File size: 48,149 Bytes
c6792da 7e8b54c c6792da |
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 |
[2024-09-30 00:25:00,956][1148693] Saving configuration to /home/luyang/workspace/rl/train_dir/default_experiment/config.json...
[2024-09-30 00:25:00,961][1148693] Rollout worker 0 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 1 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 2 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 3 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 4 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 5 uses device cpu
[2024-09-30 00:25:00,961][1148693] Rollout worker 6 uses device cpu
[2024-09-30 00:25:00,962][1148693] Rollout worker 7 uses device cpu
[2024-09-30 00:25:01,008][1148693] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:25:01,008][1148693] InferenceWorker_p0-w0: min num requests: 2
[2024-09-30 00:25:01,042][1148693] Starting all processes...
[2024-09-30 00:25:01,042][1148693] Starting process learner_proc0
[2024-09-30 00:25:02,676][1148693] Starting all processes...
[2024-09-30 00:25:02,680][1148981] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:25:02,680][1148981] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-09-30 00:25:02,680][1148693] Starting process inference_proc0-0
[2024-09-30 00:25:02,680][1148693] Starting process rollout_proc0
[2024-09-30 00:25:02,681][1148693] Starting process rollout_proc1
[2024-09-30 00:25:02,681][1148693] Starting process rollout_proc2
[2024-09-30 00:25:02,681][1148693] Starting process rollout_proc3
[2024-09-30 00:25:02,681][1148693] Starting process rollout_proc4
[2024-09-30 00:25:02,681][1148693] Starting process rollout_proc5
[2024-09-30 00:25:02,686][1148693] Starting process rollout_proc6
[2024-09-30 00:25:02,686][1148693] Starting process rollout_proc7
[2024-09-30 00:25:02,712][1148981] Num visible devices: 1
[2024-09-30 00:25:02,719][1148981] Starting seed is not provided
[2024-09-30 00:25:02,719][1148981] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:25:02,719][1148981] Initializing actor-critic model on device cuda:0
[2024-09-30 00:25:02,719][1148981] RunningMeanStd input shape: (3, 72, 128)
[2024-09-30 00:25:02,720][1148981] RunningMeanStd input shape: (1,)
[2024-09-30 00:25:02,729][1148981] ConvEncoder: input_channels=3
[2024-09-30 00:25:02,801][1148981] Conv encoder output size: 512
[2024-09-30 00:25:02,801][1148981] Policy head output size: 512
[2024-09-30 00:25:02,812][1148981] Created Actor Critic model with architecture:
[2024-09-30 00:25:02,813][1148981] 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)
)
)
[2024-09-30 00:25:02,951][1148981] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-09-30 00:25:03,366][1148693] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1148693], exiting...
[2024-09-30 00:25:03,366][1148693] Runner profile tree view:
main_loop: 2.3244
[2024-09-30 00:25:03,367][1148693] Collected {}, FPS: 0.0
[2024-09-30 00:25:03,367][1148981] Stopping Batcher_0...
[2024-09-30 00:25:03,368][1148981] Loop batcher_evt_loop terminating...
[2024-09-30 00:25:03,637][1148981] No checkpoints found
[2024-09-30 00:25:03,637][1148981] Did not load from checkpoint, starting from scratch!
[2024-09-30 00:25:03,637][1148981] Initialized policy 0 weights for model version 0
[2024-09-30 00:25:03,639][1148981] LearnerWorker_p0 finished initialization!
[2024-09-30 00:25:03,640][1148981] Saving /home/luyang/workspace/rl/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
[2024-09-30 00:25:03,662][1148981] Stopping LearnerWorker_p0...
[2024-09-30 00:25:03,662][1148981] Loop learner_proc0_evt_loop terminating...
[2024-09-30 00:26:16,204][1149865] Saving configuration to /home/luyang/workspace/rl/train_dir/default_experiment/config.json...
[2024-09-30 00:26:16,209][1149865] Rollout worker 0 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 1 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 2 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 3 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 4 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 5 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 6 uses device cpu
[2024-09-30 00:26:16,209][1149865] Rollout worker 7 uses device cpu
[2024-09-30 00:26:16,252][1149865] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:26:16,252][1149865] InferenceWorker_p0-w0: min num requests: 2
[2024-09-30 00:26:16,286][1149865] Starting all processes...
