][00684] Heartbeat connected on InferenceWorker_p0-w0 [2023-02-25 03:12:36,893][00684] Heartbeat connected on RolloutWorker_w0 [2023-02-25 03:12:36,898][00684] Heartbeat connected on RolloutWorker_w1 [2023-02-25 03:12:36,902][00684] Heartbeat connected on RolloutWorker_w2 [2023-02-25 03:12:36,913][00684] Heartbeat connected on RolloutWorker_w4 [2023-02-25 03:12:36,914][00684] Heartbeat connected on RolloutWorker_w3 [2023-02-25 03:12:36,917][00684] Heartbeat connected on RolloutWorker_w5 [2023-02-25 03:12:36,921][00684] Heartbeat connected on RolloutWorker_w6 [2023-02-25 03:12:36,926][00684] Heartbeat connected on RolloutWorker_w7 [2023-02-25 03:12:38,481][10724] Using optimizer <class 'torch.optim.adam.Adam'> [2023-02-25 03:12:38,482][10724] No checkpoints found [2023-02-25 03:12:38,482][10724] Did not load from checkpoint, starting from scratch! [2023-02-25 03:12:38,482][10724] Initialized policy 0 weights for model version 0 [2023-02-25 03:12:38,487][10724] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-25 03:12:38,494][10724] LearnerWorker_p0 finished initialization! [2023-02-25 03:12:38,495][00684] Heartbeat connected on LearnerWorker_p0 [2023-02-25 03:12:38,707][10738] RunningMeanStd input shape: (3, 72, 128) [2023-02-25 03:12:38,708][10738] RunningMeanStd input shape: (1,) [2023-02-25 03:12:38,721][10738] ConvEncoder: input_channels=3 [2023-02-25 03:12:38,821][10738] Conv encoder output size: 512 [2023-02-25 03:12:38,821][10738] Policy head output size: 512 [2023-02-25 03:12:38,900][00684] 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) [2023-02-25 03:12:41,239][00684] Inference worker 0-0 is ready! [2023-02-25 03:12:41,250][00684] All inference workers are ready! Signal rollout workers to start! [2023-02-25 03:12:41,406][10748] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,414][10739] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,396][10745] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,437][10750] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,439][10749] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,441][10740] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,450][10747] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:41,463][10746] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:12:43,334][10745] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,336][10739] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,347][10748] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,439][10750] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,453][10747] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,460][10740] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,468][10749] Decorrelating experience for 0 frames... [2023-02-25 03:12:43,900][00684] 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) [2023-02-25 03:12:44,655][10739] Decorrelating experience for 32 frames... [2023-02-25 03:12:44,678][10745] Decorrelating experience for 32 frames... [2023-02-25 03:12:44,692][10750] Decorrelating experience for 32 frames... [2023-02-25 03:12:44,708][10747] Decorrelating experience for 32 frames... [2023-02-25 03:12:44,921][10746] Decorrelating experience for 0 frames... [2023-02-25 03:12:46,136][10748] Decorrelating experience for 32 frames... [2023-02-25 03:12:46,403][10740] Decorrelating experience for 32 frames... [2023-02-25 03:12:46,433][10749] Decorrelating experience for 32 frames... [2023-02-25 03:12:46,464][10739] Decorrelating experience for 64 frames... [2023-02-25 03:12:46,470][10745] Decorrelating experience for 64 frames... [2023-02-25 03:12:46,696][10750] Decorrelating experience for 64 frames... [2023-02-25 03:12:47,810][10747] Decorrelating experience for 64 frames... [2023-02-25 03:12:47,949][10740] Decorrelating experience for 64 frames... [2023-02-25 03:12:48,022][10749] Decorrelating experience for 64 frames... [2023-02-25 03:12:48,152][10746] Decorrelating experience for 32 frames... [2023-02-25 03:12:48,474][10748] Decorrelating experience for 64 frames... [2023-02-25 03:12:48,490][10739] Decorrelating experience for 96 frames... [2023-02-25 03:12:48,497][10745] Decorrelating experience for 96 frames... [2023-02-25 03:12:48,901][00684] 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) [2023-02-25 03:12:49,020][10747] Decorrelating experience for 96 frames... [2023-02-25 03:12:49,093][10750] Decorrelating experience for 96 frames... [2023-02-25 03:12:49,230][10740] Decorrelating experience for 96 frames... [2023-02-25 03:12:49,662][10746] Decorrelating experience for 64 frames... [2023-02-25 03:12:49,969][10749] Decorrelating experience for 96 frames... [2023-02-25 03:12:50,047][10748] Decorrelating experience for 96 frames... [2023-02-25 03:12:50,314][10746] Decorrelating experience for 96 frames... [2023-02-25 03:12:53,900][00684] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 60.5. Samples: 908. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-25 03:12:53,903][00684] Avg episode reward: [(0, '1.184')] [2023-02-25 03:12:55,020][10724] Signal inference workers to stop experience collection... [2023-02-25 03:12:55,038][10738] InferenceWorker_p0-w0: stopping experience collection [2023-02-25 03:12:57,711][10724] Signal inference workers to resume experience collection... [2023-02-25 03:12:57,713][10738] InferenceWorker_p0-w0: resuming experience collection [2023-02-25 03:12:58,901][00684] Fps is (10 sec: 409.6, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 117.1. Samples: 2342. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-02-25 03:12:58,905][00684] Avg episode reward: [(0, '1.904')] [2023-02-25 03:13:03,900][00684] Fps is (10 sec: 2048.0, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 20480. Throughput: 0: 186.9. Samples: 4672. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-25 03:13:03,905][00684] Avg episode reward: [(0, '3.482')] [2023-02-25 03:13:08,900][00684] Fps is (10 sec: 3276.8, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 36864. Throughput: 0: 317.2. Samples: 9516. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:13:08,908][00684] Avg episode reward: [(0, '3.869')] [2023-02-25 03:13:09,468][10738] Updated weights for policy 0, policy_version 10 (0.0552) [2023-02-25 03:13:13,900][00684] Fps is (10 sec: 4096.0, 60 sec: 1755.4, 300 sec: 1755.4). Total num frames: 61440. Throughput: 0: 370.3. Samples: 12962. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:13:13,904][00684] Avg episode reward: [(0, '4.234')] [2023-02-25 03:13:18,245][10738] Updated weights for policy 0, policy_version 20 (0.0026) [2023-02-25 03:13:18,901][00684] Fps is (10 sec: 4505.4, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 498.8. Samples: 19954. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:13:18,906][00684] Avg episode reward: [(0, '4.389')] [2023-02-25 03:13:23,900][00684] Fps is (10 sec: 3276.8, 60 sec: 2093.5, 300 sec: 2093.5). Total num frames: 94208. Throughput: 0: 544.4. Samples: 24500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:13:23,904][00684] Avg episode reward: [(0, '4.421')] [2023-02-25 03:13:28,900][00684] Fps is (10 sec: 3277.0, 60 sec: 2293.8, 300 sec: 2293.8). Total num frames: 114688. Throughput: 0: 595.4. Samples: 26792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:13:28,903][00684] Avg episode reward: [(0, '4.384')] [2023-02-25 03:13:28,915][10724] Saving new best policy, reward=4.384! [2023-02-25 03:13:30,528][10738] Updated weights for policy 0, policy_version 30 (0.0048) [2023-02-25 03:13:33,905][00684] Fps is (10 sec: 4094.1, 60 sec: 2457.4, 300 sec: 2457.4). Total num frames: 135168. Throughput: 0: 741.5. Samples: 33370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:13:33,916][00684] Avg episode reward: [(0, '4.446')] [2023-02-25 03:13:33,919][10724] Saving new best policy, reward=4.446! [2023-02-25 03:13:38,908][00684] Fps is (10 sec: 4093.0, 60 sec: 2593.8, 300 sec: 2593.8). Total num frames: 155648. Throughput: 0: 864.2. Samples: 39804. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:13:38,916][00684] Avg episode reward: [(0, '4.443')] [2023-02-25 03:13:40,466][10738] Updated weights for policy 0, policy_version 40 (0.0013) [2023-02-25 03:13:43,900][00684] Fps is (10 sec: 3688.1, 60 sec: 2867.2, 300 sec: 2646.6). Total num frames: 172032. Throughput: 0: 881.5. Samples: 42010. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:13:43,904][00684] Avg episode reward: [(0, '4.415')] [2023-02-25 03:13:48,900][00684] Fps is (10 sec: 3279.2, 60 sec: 3140.3, 300 sec: 2691.7). Total num frames: 188416. Throughput: 0: 930.9. Samples: 46564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:13:48,907][00684] Avg episode reward: [(0, '4.374')] [2023-02-25 03:13:51,910][10738] Updated weights for policy 0, policy_version 50 (0.0012) [2023-02-25 03:13:53,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 2839.9). Total num frames: 212992. Throughput: 0: 975.5. Samples: 53414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:13:53,902][00684] Avg episode reward: [(0, '4.397')] [2023-02-25 03:13:58,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 2867.2). Total num frames: 229376. Throughput: 0: 975.4. Samples: 56856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:13:58,908][00684] Avg episode reward: [(0, '4.462')] [2023-02-25 03:13:58,919][10724] Saving new best policy, reward=4.462! [2023-02-25 03:14:03,903][00684] Fps is (10 sec: 2866.5, 60 sec: 3686.3, 300 sec: 2843.0). Total num frames: 241664. Throughput: 0: 907.3. Samples: 60782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:03,907][00684] Avg episode reward: [(0, '4.507')] [2023-02-25 03:14:03,912][10724] Saving new best policy, reward=4.507! [2023-02-25 03:14:04,736][10738] Updated weights for policy 0, policy_version 60 (0.0017) [2023-02-25 03:14:08,903][00684] Fps is (10 sec: 2047.4, 60 sec: 3549.7, 300 sec: 2776.1). Total num frames: 249856. Throughput: 0: 871.8. Samples: 63732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:08,906][00684] Avg episode reward: [(0, '4.458')] [2023-02-25 03:14:08,917][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000061_249856.pth... [2023-02-25 03:14:13,900][00684] Fps is (10 sec: 2458.2, 60 sec: 3413.3, 300 sec: 2802.5). Total num frames: 266240. Throughput: 0: 858.2. Samples: 65410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:14:13,902][00684] Avg episode reward: [(0, '4.465')] [2023-02-25 03:14:17,747][10738] Updated weights for policy 0, policy_version 70 (0.0023) [2023-02-25 03:14:18,901][00684] Fps is (10 sec: 4097.1, 60 sec: 3481.6, 300 sec: 2908.2). Total num frames: 290816. Throughput: 0: 852.4. Samples: 71724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:14:18,903][00684] Avg episode reward: [(0, '4.602')] [2023-02-25 03:14:18,912][10724] Saving new best policy, reward=4.602! [2023-02-25 03:14:23,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 2964.7). Total num frames: 311296. Throughput: 0: 856.8. Samples: 78352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:23,903][00684] Avg episode reward: [(0, '4.461')] [2023-02-25 03:14:28,850][10738] Updated weights for policy 0, policy_version 80 (0.0028) [2023-02-25 03:14:28,900][00684] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 855.7. Samples: 80518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:14:28,904][00684] Avg episode reward: [(0, '4.354')] [2023-02-25 03:14:33,901][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.9, 300 sec: 2991.9). Total num frames: 344064. Throughput: 0: 854.8. Samples: 85028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:33,907][00684] Avg episode reward: [(0, '4.342')] [2023-02-25 03:14:38,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3482.0, 300 sec: 3037.9). Total num frames: 364544. Throughput: 0: 852.4. Samples: 91770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:38,905][00684] Avg episode reward: [(0, '4.408')] [2023-02-25 03:14:39,268][10738] Updated weights for policy 0, policy_version 90 (0.0019) [2023-02-25 03:14:43,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3080.2). Total num frames: 385024. Throughput: 0: 852.3. Samples: 95210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:43,903][00684] Avg episode reward: [(0, '4.442')] [2023-02-25 03:14:48,902][00684] Fps is (10 sec: 3685.9, 60 sec: 3549.8, 300 sec: 3087.7). Total num frames: 401408. Throughput: 0: 875.8. Samples: 100190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:48,909][00684] Avg episode reward: [(0, '4.586')] [2023-02-25 03:14:51,176][10738] Updated weights for policy 0, policy_version 100 (0.0039) [2023-02-25 03:14:53,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3094.8). Total num frames: 417792. Throughput: 0: 914.7. Samples: 104890. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:14:53,902][00684] Avg episode reward: [(0, '4.507')] [2023-02-25 03:14:58,900][00684] Fps is (10 sec: 4096.6, 60 sec: 3549.9, 300 sec: 3159.8). Total num frames: 442368. Throughput: 0: 954.0. Samples: 108340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:14:58,909][00684] Avg episode reward: [(0, '4.405')] [2023-02-25 03:15:00,391][10738] Updated weights for policy 0, policy_version 110 (0.0016) [2023-02-25 03:15:03,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3686.5, 300 sec: 3192.1). Total num frames: 462848. Throughput: 0: 968.0. Samples: 115282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:03,903][00684] Avg episode reward: [(0, '4.505')] [2023-02-25 03:15:08,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3167.6). Total num frames: 475136. Throughput: 0: 921.7. Samples: 119830. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:15:08,906][00684] Avg episode reward: [(0, '4.511')] [2023-02-25 03:15:13,051][10738] Updated weights for policy 0, policy_version 120 (0.0026) [2023-02-25 03:15:13,901][00684] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3197.5). Total num frames: 495616. Throughput: 0: 921.4. Samples: 121980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:15:13,902][00684] Avg episode reward: [(0, '4.640')] [2023-02-25 03:15:13,913][10724] Saving new best policy, reward=4.640! [2023-02-25 03:15:18,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3225.6). Total num frames: 516096. Throughput: 0: 961.6. Samples: 128302. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:15:18,902][00684] Avg episode reward: [(0, '4.604')] [2023-02-25 03:15:22,028][10738] Updated weights for policy 0, policy_version 130 (0.0013) [2023-02-25 03:15:23,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3252.0). Total num frames: 536576. Throughput: 0: 957.9. Samples: 134876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:15:23,907][00684] Avg episode reward: [(0, '4.503')] [2023-02-25 03:15:28,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3252.7). Total num frames: 552960. Throughput: 0: 930.5. Samples: 137084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:28,903][00684] Avg episode reward: [(0, '4.521')] [2023-02-25 03:15:33,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3253.4). Total num frames: 569344. Throughput: 0: 917.8. Samples: 141488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:33,909][00684] Avg episode reward: [(0, '4.579')] [2023-02-25 03:15:34,416][10738] Updated weights for policy 0, policy_version 140 (0.0017) [2023-02-25 03:15:38,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3299.6). Total num frames: 593920. Throughput: 0: 966.5. Samples: 148382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:15:38,902][00684] Avg episode reward: [(0, '4.542')] [2023-02-25 03:15:43,665][10738] Updated weights for policy 0, policy_version 150 (0.0018) [2023-02-25 03:15:43,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3321.1). Total num frames: 614400. Throughput: 0: 968.3. Samples: 151914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:43,906][00684] Avg episode reward: [(0, '4.535')] [2023-02-25 03:15:48,901][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3298.4). Total num frames: 626688. Throughput: 0: 925.1. Samples: 156912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:48,907][00684] Avg episode reward: [(0, '4.429')] [2023-02-25 03:15:53,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3318.8). Total num frames: 647168. Throughput: 0: 931.7. Samples: 161756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:15:53,909][00684] Avg episode reward: [(0, '4.431')] [2023-02-25 03:15:55,697][10738] Updated weights for policy 0, policy_version 160 (0.0012) [2023-02-25 03:15:58,901][00684] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3338.2). Total num frames: 667648. Throughput: 0: 960.7. Samples: 165210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:15:58,908][00684] Avg episode reward: [(0, '4.584')] [2023-02-25 03:16:03,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3356.7). Total num frames: 688128. Throughput: 0: 975.0. Samples: 172176. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:16:03,908][00684] Avg episode reward: [(0, '4.682')] [2023-02-25 03:16:03,910][10724] Saving new best policy, reward=4.682! [2023-02-25 03:16:05,406][10738] Updated weights for policy 0, policy_version 170 (0.0012) [2023-02-25 03:16:08,900][00684] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3354.8). Total num frames: 704512. Throughput: 0: 926.9. Samples: 176586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:16:08,902][00684] Avg episode reward: [(0, '4.631')] [2023-02-25 03:16:08,920][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth... [2023-02-25 03:16:13,902][00684] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3353.0). Total num frames: 720896. Throughput: 0: 925.8. Samples: 178746. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:16:13,910][00684] Avg episode reward: [(0, '4.590')] [2023-02-25 03:16:18,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3332.7). Total num frames: 733184. Throughput: 0: 924.6. Samples: 183094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:16:18,905][00684] Avg episode reward: [(0, '4.454')] [2023-02-25 03:16:19,660][10738] Updated weights for policy 0, policy_version 180 (0.0022) [2023-02-25 03:16:23,900][00684] Fps is (10 sec: 2867.6, 60 sec: 3549.9, 300 sec: 3331.4). Total num frames: 749568. Throughput: 0: 871.2. Samples: 187588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:16:23,916][00684] Avg episode reward: [(0, '4.519')] [2023-02-25 03:16:28,901][00684] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3312.4). Total num frames: 761856. Throughput: 0: 841.2. Samples: 189770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:16:28,908][00684] Avg episode reward: [(0, '4.585')] [2023-02-25 03:16:33,148][10738] Updated weights for policy 0, policy_version 190 (0.0039) [2023-02-25 03:16:33,903][00684] Fps is (10 sec: 2866.5, 60 sec: 3481.5, 300 sec: 3311.6). Total num frames: 778240. Throughput: 0: 829.3. Samples: 194232. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:16:33,906][00684] Avg episode reward: [(0, '4.844')] [2023-02-25 03:16:33,911][10724] Saving new best policy, reward=4.844! [2023-02-25 03:16:38,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3345.1). Total num frames: 802816. Throughput: 0: 869.6. Samples: 200886. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:16:38,903][00684] Avg episode reward: [(0, '4.890')] [2023-02-25 03:16:38,918][10724] Saving new best policy, reward=4.890! [2023-02-25 03:16:42,147][10738] Updated weights for policy 0, policy_version 200 (0.0015) [2023-02-25 03:16:43,901][00684] Fps is (10 sec: 4506.5, 60 sec: 3481.6, 300 sec: 3360.4). Total num frames: 823296. Throughput: 0: 867.5. Samples: 204248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:16:43,905][00684] Avg episode reward: [(0, '4.621')] [2023-02-25 03:16:48,901][00684] Fps is (10 sec: 3686.2, 60 sec: 3549.8, 300 sec: 3358.7). Total num frames: 839680. Throughput: 0: 825.9. Samples: 209340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:16:48,907][00684] Avg episode reward: [(0, '4.538')] [2023-02-25 03:16:53,901][00684] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3357.1). Total num frames: 856064. Throughput: 0: 831.4. Samples: 213998. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:16:53,908][00684] Avg episode reward: [(0, '4.601')] [2023-02-25 03:16:54,623][10738] Updated weights for policy 0, policy_version 210 (0.0019) [2023-02-25 03:16:58,900][00684] Fps is (10 sec: 3686.6, 60 sec: 3481.6, 300 sec: 3371.3). Total num frames: 876544. Throughput: 0: 860.4. Samples: 217462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:16:58,903][00684] Avg episode reward: [(0, '4.448')] [2023-02-25 03:17:03,900][00684] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3385.0). Total num frames: 897024. Throughput: 0: 918.2. Samples: 224412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:03,902][00684] Avg episode reward: [(0, '4.440')] [2023-02-25 03:17:03,923][10738] Updated weights for policy 0, policy_version 220 (0.0025) [2023-02-25 03:17:08,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3383.0). Total num frames: 913408. Throughput: 0: 920.0. Samples: 228986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:08,910][00684] Avg episode reward: [(0, '4.531')] [2023-02-25 03:17:13,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3381.1). Total num frames: 929792. Throughput: 0: 920.7. Samples: 231202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:17:13,904][00684] Avg episode reward: [(0, '4.494')] [2023-02-25 03:17:15,971][10738] Updated weights for policy 0, policy_version 230 (0.0036) [2023-02-25 03:17:18,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3408.5). Total num frames: 954368. Throughput: 0: 961.3. Samples: 237488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:17:18,903][00684] Avg episode reward: [(0, '4.482')] [2023-02-25 03:17:23,904][00684] Fps is (10 sec: 4504.1, 60 sec: 3754.4, 300 sec: 