[2024-09-30 00:26:16,286][1149865] Starting process learner_proc0
[2024-09-30 00:26:17,897][1149865] Starting all processes...
[2024-09-30 00:26:17,901][1150061] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:26:17,901][1150061] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
[2024-09-30 00:26:17,901][1149865] Starting process inference_proc0-0
[2024-09-30 00:26:17,901][1149865] Starting process rollout_proc0
[2024-09-30 00:26:17,901][1149865] Starting process rollout_proc1
[2024-09-30 00:26:17,902][1149865] Starting process rollout_proc2
[2024-09-30 00:26:17,902][1149865] Starting process rollout_proc3
[2024-09-30 00:26:17,902][1149865] Starting process rollout_proc4
[2024-09-30 00:26:17,902][1149865] Starting process rollout_proc5
[2024-09-30 00:26:17,902][1149865] Starting process rollout_proc6
[2024-09-30 00:26:17,903][1149865] Starting process rollout_proc7
[2024-09-30 00:26:17,953][1150061] Num visible devices: 1
[2024-09-30 00:26:17,959][1150061] Starting seed is not provided
[2024-09-30 00:26:17,959][1150061] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:26:17,959][1150061] Initializing actor-critic model on device cuda:0
[2024-09-30 00:26:17,959][1150061] RunningMeanStd input shape: (3, 72, 128)
[2024-09-30 00:26:17,960][1150061] RunningMeanStd input shape: (1,)
[2024-09-30 00:26:17,968][1150061] ConvEncoder: input_channels=3
[2024-09-30 00:26:18,041][1150061] Conv encoder output size: 512
[2024-09-30 00:26:18,041][1150061] Policy head output size: 512
[2024-09-30 00:26:18,052][1150061] Created Actor Critic model with architecture:
[2024-09-30 00:26:18,052][1150061] 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)
)
)
[2024-09-30 00:26:18,183][1150061] Using optimizer <class 'torch.optim.adam.Adam'>
[2024-09-30 00:26:18,816][1150061] Loading state from checkpoint /home/luyang/workspace/rl/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth...
[2024-09-30 00:26:18,828][1150061] Loading model from checkpoint
[2024-09-30 00:26:18,829][1150061] Loaded experiment state at self.train_step=0, self.env_steps=0
[2024-09-30 00:26:18,829][1150061] Initialized policy 0 weights for model version 0
[2024-09-30 00:26:18,831][1150061] LearnerWorker_p0 finished initialization!
[2024-09-30 00:26:18,831][1150061] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:26:19,422][1150142] Worker 3 uses CPU cores [36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47]
[2024-09-30 00:26:19,449][1150140] Worker 7 uses CPU cores [84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95]
[2024-09-30 00:26:19,451][1150144] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
[2024-09-30 00:26:19,456][1150145] Worker 6 uses CPU cores [72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83]
[2024-09-30 00:26:19,456][1150137] Worker 5 uses CPU cores [60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71]
[2024-09-30 00:26:19,462][1150141] Worker 4 uses CPU cores [48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59]
[2024-09-30 00:26:19,465][1150143] Worker 1 uses CPU cores [12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23]
[2024-09-30 00:26:19,466][1150138] Worker 2 uses CPU cores [24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35]
[2024-09-30 00:26:19,483][1150139] Using GPUs [0] for process 0 (actually maps to GPUs [0])
[2024-09-30 00:26:19,484][1150139] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
[2024-09-30 00:26:19,545][1150139] Num visible devices: 1
[2024-09-30 00:26:19,557][1149865] 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)
[2024-09-30 00:26:19,639][1150139] RunningMeanStd input shape: (3, 72, 128)
[2024-09-30 00:26:19,640][1150139] RunningMeanStd input shape: (1,)
[2024-09-30 00:26:19,648][1150139] ConvEncoder: input_channels=3
[2024-09-30 00:26:19,720][1150139] Conv encoder output size: 512
[2024-09-30 00:26:19,720][1150139] Policy head output size: 512
[2024-09-30 00:26:19,751][1149865] Inference worker 0-0 is ready!
[2024-09-30 00:26:19,751][1149865] All inference workers are ready! Signal rollout workers to start!
[2024-09-30 00:26:19,776][1150144] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,776][1150141] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,777][1150142] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,777][1150138] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,777][1150145] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,781][1150140] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,785][1150137] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:19,791][1150143] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:26:20,015][1150141] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,019][1150142] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,020][1150145] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,020][1150138] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,021][1150140] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,028][1150137] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,226][1150141] Decorrelating experience for 32 frames...
[2024-09-30 00:26:20,233][1150142] Decorrelating experience for 32 frames...
[2024-09-30 00:26:20,233][1150145] Decorrelating experience for 32 frames...
[2024-09-30 00:26:20,239][1150137] Decorrelating experience for 32 frames...
[2024-09-30 00:26:20,271][1150143] Decorrelating experience for 0 frames...
[2024-09-30 00:26:20,481][1150143] Decorrelating experience for 32 frames...
[2024-09-30 00:26:20,496][1150145] Decorrelating experience for 64 frames...
[2024-09-30 00:26:20,508][1150142] Decorrelating experience for 64 frames...
[2024-09-30 00:26:20,739][1150141] Decorrelating experience for 64 frames...
[2024-09-30 00:26:20,745][1150142] Decorrelating experience for 96 frames...
[2024-09-30 00:26:20,759][1150137] Decorrelating experience for 64 frames...
[2024-09-30 00:26:20,987][1150141] Decorrelating experience for 96 frames...
[2024-09-30 00:26:20,991][1150137] Decorrelating experience for 96 frames...
[2024-09-30 00:26:20,993][1150143] Decorrelating experience for 64 frames...
[2024-09-30 00:26:21,227][1150143] Decorrelating experience for 96 frames...
[2024-09-30 00:26:21,234][1150145] Decorrelating experience for 96 frames...
[2024-09-30 00:26:21,489][1150138] Decorrelating experience for 32 frames...
[2024-09-30 00:26:21,652][1150061] Signal inference workers to stop experience collection...
[2024-09-30 00:26:21,655][1150139] InferenceWorker_p0-w0: stopping experience collection
[2024-09-30 00:26:21,743][1150140] Decorrelating experience for 32 frames...
[2024-09-30 00:26:21,758][1150138] Decorrelating experience for 64 frames...
[2024-09-30 00:26:21,995][1150138] Decorrelating experience for 96 frames...
[2024-09-30 00:26:22,002][1150140] Decorrelating experience for 64 frames...
[2024-09-30 00:26:22,237][1150140] Decorrelating experience for 96 frames...
[2024-09-30 00:26:22,624][1150061] Signal inference workers to resume experience collection...
[2024-09-30 00:26:22,624][1150139] InferenceWorker_p0-w0: resuming experience collection
[2024-09-30 00:26:23,854][1150139] Updated weights for policy 0, policy_version 10 (0.0128)
[2024-09-30 00:26:24,557][1149865] Fps is (10 sec: 12288.1, 60 sec: 12288.1, 300 sec: 12288.1). Total num frames: 61440. Throughput: 0: 484.0. Samples: 2420. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2024-09-30 00:26:24,557][1149865] Avg episode reward: [(0, '4.453')]
[2024-09-30 00:26:25,059][1150139] Updated weights for policy 0, policy_version 20 (0.0006)
[2024-09-30 00:26:26,154][1150139] Updated weights for policy 0, policy_version 30 (0.0006)
[2024-09-30 00:26:27,304][1150139] Updated weights for policy 0, policy_version 40 (0.0006)
[2024-09-30 00:26:28,424][1150139] Updated weights for policy 0, policy_version 50 (0.0006)
[2024-09-30 00:26:29,557][1149865] Fps is (10 sec: 24166.4, 60 sec: 24166.4, 300 sec: 24166.4). Total num frames: 241664. Throughput: 0: 5481.2. Samples: 54812. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-09-30 00:26:29,557][1149865] Avg episode reward: [(0, '4.420')]
[2024-09-30 00:26:29,562][1150061] Saving new best policy, reward=4.420!