3420.5). Total num frames: 974848. Throughput: 0: 963.8. Samples: 244262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:23,907][00684] Avg episode reward: [(0, '4.529')] [2023-02-25 03:17:26,212][10738] Updated weights for policy 0, policy_version 240 (0.0016) [2023-02-25 03:17:28,907][00684] Fps is (10 sec: 3274.7, 60 sec: 3754.3, 300 sec: 3403.8). Total num frames: 987136. Throughput: 0: 936.5. Samples: 246398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:17:28,914][00684] Avg episode reward: [(0, '4.559')] [2023-02-25 03:17:33,900][00684] Fps is (10 sec: 3277.9, 60 sec: 3823.1, 300 sec: 3415.6). Total num frames: 1007616. Throughput: 0: 923.2. Samples: 250884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:33,908][00684] Avg episode reward: [(0, '4.622')] [2023-02-25 03:17:37,434][10738] Updated weights for policy 0, policy_version 250 (0.0019) [2023-02-25 03:17:38,900][00684] Fps is (10 sec: 4098.6, 60 sec: 3754.7, 300 sec: 3485.1). Total num frames: 1028096. Throughput: 0: 966.3. Samples: 257482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:17:38,903][00684] Avg episode reward: [(0, '4.766')] [2023-02-25 03:17:43,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 964.4. Samples: 260860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:43,903][00684] Avg episode reward: [(0, '4.908')] [2023-02-25 03:17:43,910][10724] Saving new best policy, reward=4.908! [2023-02-25 03:17:48,392][10738] Updated weights for policy 0, policy_version 260 (0.0024) [2023-02-25 03:17:48,901][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 923.2. Samples: 265956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:48,905][00684] Avg episode reward: [(0, '5.070')] [2023-02-25 03:17:48,923][10724] Saving new best policy, reward=5.070! [2023-02-25 03:17:53,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1081344. Throughput: 0: 921.9. Samples: 270472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:17:53,903][00684] Avg episode reward: [(0, '4.888')] [2023-02-25 03:17:58,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1101824. Throughput: 0: 949.5. Samples: 273928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:17:58,907][00684] Avg episode reward: [(0, '4.373')] [2023-02-25 03:17:58,993][10738] Updated weights for policy 0, policy_version 270 (0.0020) [2023-02-25 03:18:03,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1126400. Throughput: 0: 964.7. Samples: 280900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:18:03,906][00684] Avg episode reward: [(0, '4.430')] [2023-02-25 03:18:08,901][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1138688. Throughput: 0: 914.8. Samples: 285426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:08,910][00684] Avg episode reward: [(0, '4.464')] [2023-02-25 03:18:08,925][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000278_1138688.pth... [2023-02-25 03:18:09,129][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000061_249856.pth [2023-02-25 03:18:11,112][10738] Updated weights for policy 0, policy_version 280 (0.0014) [2023-02-25 03:18:13,901][00684] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1155072. Throughput: 0: 913.1. Samples: 287480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:13,903][00684] Avg episode reward: [(0, '4.678')] [2023-02-25 03:18:18,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1179648. Throughput: 0: 952.6. Samples: 293750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:18:18,908][00684] Avg episode reward: [(0, '4.773')] [2023-02-25 03:18:20,535][10738] Updated weights for policy 0, policy_version 290 (0.0013) [2023-02-25 03:18:23,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3754.9, 300 sec: 3679.5). Total num frames: 1200128. Throughput: 0: 956.0. Samples: 300500. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:23,904][00684] Avg episode reward: [(0, '4.699')] [2023-02-25 03:18:28,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3755.1, 300 sec: 3651.7). Total num frames: 1212416. Throughput: 0: 922.2. Samples: 302358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:28,909][00684] Avg episode reward: [(0, '4.841')] [2023-02-25 03:18:33,900][00684] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1224704. Throughput: 0: 885.7. Samples: 305814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:18:33,903][00684] Avg episode reward: [(0, '4.724')] [2023-02-25 03:18:35,677][10738] Updated weights for policy 0, policy_version 300 (0.0013) [2023-02-25 03:18:38,900][00684] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 1236992. Throughput: 0: 868.4. Samples: 309552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:18:38,907][00684] Avg episode reward: [(0, '4.774')] [2023-02-25 03:18:43,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 1257472. Throughput: 0: 865.1. Samples: 312858. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:18:43,903][00684] Avg episode reward: [(0, '4.744')] [2023-02-25 03:18:45,703][10738] Updated weights for policy 0, policy_version 310 (0.0017) [2023-02-25 03:18:48,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 1277952. Throughput: 0: 863.2. Samples: 319742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:18:48,908][00684] Avg episode reward: [(0, '4.617')] [2023-02-25 03:18:53,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 1294336. Throughput: 0: 860.0. Samples: 324124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:53,902][00684] Avg episode reward: [(0, '4.588')] [2023-02-25 03:18:58,265][10738] Updated weights for policy 0, policy_version 320 (0.0030) [2023-02-25 03:18:58,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 1310720. Throughput: 0: 862.1. Samples: 326276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:18:58,903][00684] Avg episode reward: [(0, '4.577')] [2023-02-25 03:19:03,901][00684] Fps is (10 sec: 4095.8, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 1335296. Throughput: 0: 869.5. Samples: 332876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:03,903][00684] Avg episode reward: [(0, '4.786')] [2023-02-25 03:19:07,247][10738] Updated weights for policy 0, policy_version 330 (0.0014) [2023-02-25 03:19:08,904][00684] Fps is (10 sec: 4504.0, 60 sec: 3617.9, 300 sec: 3693.3). Total num frames: 1355776. Throughput: 0: 863.4. Samples: 339358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:08,907][00684] Avg episode reward: [(0, '4.774')] [2023-02-25 03:19:13,900][00684] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1368064. Throughput: 0: 870.2. Samples: 341516. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:19:13,903][00684] Avg episode reward: [(0, '4.671')] [2023-02-25 03:19:18,901][00684] Fps is (10 sec: 3277.9, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 1388544. Throughput: 0: 889.2. Samples: 345830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:18,903][00684] Avg episode reward: [(0, '4.441')] [2023-02-25 03:19:19,858][10738] Updated weights for policy 0, policy_version 340 (0.0038) [2023-02-25 03:19:23,901][00684] Fps is (10 sec: 4095.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1409024. Throughput: 0: 960.4. Samples: 352770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:23,907][00684] Avg episode reward: [(0, '4.452')] [2023-02-25 03:19:28,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 1429504. Throughput: 0: 962.8. Samples: 356184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:19:28,909][00684] Avg episode reward: [(0, '4.497')] [2023-02-25 03:19:29,653][10738] Updated weights for policy 0, policy_version 350 (0.0019) [2023-02-25 03:19:33,900][00684] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1445888. Throughput: 0: 914.1. Samples: 360878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:19:33,907][00684] Avg episode reward: [(0, '4.352')] [2023-02-25 03:19:38,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1462272. Throughput: 0: 928.1. Samples: 365888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:19:38,906][00684] Avg episode reward: [(0, '4.462')] [2023-02-25 03:19:41,214][10738] Updated weights for policy 0, policy_version 360 (0.0012) [2023-02-25 03:19:43,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 1486848. Throughput: 0: 955.5. Samples: 369274. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:43,906][00684] Avg episode reward: [(0, '4.568')] [2023-02-25 03:19:48,903][00684] Fps is (10 sec: 4504.5, 60 sec: 3822.8, 300 sec: 3693.3). Total num frames: 1507328. Throughput: 0: 964.3. Samples: 376272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:48,910][00684] Avg episode reward: [(0, '4.557')] [2023-02-25 03:19:51,718][10738] Updated weights for policy 0, policy_version 370 (0.0032) [2023-02-25 03:19:53,908][00684] Fps is (10 sec: 3274.4, 60 sec: 3754.2, 300 sec: 3651.6). Total num frames: 1519616. Throughput: 0: 914.6. Samples: 380520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:19:53,912][00684] Avg episode reward: [(0, '4.748')] [2023-02-25 03:19:58,900][00684] Fps is (10 sec: 2867.9, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1536000. Throughput: 0: 913.2. Samples: 382610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:19:58,908][00684] Avg episode reward: [(0, '4.792')] [2023-02-25 03:20:02,863][10738] Updated weights for policy 0, policy_version 380 (0.0017) [2023-02-25 03:20:03,900][00684] Fps is (10 sec: 4099.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1560576. Throughput: 0: 958.6. Samples: 388966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:20:03,908][00684] Avg episode reward: [(0, '4.753')] [2023-02-25 03:20:08,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3754.9, 300 sec: 3679.5). Total num frames: 1581056. Throughput: 0: 947.8. Samples: 395422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:08,905][00684] Avg episode reward: [(0, '4.741')] [2023-02-25 03:20:08,923][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth... [2023-02-25 03:20:09,060][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth [2023-02-25 03:20:13,905][00684] Fps is (10 sec: 3275.3, 60 sec: 3754.4, 300 sec: 3651.6). Total num frames: 1593344. Throughput: 0: 918.3. Samples: 397510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:13,916][00684] Avg episode reward: [(0, '4.656')] [2023-02-25 03:20:14,694][10738] Updated weights for policy 0, policy_version 390 (0.0019) [2023-02-25 03:20:18,901][00684] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1609728. Throughput: 0: 913.2. Samples: 401974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:20:18,903][00684] Avg episode reward: [(0, '4.762')] [2023-02-25 03:20:23,904][00684] Fps is (10 sec: 4096.4, 60 sec: 3754.5, 300 sec: 3665.5). Total num frames: 1634304. Throughput: 0: 954.1. Samples: 408824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:23,908][00684] Avg episode reward: [(0, '4.495')] [2023-02-25 03:20:24,471][10738] Updated weights for policy 0, policy_version 400 (0.0026) [2023-02-25 03:20:28,904][00684] Fps is (10 sec: 4504.1, 60 sec: 3754.4, 300 sec: 3679.4). Total num frames: 1654784. Throughput: 0: 956.6. Samples: 412324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:28,907][00684] Avg episode reward: [(0, '4.568')] [2023-02-25 03:20:33,900][00684] Fps is (10 sec: 3687.7, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1671168. Throughput: 0: 907.6. Samples: 417112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:33,910][00684] Avg episode reward: [(0, '4.618')] [2023-02-25 03:20:36,550][10738] Updated weights for policy 0, policy_version 410 (0.0022) [2023-02-25 03:20:38,901][00684] Fps is (10 sec: 2868.2, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1683456. Throughput: 0: 916.0. Samples: 421734. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:20:38,904][00684] Avg episode reward: [(0, '4.960')] [2023-02-25 03:20:43,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1699840. Throughput: 0: 917.1. Samples: 423878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:43,907][00684] Avg episode reward: [(0, '5.017')] [2023-02-25 03:20:48,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3413.5, 300 sec: 3610.0). Total num frames: 1712128. Throughput: 0: 871.5. Samples: 428182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:48,906][00684] Avg episode reward: [(0, '4.977')] [2023-02-25 03:20:50,516][10738] Updated weights for policy 0, policy_version 420 (0.0011) [2023-02-25 03:20:53,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3482.0, 300 sec: 3596.2). Total num frames: 1728512. Throughput: 0: 825.8. Samples: 432584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:20:53,903][00684] Avg episode reward: [(0, '4.810')] [2023-02-25 03:20:58,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 1744896. Throughput: 0: 826.4. Samples: 434696. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:20:58,902][00684] Avg episode reward: [(0, '4.618')] [2023-02-25 03:21:01,696][10738] Updated weights for policy 0, policy_version 430 (0.0022) [2023-02-25 03:21:03,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 1769472. Throughput: 0: 875.9. Samples: 441388. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:21:03,903][00684] Avg episode reward: [(0, '4.804')] [2023-02-25 03:21:08,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 1789952. Throughput: 0: 865.2. Samples: 447754. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:21:08,903][00684] Avg episode reward: [(0, '4.976')] [2023-02-25 03:21:12,988][10738] Updated weights for policy 0, policy_version 440 (0.0018) [2023-02-25 03:21:13,902][00684] Fps is (10 sec: 3276.3, 60 sec: 3481.8, 300 sec: 3623.9). Total num frames: 1802240. Throughput: 0: 835.5. Samples: 449922. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:21:13,906][00684] Avg episode reward: [(0, '4.829')] [2023-02-25 03:21:18,901][00684] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1822720. Throughput: 0: 827.7. Samples: 454360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:21:18,903][00684] Avg episode reward: [(0, '4.925')] [2023-02-25 03:21:23,373][10738] Updated weights for policy 0, policy_version 450 (0.0017) [2023-02-25 03:21:23,900][00684] Fps is (10 sec: 4096.6, 60 sec: 3481.8, 300 sec: 3665.6). Total num frames: 1843200. Throughput: 0: 877.5. Samples: 461220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:21:23,909][00684] Avg episode reward: [(0, '4.644')] [2023-02-25 03:21:28,901][00684] Fps is (10 sec: 4096.0, 60 sec: 3481.8, 300 sec: 3679.5). Total num frames: 1863680. Throughput: 0: 905.2. Samples: 464610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:21:28,903][00684] Avg episode reward: [(0, '4.526')] [2023-02-25 03:21:33,906][00684] Fps is (10 sec: 3275.0, 60 sec: 3413.0, 300 sec: 3637.7). Total num frames: 1875968. Throughput: 0: 910.9. Samples: 469178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:21:33,909][00684] Avg episode reward: [(0, '4.840')] [2023-02-25 03:21:35,562][10738] Updated weights for policy 0, policy_version 460 (0.0045) [2023-02-25 03:21:38,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1896448. Throughput: 0: 924.4. Samples: 474184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:21:38,904][00684] Avg episode reward: [(0, '4.891')] [2023-02-25 03:21:43,900][00684] Fps is (10 sec: 4098.2, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1916928. Throughput: 0: 955.0. Samples: 477672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:21:43,907][00684] Avg episode reward: [(0, '4.818')] [2023-02-25 03:21:44,931][10738] Updated weights for policy 0, policy_version 470 (0.0015) [2023-02-25 03:21:48,901][00684] Fps is (10 sec: 4095.7, 60 sec: 3754.6, 300 sec: 3665.6). Total num frames: 1937408. Throughput: 0: 956.7. Samples: 484442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:21:48,904][00684] Avg episode reward: [(0, '4.765')] [2023-02-25 03:21:53,903][00684] Fps is (10 sec: 3685.6, 60 sec: 3754.5, 300 sec: 3651.7). Total num frames: 1953792. Throughput: 0: 911.6. Samples: 488778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:21:53,905][00684] Avg episode reward: [(0, '4.740')] [2023-02-25 03:21:57,545][10738] Updated weights for policy 0, policy_version 480 (0.0043) [2023-02-25 03:21:58,900][00684] Fps is (10 sec: 3277.1, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1970176. Throughput: 0: 912.5. Samples: 490984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:21:58,909][00684] Avg episode reward: [(0, '4.806')] [2023-02-25 03:22:03,900][00684] Fps is (10 sec: 4096.9, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1994752. Throughput: 0: 962.1. Samples: 497654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:03,906][00684] Avg episode reward: [(0, '4.698')] [2023-02-25 03:22:06,355][10738] Updated weights for policy 0, policy_version 490 (0.0022) [2023-02-25 03:22:08,901][00684] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2015232. Throughput: 0: 950.6. Samples: 503998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:22:08,909][00684] Avg episode reward: [(0, '4.665')] [2023-02-25 03:22:08,918][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth... [2023-02-25 03:22:09,066][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000278_1138688.pth [2023-02-25 03:22:13,904][00684] Fps is (10 sec: 3275.6, 60 sec: 3754.5, 300 sec: 3637.8). Total num frames: 2027520. Throughput: 0: 922.9. Samples: 506144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:13,907][00684] Avg episode reward: [(0, '4.836')] [2023-02-25 03:22:18,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3624.0). Total num frames: 2043904. Throughput: 0: 920.4. Samples: 510592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:18,908][00684] Avg episode reward: [(0, '4.714')] [2023-02-25 03:22:18,997][10738] Updated weights for policy 0, policy_version 500 (0.0015) [2023-02-25 03:22:23,901][00684] Fps is (10 sec: 4097.4, 60 sec: 3754.7, 300 sec: 3665.7). Total num frames: 2068480. Throughput: 0: 963.5. Samples: 517542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:23,908][00684] Avg episode reward: [(0, '4.515')] [2023-02-25 03:22:28,248][10738] Updated weights for policy 0, policy_version 510 (0.0014) [2023-02-25 03:22:28,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2088960. Throughput: 0: 961.1. Samples: 520922. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:22:28,906][00684] Avg episode reward: [(0, '4.679')] [2023-02-25 03:22:33,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3755.0, 300 sec: 3637.8). Total num frames: 2101248. Throughput: 0: 916.8. Samples: 525698. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:22:33,910][00684] Avg episode reward: [(0, '4.766')] [2023-02-25 03:22:38,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2121728. Throughput: 0: 929.7. Samples: 530612. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:22:38,906][00684] Avg episode reward: [(0, '4.823')] [2023-02-25 03:22:40,392][10738] Updated weights for policy 0, policy_version 520 (0.0039) [2023-02-25 03:22:43,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2146304. Throughput: 0: 957.2. Samples: 534056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:43,906][00684] Avg episode reward: [(0, '4.762')] [2023-02-25 03:22:48,901][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2162688. Throughput: 0: 960.6. Samples: 540880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:22:48,906][00684] Avg episode reward: [(0, '4.607')] [2023-02-25 03:22:50,625][10738] Updated weights for policy 0, policy_version 530 (0.0012) [2023-02-25 03:22:53,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3651.7). Total num frames: 2179072. Throughput: 0: 911.6. Samples: 545022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:22:53,906][00684] Avg episode reward: [(0, '4.664')] [2023-02-25 03:22:58,901][00684] Fps is (10 sec: 2457.6, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2187264. Throughput: 0: 901.0. Samples: 546684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:22:58,908][00684] Avg episode reward: [(0, '4.664')] [2023-02-25 03:23:03,900][00684] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 2203648. Throughput: 0: 890.4. Samples: 550658. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:23:03,906][00684] Avg episode reward: [(0, '4.715')] [2023-02-25 03:23:05,416][10738] Updated weights for policy 0, policy_version 540 (0.0029) [2023-02-25 03:23:08,901][00684] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 2224128. Throughput: 0: 875.3. Samples: 556930. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:23:08,902][00684] Avg episode reward: [(0, '4.818')] [2023-02-25 03:23:13,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3550.1, 300 sec: 3596.1). Total num frames: 2240512. Throughput: 0: 859.2. Samples: 559584. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:23:13,906][00684] Avg episode reward: [(0, '4.723')] [2023-02-25 03:23:16,749][10738] Updated weights for policy 0, policy_version 550 (0.0019) [2023-02-25 03:23:18,901][00684] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2256896. Throughput: 0: 850.4. Samples: 563968. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:23:18,908][00684] Avg episode reward: [(0, '4.679')] [2023-02-25 03:23:23,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 2277376. Throughput: 0: 875.6. Samples: 570014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:23:23,903][00684] Avg episode reward: [(0, '4.747')] [2023-02-25 03:23:26,717][10738] Updated weights for policy 0, policy_version 560 (0.0039) [2023-02-25 03:23:28,900][00684] Fps is (10 sec: 4505.7, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2301952. Throughput: 0: 876.9. Samples: 573518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:23:28,903][00684] Avg episode reward: [(0, '4.756')] [2023-02-25 03:23:33,902][00684] Fps is (10 sec: 4095.5, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2318336. Throughput: 0: 851.9. Samples: 579216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:23:33,907][00684] Avg episode reward: [(0, '4.691')] [2023-02-25 03:23:38,901][00684] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 2330624. Throughput: 0: 857.3. Samples: 583600. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:23:38,905][00684] Avg episode reward: [(0, '4.717')] [2023-02-25 03:23:39,209][10738] Updated weights for policy 0, policy_version 570 (0.0036) [2023-02-25 03:23:43,900][00684] Fps is (10 sec: 3686.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 2355200. Throughput: 0: 888.1. Samples: 586648. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:23:43,903][00684] Avg episode reward: [(0, '4.584')] [2023-02-25 03:23:47,930][10738] Updated weights for policy 0, policy_version 580 (0.0012) [2023-02-25 03:23:48,900][00684] Fps is (10 sec: 4915.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2379776. Throughput: 0: 954.8. Samples: 593624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:23:48,903][00684] Avg episode reward: [(0, '4.699')] [2023-02-25 03:23:53,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 2392064. Throughput: 0: 931.8. Samples: 598860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:23:53,903][00684] Avg episode reward: [(0, '4.633')] [2023-02-25 03:23:58,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2408448. Throughput: 0: 921.0. Samples: 601030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:23:58,904][00684] Avg episode reward: [(0, '4.664')] [2023-02-25 03:24:00,510][10738] Updated weights for policy 0, policy_version 590 (0.0030) [2023-02-25 03:24:03,901][00684] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 3637.8). Total num frames: 2428928. Throughput: 0: 951.6. Samples: 606788. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:03,908][00684] Avg episode reward: [(0, '4.616')] [2023-02-25 03:24:08,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 2453504. Throughput: 0: 968.7. Samples: 613604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:24:08,902][00684] Avg episode reward: [(0, '4.602')] [2023-02-25 03:24:08,919][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000599_2453504.pth... [2023-02-25 03:24:09,048][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth [2023-02-25 03:24:09,616][10738] Updated weights for policy 0, policy_version 600 (0.0014) [2023-02-25 03:24:13,900][00684] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2469888. Throughput: 0: 945.5. Samples: 616066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:24:13,910][00684] Avg episode reward: [(0, '4.808')] [2023-02-25 03:24:18,901][00684] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2482176. Throughput: 0: 914.6. Samples: 620374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:24:18,905][00684] Avg episode reward: [(0, '4.789')] [2023-02-25 03:24:22,153][10738] Updated weights for policy 0, policy_version 610 (0.0015) [2023-02-25 03:24:23,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2502656. Throughput: 0: 953.1. Samples: 626490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:24:23,903][00684] Avg episode reward: [(0, '4.893')] [2023-02-25 03:24:28,900][00684] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2527232. Throughput: 0: 963.1. Samples: 629988. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:28,904][00684] Avg episode reward: [(0, '4.750')] [2023-02-25 03:24:32,041][10738] Updated weights for policy 0, policy_version 620 (0.0022) [2023-02-25 03:24:33,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2543616. Throughput: 0: 932.8. Samples: 635600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:33,910][00684] Avg episode reward: [(0, '4.579')] [2023-02-25 03:24:38,901][00684] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3623.9). Total num frames: 2555904. Throughput: 0: 914.3. Samples: 640002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:38,903][00684] Avg episode reward: [(0, '4.739')] [2023-02-25 03:24:43,528][10738] Updated weights for policy 0, policy_version 630 (0.0022) [2023-02-25 03:24:43,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2580480. Throughput: 0: 936.4. Samples: 643166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:43,909][00684] Avg episode reward: [(0, '4.858')] [2023-02-25 03:24:48,901][00684] Fps is (10 sec: 4915.4, 60 sec: 3754.6, 300 sec: 3679.5). Total num frames: 2605056. Throughput: 0: 962.8. Samples: 650112. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:24:48,907][00684] Avg episode reward: [(0, '5.058')] [2023-02-25 03:24:53,906][00684] Fps is (10 sec: 3684.3, 60 sec: 3754.3, 300 sec: 3665.5). Total num frames: 2617344. Throughput: 0: 923.6. Samples: 655172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:24:53,913][00684] Avg episode reward: [(0, '4.850')] [2023-02-25 03:24:54,206][10738] Updated weights for policy 0, policy_version 640 (0.0034) [2023-02-25 03:24:58,900][00684] Fps is (10 sec: 2867.3, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2633728. Throughput: 0: 915.9. Samples: 657282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:24:58,908][00684] Avg episode reward: [(0, '4.931')] [2023-02-25 03:25:03,900][00684] Fps is (10 sec: 3688.5, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2654208. Throughput: 0: 949.1. Samples: 663082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:25:03,905][00684] Avg episode reward: [(0, '4.890')] [2023-02-25 03:25:04,929][10738] Updated weights for policy 0, policy_version 650 (0.0023) [2023-02-25 03:25:08,901][00684] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2674688. Throughput: 0: 953.6. Samples: 669404. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:25:08,903][00684] Avg episode reward: [(0, '5.026')] [2023-02-25 03:25:13,902][00684] Fps is (10 sec: 3276.3, 60 sec: 3618.0, 300 sec: 3651.7). Total num frames: 2686976. Throughput: 0: 917.5. Samples: 671278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:25:13,904][00684] Avg episode reward: [(0, '4.885')] [2023-02-25 03:25:18,902][00684] Fps is (10 sec: 2457.2, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 2699264. Throughput: 0: 867.9. Samples: 674658. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-25 03:25:18,906][00684] Avg episode reward: [(0, '4.974')] [2023-02-25 03:25:20,386][10738] Updated weights for policy 0, policy_version 660 (0.0048) [2023-02-25 03:25:23,900][00684] Fps is (10 sec: 2458.0, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2711552. Throughput: 0: 859.0. Samples: 678658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:25:23,906][00684] Avg episode reward: [(0, '4.874')] [2023-02-25 03:25:28,901][00684] Fps is (10 sec: 3686.9, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 2736128. Throughput: 0: 865.4. Samples: 682108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:25:28,904][00684] Avg episode reward: [(0, '4.721')] [2023-02-25 03:25:30,200][10738] Updated weights for policy 0, policy_version 670 (0.0018) [2023-02-25 03:25:33,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2756608. Throughput: 0: 865.0. Samples: 689038. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:25:33,906][00684] Avg episode reward: [(0, '4.744')] [2023-02-25 03:25:38,901][00684] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2772992. Throughput: 0: 858.4. Samples: 693794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:25:38,905][00684] Avg episode reward: [(0, '4.722')] [2023-02-25 03:25:42,522][10738] Updated weights for policy 0, policy_version 680 (0.0026) [2023-02-25 03:25:43,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 2789376. Throughput: 0: 860.4. Samples: 696000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:25:43,903][00684] Avg episode reward: [(0, '4.970')] [2023-02-25 03:25:48,902][00684] Fps is (10 sec: 4095.5, 60 sec: 3481.5, 300 sec: 3679.4). Total num frames: 2813952. Throughput: 0: 870.2. Samples: 702244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:25:48,905][00684] Avg episode reward: [(0, '4.776')] [2023-02-25 03:25:51,416][10738] Updated weights for policy 0, policy_version 690 (0.0013) [2023-02-25 03:25:53,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3618.5, 300 sec: 3693.3). Total num frames: 2834432. Throughput: 0: 881.2. Samples: 709060. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:25:53,906][00684] Avg episode reward: [(0, '4.684')] [2023-02-25 03:25:58,901][00684] Fps is (10 sec: 3277.3, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2846720. Throughput: 0: 888.3. Samples: 711252. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:25:58,907][00684] Avg episode reward: [(0, '4.859')] [2023-02-25 03:26:03,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 2863104. Throughput: 0: 912.1. Samples: 715702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:26:03,908][00684] Avg episode reward: [(0, '4.802')] [2023-02-25 03:26:04,017][10738] Updated weights for policy 0, policy_version 700 (0.0018) [2023-02-25 03:26:08,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2887680. Throughput: 0: 976.2. Samples: 722586. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:26:08,903][00684] Avg episode reward: [(0, '4.867')] [2023-02-25 03:26:08,911][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000705_2887680.pth... [2023-02-25 03:26:09,037][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth [2023-02-25 03:26:12,555][10738] Updated weights for policy 0, policy_version 710 (0.0018) [2023-02-25 03:26:13,900][00684] Fps is (10 sec: 4915.2, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 2912256. Throughput: 0: 976.3. Samples: 726040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:26:13,903][00684] Avg episode reward: [(0, '5.064')] [2023-02-25 03:26:18,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3665.6). Total num frames: 2924544. Throughput: 0: 938.8. Samples: 731284. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:26:18,908][00684] Avg episode reward: [(0, '4.940')] [2023-02-25 03:26:23,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 2940928. Throughput: 0: 937.1. Samples: 735964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:26:23,902][00684] Avg episode reward: [(0, '4.950')] [2023-02-25 03:26:24,785][10738] Updated weights for policy 0, policy_version 720 (0.0019) [2023-02-25 03:26:28,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.4). Total num frames: 2965504. Throughput: 0: 969.2. Samples: 739614. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:26:28,903][00684] Avg episode reward: [(0, '5.028')] [2023-02-25 03:26:33,741][10738] Updated weights for policy 0, policy_version 730 (0.0026) [2023-02-25 03:26:33,900][00684] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3707.2). Total num frames: 2990080. Throughput: 0: 990.4. Samples: 746812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:26:33,906][00684] Avg episode reward: [(0, '5.051')] [2023-02-25 03:26:38,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3679.5). Total num frames: 3002368. Throughput: 0: 942.5. Samples: 751474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:26:38,902][00684] Avg episode reward: [(0, '5.111')] [2023-02-25 03:26:38,967][10724] Saving new best policy, reward=5.111! [2023-02-25 03:26:43,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3018752. Throughput: 0: 942.2. Samples: 753650. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-25 03:26:43,907][00684] Avg episode reward: [(0, '5.387')] [2023-02-25 03:26:43,956][10724] Saving new best policy, reward=5.387! [2023-02-25 03:26:45,798][10738] Updated weights for policy 0, policy_version 740 (0.0013) [2023-02-25 03:26:48,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3693.4). Total num frames: 3043328. Throughput: 0: 988.1. Samples: 760168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:26:48,908][00684] Avg episode reward: [(0, '5.705')] [2023-02-25 03:26:48,922][10724] Saving new best policy, reward=5.705! [2023-02-25 03:26:53,908][00684] Fps is (10 sec: 4502.2, 60 sec: 3822.5, 300 sec: 3707.1). Total num frames: 3063808. Throughput: 0: 984.2. Samples: 766882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:26:53,915][00684] Avg episode reward: [(0, '5.614')] [2023-02-25 03:26:55,606][10738] Updated weights for policy 0, policy_version 750 (0.0025) [2023-02-25 03:26:58,903][00684] Fps is (10 sec: 3685.5, 60 sec: 3891.0, 300 sec: 3679.4). Total num frames: 3080192. Throughput: 0: 956.9. Samples: 769104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:26:58,907][00684] Avg episode reward: [(0, '5.734')] [2023-02-25 03:26:58,927][10724] Saving new best policy, reward=5.734! [2023-02-25 03:27:03,900][00684] Fps is (10 sec: 3279.3, 60 sec: 3891.2, 300 sec: 3665.6). Total num frames: 3096576. Throughput: 0: 939.5. Samples: 773560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:27:03,903][00684] Avg episode reward: [(0, '5.876')] [2023-02-25 03:27:03,906][10724] Saving new best policy, reward=5.876! [2023-02-25 03:27:06,748][10738] Updated weights for policy 0, policy_version 760 (0.0023) [2023-02-25 03:27:08,900][00684] Fps is (10 sec: 4097.0, 60 sec: 3891.2, 300 sec: 3707.3). Total num frames: 3121152. Throughput: 0: 989.6. Samples: 780496. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:27:08,906][00684] Avg episode reward: [(0, '5.371')] [2023-02-25 03:27:13,901][00684] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3141632. Throughput: 0: 987.1. Samples: 784034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:27:13,905][00684] Avg episode reward: [(0, '5.193')] [2023-02-25 03:27:17,170][10738] Updated weights for policy 0, policy_version 770 (0.0016) [2023-02-25 03:27:18,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3693.3). Total num frames: 3158016. Throughput: 0: 936.9. Samples: 788972. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:27:18,908][00684] Avg episode reward: [(0, '5.310')] [2023-02-25 03:27:23,900][00684] Fps is (10 sec: 2867.3, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3170304. Throughput: 0: 930.8. Samples: 793358. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:27:23,903][00684] Avg episode reward: [(0, '5.416')] [2023-02-25 03:27:28,905][00684] Fps is (10 sec: 2865.9, 60 sec: 3686.1, 300 sec: 3679.4). Total num frames: 3186688. Throughput: 0: 933.8. Samples: 795674. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:27:28,909][00684] Avg episode reward: [(0, '5.229')] [2023-02-25 03:27:31,060][10738] Updated weights for policy 0, policy_version 780 (0.0024) [2023-02-25 03:27:33,906][00684] Fps is (10 sec: 3274.9, 60 sec: 3549.5, 300 sec: 3665.5). Total num frames: 3203072. Throughput: 0: 896.8. Samples: 800528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:27:33,909][00684] Avg episode reward: [(0, '5.247')] [2023-02-25 03:27:38,900][00684] Fps is (10 sec: 3278.3, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3219456. Throughput: 0: 850.6. Samples: 805152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:27:38,903][00684] Avg episode reward: [(0, '5.219')] [2023-02-25 03:27:43,373][10738] Updated weights for policy 0, policy_version 790 (0.0033) [2023-02-25 03:27:43,900][00684] Fps is (10 sec: 3278.7, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3235840. Throughput: 0: 851.7. Samples: 807428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:27:43,909][00684] Avg episode reward: [(0, '5.387')] [2023-02-25 03:27:48,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 3260416. Throughput: 0: 902.1. Samples: 814154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:27:48,903][00684] Avg episode reward: [(0, '5.213')] [2023-02-25 03:27:51,955][10738] Updated weights for policy 0, policy_version 800 (0.0012) [2023-02-25 03:27:53,901][00684] Fps is (10 sec: 4505.4, 60 sec: 3618.6, 300 sec: 3707.2). Total num frames: 3280896. Throughput: 0: 897.9. Samples: 820904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:27:53,906][00684] Avg episode reward: [(0, '5.020')] [2023-02-25 03:27:58,902][00684] Fps is (10 sec: 3685.7, 60 sec: 3618.2, 300 sec: 3707.2). Total num frames: 3297280. Throughput: 0: 867.1. Samples: 823056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2023-02-25 03:27:58,906][00684] Avg episode reward: [(0, '5.024')] [2023-02-25 03:28:03,900][00684] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3313664. Throughput: 0: 860.9. Samples: 827712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:03,903][00684] Avg episode reward: [(0, '4.766')] [2023-02-25 03:28:04,253][10738] Updated weights for policy 0, policy_version 810 (0.0020) [2023-02-25 03:28:08,900][00684] Fps is (10 sec: 4096.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3338240. Throughput: 0: 920.2. Samples: 834766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:08,905][00684] Avg episode reward: [(0, '4.915')] [2023-02-25 03:28:08,927][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000815_3338240.pth... [2023-02-25 03:28:09,072][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000599_2453504.pth [2023-02-25 03:28:13,620][10738] Updated weights for policy 0, policy_version 820 (0.0015) [2023-02-25 03:28:13,902][00684] Fps is (10 sec: 4504.7, 60 sec: 3618.0, 300 sec: 3735.0). Total num frames: 3358720. Throughput: 0: 945.2. Samples: 838204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:13,905][00684] Avg episode reward: [(0, '5.100')] [2023-02-25 03:28:18,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 3371008. Throughput: 0: 942.0. Samples: 842914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:18,909][00684] Avg episode reward: [(0, '4.992')] [2023-02-25 03:28:23,902][00684] Fps is (10 sec: 3277.0, 60 sec: 3686.3, 300 sec: 3693.3). Total num frames: 3391488. Throughput: 0: 952.3. Samples: 848006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:23,904][00684] Avg episode reward: [(0, '5.062')] [2023-02-25 03:28:25,438][10738] Updated weights for policy 0, policy_version 830 (0.0021) [2023-02-25 03:28:28,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3754.9, 300 sec: 3707.2). Total num frames: 3411968. Throughput: 0: 978.0. Samples: 851436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:28,903][00684] Avg episode reward: [(0, '4.711')] [2023-02-25 03:28:33,900][00684] Fps is (10 sec: 4096.5, 60 sec: 3823.3, 300 sec: 3735.0). Total num frames: 3432448. Throughput: 0: 982.9. Samples: 858384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:28:33,908][00684] Avg episode reward: [(0, '4.744')] [2023-02-25 03:28:35,311][10738] Updated weights for policy 0, policy_version 840 (0.0025) [2023-02-25 03:28:38,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3448832. Throughput: 0: 932.1. Samples: 862848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:38,907][00684] Avg episode reward: [(0, '4.620')] [2023-02-25 03:28:43,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3693.3). Total num frames: 3469312. Throughput: 0: 934.6. Samples: 865112. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:28:43,909][00684] Avg episode reward: [(0, '4.645')] [2023-02-25 03:28:46,374][10738] Updated weights for policy 0, policy_version 850 (0.0038) [2023-02-25 03:28:48,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3489792. Throughput: 0: 984.6. Samples: 872020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:28:48,905][00684] Avg episode reward: [(0, '4.665')] [2023-02-25 03:28:53,901][00684] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 3510272. Throughput: 0: 969.4. Samples: 878390. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:28:53,903][00684] Avg episode reward: [(0, '4.650')] [2023-02-25 03:28:56,887][10738] Updated weights for policy 0, policy_version 860 (0.0014) [2023-02-25 03:28:58,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3721.1). Total num frames: 3526656. Throughput: 0: 942.5. Samples: 880614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-25 03:28:58,906][00684] Avg episode reward: [(0, '4.650')] [2023-02-25 03:29:03,901][00684] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3707.2). Total num frames: 3547136. Throughput: 0: 944.8. Samples: 885432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:29:03,906][00684] Avg episode reward: [(0, '4.670')] [2023-02-25 03:29:07,375][10738] Updated weights for policy 0, policy_version 870 (0.0015) [2023-02-25 03:29:08,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3567616. Throughput: 0: 987.6. Samples: 892448. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:29:08,902][00684] Avg episode reward: [(0, '4.474')] [2023-02-25 03:29:13,900][00684] Fps is (10 sec: 4096.1, 60 sec: 3823.1, 300 sec: 3748.9). Total num frames: 3588096. Throughput: 0: 986.3. Samples: 895820. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:13,903][00684] Avg episode reward: [(0, '4.474')] [2023-02-25 03:29:18,905][00684] Fps is (10 sec: 3275.3, 60 sec: 3822.6, 300 sec: 3721.1). Total num frames: 3600384. Throughput: 0: 934.2. Samples: 900426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:18,909][00684] Avg episode reward: [(0, '4.525')] [2023-02-25 03:29:19,014][10738] Updated weights for policy 0, policy_version 880 (0.0017) [2023-02-25 03:29:23,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 3616768. Throughput: 0: 929.4. Samples: 904670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:23,908][00684] Avg episode reward: [(0, '4.417')] [2023-02-25 03:29:28,900][00684] Fps is (10 sec: 3278.3, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3633152. Throughput: 0: 921.1. Samples: 906562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-25 03:29:28,906][00684] Avg episode reward: [(0, '4.414')] [2023-02-25 03:29:30,966][10738] Updated weights for policy 0, policy_version 890 (0.0025) [2023-02-25 03:29:33,902][00684] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3721.1). Total num frames: 3653632. Throughput: 0: 913.8. Samples: 913144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:29:33,904][00684] Avg episode reward: [(0, '4.600')] [2023-02-25 03:29:38,903][00684] Fps is (10 sec: 3275.9, 60 sec: 3618.0, 300 sec: 3679.4). Total num frames: 3665920. Throughput: 0: 865.1. Samples: 917324. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-25 03:29:38,907][00684] Avg episode reward: [(0, '4.577')] [2023-02-25 03:29:43,901][00684] Fps is (10 sec: 2457.7, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3678208. Throughput: 0: 853.5. Samples: 919022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:43,909][00684] Avg episode reward: [(0, '4.673')] [2023-02-25 03:29:46,093][10738] Updated weights for policy 0, policy_version 900 (0.0015) [2023-02-25 03:29:48,900][00684] Fps is (10 sec: 2868.0, 60 sec: 3413.3, 300 sec: 3651.8). Total num frames: 3694592. Throughput: 0: 836.6. Samples: 923078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:48,906][00684] Avg episode reward: [(0, '4.643')] [2023-02-25 03:29:53,900][00684] Fps is (10 sec: 3686.7, 60 sec: 3413.3, 300 sec: 3665.6). Total num frames: 3715072. Throughput: 0: 824.7. Samples: 929560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:29:53,903][00684] Avg episode reward: [(0, '4.650')] [2023-02-25 03:29:56,373][10738] Updated weights for policy 0, policy_version 910 (0.0015) [2023-02-25 03:29:58,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 3731456. Throughput: 0: 811.2. Samples: 932326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:29:58,902][00684] Avg episode reward: [(0, '4.647')] [2023-02-25 03:30:03,900][00684] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3637.8). Total num frames: 3747840. Throughput: 0: 807.1. Samples: 936744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:30:03,906][00684] Avg episode reward: [(0, '4.710')] [2023-02-25 03:30:08,038][10738] Updated weights for policy 0, policy_version 920 (0.0028) [2023-02-25 03:30:08,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3679.5). Total num frames: 3772416. Throughput: 0: 851.2. Samples: 942974. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:30:08,907][00684] Avg episode reward: [(0, '4.653')] [2023-02-25 03:30:08,919][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000921_3772416.pth... [2023-02-25 03:30:09,055][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000705_2887680.pth [2023-02-25 03:30:13,900][00684] Fps is (10 sec: 4505.6, 60 sec: 3413.3, 300 sec: 3707.2). Total num frames: 3792896. Throughput: 0: 886.4. Samples: 946452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:30:13,903][00684] Avg episode reward: [(0, '4.579')] [2023-02-25 03:30:18,306][10738] Updated weights for policy 0, policy_version 930 (0.0018) [2023-02-25 03:30:18,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3481.9, 300 sec: 3721.1). Total num frames: 3809280. Throughput: 0: 867.5. Samples: 952180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:30:18,906][00684] Avg episode reward: [(0, '4.557')] [2023-02-25 03:30:23,901][00684] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 3825664. Throughput: 0: 872.4. Samples: 956578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:30:23,908][00684] Avg episode reward: [(0, '4.610')] [2023-02-25 03:30:28,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3846144. Throughput: 0: 900.6. Samples: 959550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-25 03:30:28,903][00684] Avg episode reward: [(0, '4.774')] [2023-02-25 03:30:29,459][10738] Updated weights for policy 0, policy_version 940 (0.0022) [2023-02-25 03:30:33,900][00684] Fps is (10 sec: 4505.7, 60 sec: 3618.2, 300 sec: 3721.1). Total num frames: 3870720. Throughput: 0: 969.0. Samples: 966684. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:30:33,902][00684] Avg episode reward: [(0, '4.831')] [2023-02-25 03:30:38,900][00684] Fps is (10 sec: 4096.0, 60 sec: 3686.6, 300 sec: 3721.1). Total num frames: 3887104. Throughput: 0: 946.6. Samples: 972158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:30:38,909][00684] Avg episode reward: [(0, '4.905')] [2023-02-25 03:30:39,917][10738] Updated weights for policy 0, policy_version 950 (0.0017) [2023-02-25 03:30:43,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3899392. Throughput: 0: 933.9. Samples: 974352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-25 03:30:43,908][00684] Avg episode reward: [(0, '5.266')] [2023-02-25 03:30:48,900][00684] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 3923968. Throughput: 0: 967.3. Samples: 980274. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:30:48,910][00684] Avg episode reward: [(0, '5.269')] [2023-02-25 03:30:50,332][10738] Updated weights for policy 0, policy_version 960 (0.0021) [2023-02-25 03:30:53,900][00684] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3948544. Throughput: 0: 982.6. Samples: 987192. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-02-25 03:30:53,907][00684] Avg episode reward: [(0, '4.902')] [2023-02-25 03:30:58,902][00684] Fps is (10 sec: 3685.9, 60 sec: 3822.8, 300 sec: 3721.1). Total num frames: 3960832. Throughput: 0: 964.7. Samples: 989864. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2023-02-25 03:30:58,904][00684] Avg episode reward: [(0, '4.536')] [2023-02-25 03:31:01,694][10738] Updated weights for policy 0, policy_version 970 (0.0024) [2023-02-25 03:31:03,900][00684] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 3977216. Throughput: 0: 935.5. Samples: 994278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:31:03,910][00684] Avg episode reward: [(0, '4.528')] [2023-02-25 03:31:08,900][00684] Fps is (10 sec: 4096.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 4001792. Throughput: 0: 979.6. Samples: 1000658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-25 03:31:08,909][00684] Avg episode reward: [(0, '4.740')] [2023-02-25 03:31:09,481][10724] Stopping Batcher_0... [2023-02-25 03:31:09,481][10724] Loop batcher_evt_loop terminating... [2023-02-25 03:31:09,484][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-25 03:31:09,482][00684] Component Batcher_0 stopped! [2023-02-25 03:31:09,539][00684] Component RolloutWorker_w6 stopped! [2023-02-25 03:31:09,545][10748] Stopping RolloutWorker_w6... [2023-02-25 03:31:09,549][10745] Stopping RolloutWorker_w2... [2023-02-25 03:31:09,550][00684] Component RolloutWorker_w2 stopped! [2023-02-25 03:31:09,556][10748] Loop rollout_proc6_evt_loop terminating... [2023-02-25 03:31:09,556][10745] Loop rollout_proc2_evt_loop terminating... [2023-02-25 03:31:09,558][00684] Component RolloutWorker_w0 stopped! [2023-02-25 03:31:09,561][00684] Component RolloutWorker_w4 stopped! [2023-02-25 03:31:09,559][10746] Stopping RolloutWorker_w4... [2023-02-25 03:31:09,572][10738] Weights refcount: 2 0 [2023-02-25 03:31:09,559][10739] Stopping RolloutWorker_w0... [2023-02-25 03:31:09,578][10739] Loop rollout_proc0_evt_loop terminating... [2023-02-25 03:31:09,566][10746] Loop rollout_proc4_evt_loop terminating... [2023-02-25 03:31:09,579][10738] Stopping InferenceWorker_p0-w0... [2023-02-25 03:31:09,579][10738] Loop inference_proc0-0_evt_loop terminating... [2023-02-25 03:31:09,578][00684] Component InferenceWorker_p0-w0 stopped! [2023-02-25 03:31:09,581][00684] Component RolloutWorker_w7 stopped! [2023-02-25 03:31:09,586][00684] Component RolloutWorker_w1 stopped! [2023-02-25 03:31:09,587][10740] Stopping RolloutWorker_w1... [2023-02-25 03:31:09,596][10749] Stopping RolloutWorker_w5... [2023-02-25 03:31:09,593][00684] Component RolloutWorker_w5 stopped! [2023-02-25 03:31:09,578][10750] Stopping RolloutWorker_w7... [2023-02-25 03:31:09,604][00684] Component RolloutWorker_w3 stopped! [2023-02-25 03:31:09,604][10747] Stopping RolloutWorker_w3... [2023-02-25 03:31:09,599][10740] Loop rollout_proc1_evt_loop terminating... [2023-02-25 03:31:09,601][10750] Loop rollout_proc7_evt_loop terminating... [2023-02-25 03:31:09,607][10747] Loop rollout_proc3_evt_loop terminating... [2023-02-25 03:31:09,609][10749] Loop rollout_proc5_evt_loop terminating... [2023-02-25 03:31:09,672][10724] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000815_3338240.pth [2023-02-25 03:31:09,685][10724] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-25 03:31:09,840][00684] Component LearnerWorker_p0 stopped! [2023-02-25 03:31:09,847][00684] Waiting for process learner_proc0 to stop... [2023-02-25 03:31:09,850][10724] Stopping LearnerWorker_p0... [2023-02-25 03:31:09,856][10724] Loop learner_proc0_evt_loop terminating... [2023-02-25 03:31:11,709][00684] Waiting for process inference_proc0-0 to join... [2023-02-25 03:31:12,105][00684] Waiting for process rollout_proc0 to join... [2023-02-25 03:31:12,447][00684] Waiting for process rollout_proc1 to join... [2023-02-25 03:31:12,449][00684] Waiting for process rollout_proc2 to join... [2023-02-25 03:31:12,450][00684] Waiting for process rollout_proc3 to join... [2023-02-25 03:31:12,454][00684] Waiting for process rollout_proc4 to join... [2023-02-25 03:31:12,459][00684] Waiting for process rollout_proc5 to join... [2023-02-25 03:31:12,461][00684] Waiting for process rollout_proc6 to join... [2023-02-25 03:31:12,462][00684] Waiting for process rollout_proc7 to join... [2023-02-25 03:31:12,463][00684] Batcher 0 profile tree view: batching: 26.1172, releasing_batches: 0.0235 [2023-02-25 03:31:12,464][00684] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 543.8694 update_model: 8.3784 weight_update: 0.0028 one_step: 0.0046 handle_policy_step: 512.2967 deserialize: 14.4449, stack: 3.0640, obs_to_device_normalize: 114.9805, forward: 245.1865, send_messages: 26.5766 prepare_outputs: 82.8011 to_cpu: 51.6852 [2023-02-25 03:31:12,465][00684] Learner 0 profile tree view: misc: 0.0055, prepare_batch: 16.5850 train: 76.8693 epoch_init: 0.0057, minibatch_init: 0.0060, losses_postprocess: 0.5953, kl_divergence: 0.5442, after_optimizer: 33.0519 calculate_losses: 27.7165 losses_init: 0.0050, forward_head: 1.8492, bptt_initial: 18.2454, tail: 0.9933, advantages_returns: 0.2640, losses: 3.6414 bptt: 2.4031 bptt_forward_core: 2.2952 update: 14.3705 clip: 1.3783 [2023-02-25 03:31:12,467][00684] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.3985, enqueue_policy_requests: 148.0838, env_step: 831.2662, overhead: 20.1279, complete_rollouts: 6.9592 save_policy_outputs: 20.1943 split_output_tensors: 9.6090 [2023-02-25 03:31:12,470][00684] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.2843, enqueue_policy_requests: 145.8879, env_step: 831.6847, overhead: 20.7200, complete_rollouts: 6.9964 save_policy_outputs: 19.6809 split_output_tensors: 9.4047 [2023-02-25 03:31:12,472][00684] Loop Runner_EvtLoop terminating... [2023-02-25 03:31:12,475][00684] Runner profile tree view: main_loop: 1135.5441 [2023-02-25 03:31:12,476][00684] Collected {0: 4005888}, FPS: 3527.7 [2023-02-25 03:31:12,593][00684] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-25 