[2024-09-30 00:26:29,562][1150139] Updated weights for policy 0, policy_version 60 (0.0005)
[2024-09-30 00:26:30,697][1150139] Updated weights for policy 0, policy_version 70 (0.0005)
[2024-09-30 00:26:31,899][1150139] Updated weights for policy 0, policy_version 80 (0.0005)
[2024-09-30 00:26:33,041][1150139] Updated weights for policy 0, policy_version 90 (0.0005)
[2024-09-30 00:26:34,164][1150139] Updated weights for policy 0, policy_version 100 (0.0006)
[2024-09-30 00:26:34,557][1149865] Fps is (10 sec: 36044.6, 60 sec: 28125.8, 300 sec: 28125.8). Total num frames: 421888. Throughput: 0: 5422.5. Samples: 81338. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-09-30 00:26:34,557][1149865] Avg episode reward: [(0, '4.360')]
[2024-09-30 00:26:35,313][1150139] Updated weights for policy 0, policy_version 110 (0.0006)
[2024-09-30 00:26:36,243][1149865] Heartbeat connected on Batcher_0
[2024-09-30 00:26:36,247][1149865] Heartbeat connected on LearnerWorker_p0
[2024-09-30 00:26:36,254][1149865] Heartbeat connected on InferenceWorker_p0-w0
[2024-09-30 00:26:36,261][1149865] Heartbeat connected on RolloutWorker_w1
[2024-09-30 00:26:36,265][1149865] Heartbeat connected on RolloutWorker_w2
[2024-09-30 00:26:36,270][1149865] Heartbeat connected on RolloutWorker_w3
[2024-09-30 00:26:36,273][1149865] Heartbeat connected on RolloutWorker_w4
[2024-09-30 00:26:36,278][1149865] Heartbeat connected on RolloutWorker_w5
[2024-09-30 00:26:36,283][1149865] Heartbeat connected on RolloutWorker_w6
[2024-09-30 00:26:36,286][1149865] Heartbeat connected on RolloutWorker_w7
[2024-09-30 00:26:36,388][1150139] Updated weights for policy 0, policy_version 120 (0.0006)
[2024-09-30 00:26:37,485][1150139] Updated weights for policy 0, policy_version 130 (0.0005)
[2024-09-30 00:26:38,623][1150139] Updated weights for policy 0, policy_version 140 (0.0005)
[2024-09-30 00:26:39,557][1149865] Fps is (10 sec: 36454.4, 60 sec: 30310.4, 300 sec: 30310.4). Total num frames: 606208. Throughput: 0: 6816.1. Samples: 136322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-09-30 00:26:39,557][1149865] Avg episode reward: [(0, '4.362')]
[2024-09-30 00:26:39,793][1150139] Updated weights for policy 0, policy_version 150 (0.0005)
[2024-09-30 00:26:40,942][1150139] Updated weights for policy 0, policy_version 160 (0.0006)
[2024-09-30 00:26:42,120][1150139] Updated weights for policy 0, policy_version 170 (0.0006)
[2024-09-30 00:26:43,255][1150139] Updated weights for policy 0, policy_version 180 (0.0006)
[2024-09-30 00:26:44,363][1150139] Updated weights for policy 0, policy_version 190 (0.0006)
[2024-09-30 00:26:44,557][1149865] Fps is (10 sec: 36044.9, 60 sec: 31293.4, 300 sec: 31293.4). Total num frames: 782336. Throughput: 0: 7583.6. Samples: 189590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
[2024-09-30 00:26:44,557][1149865] Avg episode reward: [(0, '4.718')]
[2024-09-30 00:26:44,560][1150061] Saving new best policy, reward=4.718!
[2024-09-30 00:26:45,498][1150139] Updated weights for policy 0, policy_version 200 (0.0006)
[2024-09-30 00:26:46,658][1150139] Updated weights for policy 0, policy_version 210 (0.0005)
[2024-09-30 00:26:47,749][1150139] Updated weights for policy 0, policy_version 220 (0.0005)
[2024-09-30 00:26:48,879][1150139] Updated weights for policy 0, policy_version 230 (0.0006)
[2024-09-30 00:26:49,557][1149865] Fps is (10 sec: 36044.5, 60 sec: 32221.8, 300 sec: 32221.8). Total num frames: 966656. Throughput: 0: 7214.5. Samples: 216436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-09-30 00:26:49,558][1149865] Avg episode reward: [(0, '4.984')]
[2024-09-30 00:26:49,558][1150061] Saving new best policy, reward=4.984!
[2024-09-30 00:26:49,996][1150139] Updated weights for policy 0, policy_version 240 (0.0006)
[2024-09-30 00:26:51,078][1150139] Updated weights for policy 0, policy_version 250 (0.0005)
[2024-09-30 00:26:52,165][1150139] Updated weights for policy 0, policy_version 260 (0.0005)
[2024-09-30 00:26:53,360][1150139] Updated weights for policy 0, policy_version 270 (0.0006)
[2024-09-30 00:26:54,557][1149865] Fps is (10 sec: 36044.3, 60 sec: 32650.8, 300 sec: 32650.8). Total num frames: 1142784. Throughput: 0: 7775.5. Samples: 272144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-09-30 00:26:54,558][1149865] Avg episode reward: [(0, '6.825')]
[2024-09-30 00:26:54,561][1150061] Saving new best policy, reward=6.825!
[2024-09-30 00:26:54,627][1150139] Updated weights for policy 0, policy_version 280 (0.0006)
[2024-09-30 00:26:55,804][1150139] Updated weights for policy 0, policy_version 290 (0.0006)
[2024-09-30 00:26:56,921][1150139] Updated weights for policy 0, policy_version 300 (0.0006)
[2024-09-30 00:26:58,061][1150139] Updated weights for policy 0, policy_version 310 (0.0006)
[2024-09-30 00:26:59,306][1150139] Updated weights for policy 0, policy_version 320 (0.0006)
[2024-09-30 00:26:59,557][1149865] Fps is (10 sec: 35225.8, 60 sec: 32972.8, 300 sec: 32972.8). Total num frames: 1318912. Throughput: 0: 8094.2. Samples: 323770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-09-30 00:26:59,557][1149865] Avg episode reward: [(0, '7.969')]
[2024-09-30 00:26:59,558][1150061] Saving new best policy, reward=7.969!
[2024-09-30 00:27:00,379][1150139] Updated weights for policy 0, policy_version 330 (0.0006)
[2024-09-30 00:27:01,493][1150139] Updated weights for policy 0, policy_version 340 (0.0006)
[2024-09-30 00:27:02,648][1150139] Updated weights for policy 0, policy_version 350 (0.0005)
[2024-09-30 00:27:03,846][1150139] Updated weights for policy 0, policy_version 360 (0.0006)
[2024-09-30 00:27:04,557][1149865] Fps is (10 sec: 35635.7, 60 sec: 33314.1, 300 sec: 33314.1). Total num frames: 1499136. Throughput: 0: 7803.8. Samples: 351172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-09-30 00:27:04,557][1149865] Avg episode reward: [(0, '9.395')]
[2024-09-30 00:27:04,560][1150061] Saving new best policy, reward=9.395!
[2024-09-30 00:27:04,958][1150139] Updated weights for policy 0, policy_version 370 (0.0005)
[2024-09-30 00:27:06,158][1150139] Updated weights for policy 0, policy_version 380 (0.0006)
[2024-09-30 00:27:07,341][1150139] Updated weights for policy 0, policy_version 390 (0.0006)
[2024-09-30 00:27:08,471][1150139] Updated weights for policy 0, policy_version 400 (0.0006)
[2024-09-30 00:27:09,550][1150139] Updated weights for policy 0, policy_version 410 (0.0005)
[2024-09-30 00:27:09,557][1149865] Fps is (10 sec: 36045.1, 60 sec: 33587.2, 300 sec: 33587.2). Total num frames: 1679360. Throughput: 0: 8916.3. Samples: 403652. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-09-30 00:27:09,557][1149865] Avg episode reward: [(0, '10.451')]
[2024-09-30 00:27:09,558][1150061] Saving new best policy, reward=10.451!