03:31:12,595][00684] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-25 03:31:12,597][00684] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-25 03:31:12,599][00684] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-25 03:31:12,601][00684] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-25 03:31:12,603][00684] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-25 03:31:12,605][00684] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-02-25 03:31:12,607][00684] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-25 03:31:12,608][00684] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-02-25 03:31:12,609][00684] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-02-25 03:31:12,610][00684] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-25 03:31:12,612][00684] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-25 03:31:12,614][00684] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-25 03:31:12,616][00684] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-25 03:31:12,617][00684] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-25 03:31:12,642][00684] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-25 03:31:12,646][00684] RunningMeanStd input shape: (3, 72, 128) [2023-02-25 03:31:12,649][00684] RunningMeanStd input shape: (1,) [2023-02-25 03:31:12,668][00684] ConvEncoder: input_channels=3 [2023-02-25 03:31:13,334][00684] Conv encoder output size: 512 [2023-02-25 03:31:13,337][00684] Policy head output size: 512 [2023-02-25 03:31:16,340][00684] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-25 03:31:17,967][00684] Num frames 100... [2023-02-25 03:31:18,089][00684] Num frames 200... [2023-02-25 03:31:18,215][00684] Num frames 300... [2023-02-25 03:31:18,374][00684] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 [2023-02-25 03:31:18,376][00684] Avg episode reward: 3.840, avg true_objective: 3.840 [2023-02-25 03:31:18,399][00684] Num frames 400... [2023-02-25 03:31:18,519][00684] Num frames 500... [2023-02-25 03:31:18,637][00684] Num frames 600... [2023-02-25 03:31:18,761][00684] Num frames 700... [2023-02-25 03:31:18,882][00684] Num frames 800... [2023-02-25 03:31:18,975][00684] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160 [2023-02-25 03:31:18,977][00684] Avg episode reward: 4.660, avg true_objective: 4.160 [2023-02-25 03:31:19,060][00684] Num frames 900... [2023-02-25 03:31:19,184][00684] Num frames 1000... [2023-02-25 03:31:19,302][00684] Num frames 1100... [2023-02-25 03:31:19,414][00684] Num frames 1200... [2023-02-25 03:31:19,494][00684] Avg episode rewards: #0: 4.387, true rewards: #0: 4.053 [2023-02-25 03:31:19,496][00684] Avg episode reward: 4.387, avg true_objective: 4.053 [2023-02-25 03:31:19,593][00684] Num frames 1300... [2023-02-25 03:31:19,720][00684] Num frames 1400... [2023-02-25 03:31:19,846][00684] Num frames 1500... [2023-02-25 03:31:19,966][00684] Num frames 1600... [2023-02-25 03:31:20,059][00684] Avg episode rewards: #0: 4.580, true rewards: #0: 4.080 [2023-02-25 03:31:20,060][00684] Avg episode reward: 4.580, avg true_objective: 4.080 [2023-02-25 03:31:20,146][00684] Num frames 1700... [2023-02-25 03:31:20,269][00684] Num frames 1800... [2023-02-25 03:31:20,391][00684] Num frames 1900... [2023-02-25 03:31:20,510][00684] Num frames 2000... [2023-02-25 03:31:20,676][00684] Avg episode rewards: #0: 4.760, true rewards: #0: 4.160 [2023-02-25 03:31:20,678][00684] Avg episode reward: 4.760, avg true_objective: 4.160 [2023-02-25 03:31:20,704][00684] Num frames 2100... [2023-02-25 03:31:20,827][00684] Num frames 2200... [2023-02-25 03:31:20,954][00684] Num frames 2300... [2023-02-25 03:31:21,078][00684] Num frames 2400... [2023-02-25 03:31:21,208][00684] Avg episode rewards: #0: 4.607, true rewards: #0: 4.107 [2023-02-25 03:31:21,209][00684] Avg episode reward: 4.607, avg true_objective: 4.107 [2023-02-25 03:31:21,253][00684] Num frames 2500... [2023-02-25 03:31:21,375][00684] Num frames 2600... [2023-02-25 03:31:21,492][00684] Num frames 2700... [2023-02-25 03:31:21,610][00684] Num frames 2800... [2023-02-25 03:31:21,724][00684] Avg episode rewards: #0: 4.497, true rewards: #0: 4.069 [2023-02-25 03:31:21,727][00684] Avg episode reward: 4.497, avg true_objective: 4.069 [2023-02-25 03:31:21,800][00684] Num frames 2900... [2023-02-25 03:31:21,913][00684] Num frames 3000... [2023-02-25 03:31:22,032][00684] Num frames 3100... [2023-02-25 03:31:22,153][00684] Num frames 3200... [2023-02-25 03:31:22,245][00684] Avg episode rewards: #0: 4.415, true rewards: #0: 4.040 [2023-02-25 03:31:22,246][00684] Avg episode reward: 4.415, avg true_objective: 4.040 [2023-02-25 03:31:22,335][00684] Num frames 3300... [2023-02-25 03:31:22,449][00684] Num frames 3400... [2023-02-25 03:31:22,570][00684] Num frames 3500... [2023-02-25 03:31:22,688][00684] Num frames 3600... [2023-02-25 03:31:22,798][00684] Avg episode rewards: #0: 4.609, true rewards: #0: 4.053 [2023-02-25 03:31:22,800][00684] Avg episode reward: 4.609, avg true_objective: 4.053 [2023-02-25 03:31:22,867][00684] Num frames 3700... [2023-02-25 03:31:22,987][00684] Num frames 3800... [2023-02-25 03:31:23,113][00684] Num frames 3900... [2023-02-25 03:31:23,235][00684] Num frames 4000... [2023-02-25 03:31:23,412][00684] Avg episode rewards: #0: 4.696, true rewards: #0: 4.096 [2023-02-25 03:31:23,414][00684] Avg episode reward: 4.696, avg true_objective: 4.096 [2023-02-25 03:31:44,419][00684] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2023-02-25 03:33:48,199][00684] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-25 03:33:48,202][00684] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-25 03:33:48,204][00684] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-25 03:33:48,207][00684] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-25 03:33:48,213][00684] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-25 03:33:48,214][00684] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-25 03:33:48,215][00684] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-02-25 03:33:48,217][00684] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-25 03:33:48,218][00684] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-02-25 03:33:48,219][00684] Adding new argument 'hf_repository'='menoua/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2023-02-25 03:33:48,220][00684] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-25 03:33:48,222][00684] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-25 03:33:48,223][00684] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-25 03:33:48,224][00684] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-25 03:33:48,226][00684] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-25 03:33:48,255][00684] RunningMeanStd input shape: (3, 72, 128) [2023-02-25 03:33:48,258][00684] RunningMeanStd input shape: (1,) [2023-02-25 03:33:48,278][00684] ConvEncoder: input_channels=3 [2023-02-25 03:33:48,341][00684] Conv encoder output size: 512 [2023-02-25 03:33:48,345][00684] Policy head output size: 512 [2023-02-25 03:33:48,380][00684] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-25 03:33:49,045][00684] Num frames 100... [2023-02-25 03:33:49,213][00684] Num frames 200... [2023-02-25 03:33:49,379][00684] Num frames 300... [2023-02-25 03:33:49,548][00684] Num frames 400... [2023-02-25 03:33:49,634][00684] Avg episode rewards: #0: 4.160, true rewards: #0: 4.160 [2023-02-25 03:33:49,637][00684] Avg episode reward: 4.160, avg true_objective: 4.160 [2023-02-25 03:33:49,776][00684] Num frames 500... [2023-02-25 03:33:49,950][00684] Num frames 600... [2023-02-25 03:33:50,128][00684] Num frames 700... [2023-02-25 03:33:50,308][00684] Num frames 800... [2023-02-25 03:33:50,363][00684] Avg episode rewards: #0: 4.000, true rewards: #0: 4.000 [2023-02-25 03:33:50,365][00684] Avg episode reward: 4.000, avg true_objective: 4.000 [2023-02-25 03:33:50,530][00684] Num frames 900... [2023-02-25 03:33:50,700][00684] Num frames 1000... [2023-02-25 03:33:50,837][00684] Num frames 1100... [2023-02-25 03:33:50,950][00684] Num frames 1200... [2023-02-25 03:33:51,059][00684] Avg episode rewards: #0: 4.493, true rewards: #0: 4.160 [2023-02-25 03:33:51,063][00684] Avg episode reward: 4.493, avg true_objective: 4.160 [2023-02-25 03:33:51,124][00684] Num frames 1300... [2023-02-25 03:33:51,251][00684] Num frames 1400... [2023-02-25 03:33:51,374][00684] Num frames 1500... [2023-02-25 03:33:51,491][00684] Num frames 1600... [2023-02-25 03:33:51,582][00684] Avg episode rewards: #0: 4.330, true rewards: #0: 4.080 [2023-02-25 03:33:51,584][00684] Avg episode reward: 4.330, avg true_objective: 4.080 [2023-02-25 03:33:51,661][00684] Num frames 1700... [2023-02-25 03:33:51,770][00684] Num frames 1800... [2023-02-25 03:33:51,882][00684] Num frames 1900... [2023-02-25 03:33:51,999][00684] Num frames 2000... [2023-02-25 03:33:52,079][00684] Avg episode rewards: #0: 4.232, true rewards: #0: 4.032 [2023-02-25 03:33:52,081][00684] Avg episode reward: 4.232, avg true_objective: 4.032 [2023-02-25 03:33:52,192][00684] Num frames 2100... [2023-02-25 03:33:52,315][00684] Num frames 2200... [2023-02-25 03:33:52,438][00684] Num frames 2300... [2023-02-25 03:33:52,554][00684] Num frames 2400... [2023-02-25 03:33:52,606][00684] Avg episode rewards: #0: 4.167, true rewards: #0: 4.000 [2023-02-25 03:33:52,608][00684] Avg episode reward: 4.167, avg true_objective: 4.000 [2023-02-25 03:33:52,728][00684] Num frames 2500... [2023-02-25 03:33:52,845][00684] Num frames 2600... [2023-02-25 03:33:52,969][00684] Num frames 2700... [2023-02-25 03:33:53,082][00684] Num frames 2800... [2023-02-25 03:33:53,156][00684] Avg episode rewards: #0: 4.309, true rewards: #0: 4.023 [2023-02-25 03:33:53,158][00684] Avg episode reward: 4.309, avg true_objective: 4.023 [2023-02-25 03:33:53,261][00684] Num frames 2900... [2023-02-25 03:33:53,385][00684] Num frames 3000... [2023-02-25 03:33:53,503][00684] Num frames 3100... [2023-02-25 03:33:53,636][00684] Num frames 3200... [2023-02-25 03:33:53,688][00684] Avg episode rewards: #0: 4.250, true rewards: #0: 4.000 [2023-02-25 03:33:53,689][00684] Avg episode reward: 4.250, avg true_objective: 4.000 [2023-02-25 03:33:53,805][00684] Num frames 3300... [2023-02-25 03:33:53,926][00684] Num frames 3400... [2023-02-25 03:33:54,048][00684] Num frames 3500... [2023-02-25 03:33:54,203][00684] Avg episode rewards: #0: 4.204, true rewards: #0: 3.982 [2023-02-25 03:33:54,206][00684] Avg episode reward: 4.204, avg true_objective: 3.982 [2023-02-25 03:33:54,231][00684] Num frames 3600... [2023-02-25 03:33:54,350][00684] Num frames 3700... [2023-02-25 03:33:54,468][00684] Num frames 3800... [2023-02-25 03:33:54,589][00684] Num frames 3900... [2023-02-25 03:33:54,714][00684] Num frames 4000... [2023-02-25 03:33:54,810][00684] Avg episode rewards: #0: 4.332, true rewards: #0: 4.032 [2023-02-25 03:33:54,812][00684] Avg episode reward: 4.332, avg true_objective: 4.032 [2023-02-25 03:34:14,342][00684] Replay video saved to /content/train_dir/default_experiment/replay.mp4! |