[2024-09-30 00:27:10,625][1150139] Updated weights for policy 0, policy_version 420 (0.0005)
[2024-09-30 00:27:11,753][1150139] Updated weights for policy 0, policy_version 430 (0.0006)
[2024-09-30 00:27:12,906][1150139] Updated weights for policy 0, policy_version 440 (0.0005)
[2024-09-30 00:27:14,043][1150139] Updated weights for policy 0, policy_version 450 (0.0005)
[2024-09-30 00:27:14,557][1149865] Fps is (10 sec: 36044.8, 60 sec: 33810.6, 300 sec: 33810.6). Total num frames: 1859584. Throughput: 0: 8974.4. Samples: 458662. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
[2024-09-30 00:27:14,557][1149865] Avg episode reward: [(0, '13.438')]
[2024-09-30 00:27:14,560][1150061] Saving new best policy, reward=13.438!
[2024-09-30 00:27:15,159][1150139] Updated weights for policy 0, policy_version 460 (0.0006)
[2024-09-30 00:27:16,224][1150139] Updated weights for policy 0, policy_version 470 (0.0006)
[2024-09-30 00:27:17,339][1150139] Updated weights for policy 0, policy_version 480 (0.0006)
[2024-09-30 00:27:18,411][1150139] Updated weights for policy 0, policy_version 490 (0.0006)
[2024-09-30 00:27:19,490][1150139] Updated weights for policy 0, policy_version 500 (0.0006)
[2024-09-30 00:27:19,557][1149865] Fps is (10 sec: 36863.4, 60 sec: 34133.3, 300 sec: 34133.3). Total num frames: 2048000. Throughput: 0: 9008.8. Samples: 486736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-09-30 00:27:19,558][1149865] Avg episode reward: [(0, '15.719')]
[2024-09-30 00:27:19,558][1150061] Saving new best policy, reward=15.719!
[2024-09-30 00:27:20,560][1150139] Updated weights for policy 0, policy_version 510 (0.0006)
[2024-09-30 00:27:21,675][1150139] Updated weights for policy 0, policy_version 520 (0.0006)
[2024-09-30 00:27:22,733][1150139] Updated weights for policy 0, policy_version 530 (0.0006)
[2024-09-30 00:27:23,821][1150139] Updated weights for policy 0, policy_version 540 (0.0006)
[2024-09-30 00:27:24,557][1149865] Fps is (10 sec: 37683.2, 60 sec: 36249.6, 300 sec: 34406.4). Total num frames: 2236416. Throughput: 0: 9047.6. Samples: 543462. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-09-30 00:27:24,557][1149865] Avg episode reward: [(0, '18.072')]
[2024-09-30 00:27:24,569][1150061] Saving new best policy, reward=18.072!
[2024-09-30 00:27:24,893][1150139] Updated weights for policy 0, policy_version 550 (0.0006)
[2024-09-30 00:27:25,971][1150139] Updated weights for policy 0, policy_version 560 (0.0005)
[2024-09-30 00:27:27,037][1150139] Updated weights for policy 0, policy_version 570 (0.0006)
[2024-09-30 00:27:28,155][1150139] Updated weights for policy 0, policy_version 580 (0.0005)
[2024-09-30 00:27:29,272][1150139] Updated weights for policy 0, policy_version 590 (0.0006)
[2024-09-30 00:27:29,557][1149865] Fps is (10 sec: 37683.7, 60 sec: 36386.1, 300 sec: 34640.5). Total num frames: 2424832. Throughput: 0: 9118.1. Samples: 599906. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-09-30 00:27:29,557][1149865] Avg episode reward: [(0, '20.999')]
[2024-09-30 00:27:29,558][1150061] Saving new best policy, reward=20.999!
[2024-09-30 00:27:30,323][1150139] Updated weights for policy 0, policy_version 600 (0.0006)
[2024-09-30 00:27:31,407][1150139] Updated weights for policy 0, policy_version 610 (0.0006)
[2024-09-30 00:27:32,467][1150139] Updated weights for policy 0, policy_version 620 (0.0006)
[2024-09-30 00:27:33,593][1150139] Updated weights for policy 0, policy_version 630 (0.0006)
[2024-09-30 00:27:34,557][1149865] Fps is (10 sec: 37683.3, 60 sec: 36522.7, 300 sec: 34843.3). Total num frames: 2613248. Throughput: 0: 9160.0. Samples: 628636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
[2024-09-30 00:27:34,557][1149865] Avg episode reward: [(0, '20.389')]
[2024-09-30 00:27:34,683][1150139] Updated weights for policy 0, policy_version 640 (0.0005)
[2024-09-30 00:27:35,755][1150139] Updated weights for policy 0, policy_version 650 (0.0006)
[2024-09-30 00:27:36,830][1150139] Updated weights for policy 0, policy_version 660 (0.0006)
[2024-09-30 00:27:37,890][1150139] Updated weights for policy 0, policy_version 670 (0.0006)
[2024-09-30 00:27:38,971][1150139] Updated weights for policy 0, policy_version 680 (0.0006)
[2024-09-30 00:27:39,557][1149865] Fps is (10 sec: 38092.7, 60 sec: 36659.2, 300 sec: 35072.0). Total num frames: 2805760. Throughput: 0: 9181.5. Samples: 685308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-09-30 00:27:39,557][1149865] Avg episode reward: [(0, '19.388')]
[2024-09-30 00:27:40,031][1150139] Updated weights for policy 0, policy_version 690 (0.0006)
[2024-09-30 00:27:41,100][1150139] Updated weights for policy 0, policy_version 700 (0.0005)
[2024-09-30 00:27:42,153][1150139] Updated weights for policy 0, policy_version 710 (0.0006)
[2024-09-30 00:27:43,230][1150139] Updated weights for policy 0, policy_version 720 (0.0006)
[2024-09-30 00:27:44,312][1150139] Updated weights for policy 0, policy_version 730 (0.0006)
[2024-09-30 00:27:44,557][1149865] Fps is (10 sec: 38502.4, 60 sec: 36932.3, 300 sec: 35273.8). Total num frames: 2998272. Throughput: 0: 9311.9. Samples: 742806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-09-30 00:27:44,557][1149865] Avg episode reward: [(0, '22.197')]
[2024-09-30 00:27:44,560][1150061] Saving new best policy, reward=22.197!
[2024-09-30 00:27:45,376][1150139] Updated weights for policy 0, policy_version 740 (0.0006)
[2024-09-30 00:27:46,438][1150139] Updated weights for policy 0, policy_version 750 (0.0006)
[2024-09-30 00:27:47,515][1150139] Updated weights for policy 0, policy_version 760 (0.0005)
[2024-09-30 00:27:48,572][1150139] Updated weights for policy 0, policy_version 770 (0.0006)
[2024-09-30 00:27:49,557][1149865] Fps is (10 sec: 38502.4, 60 sec: 37068.9, 300 sec: 35453.2). Total num frames: 3190784. Throughput: 0: 9343.1. Samples: 771610. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
[2024-09-30 00:27:49,557][1149865] Avg episode reward: [(0, '21.389')]
[2024-09-30 00:27:49,645][1150139] Updated weights for policy 0, policy_version 780 (0.0006)
[2024-09-30 00:27:50,716][1150139] Updated weights for policy 0, policy_version 790 (0.0005)
[2024-09-30 00:27:51,800][1150139] Updated weights for policy 0, policy_version 800 (0.0006)
[2024-09-30 00:27:52,845][1150139] Updated weights for policy 0, policy_version 810 (0.0006)
[2024-09-30 00:27:53,913][1150139] Updated weights for policy 0, policy_version 820 (0.0005)
[2024-09-30 00:27:54,557][1149865] Fps is (10 sec: 38092.7, 60 sec: 37273.7, 300 sec: 35570.5). Total num frames: 3379200. Throughput: 0: 9454.0. Samples: 829084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
[2024-09-30 00:27:54,557][1149865] Avg episode reward: [(0, '25.173')]
[2024-09-30 00:27:54,560][1150061] Saving new best policy, reward=25.173!
[2024-09-30 00:27:54,982][1150139] Updated weights for policy 0, policy_version 830 (0.0006)
[2024-09-30 00:27:56,101][1150139] Updated weights for policy 0, policy_version 840 (0.0006)
[2024-09-30 00:27:57,180][1150139] Updated weights for policy 0, policy_version 850 (0.0005)
[2024-09-30 00:27:58,258][1150139] Updated weights for policy 0, policy_version 860 (0.0006)
[2024-09-30 00:27:59,351][1150139] Updated weights for policy 0, policy_version 870 (0.0005)
[2024-09-30 00:27:59,557][1149865] Fps is (10 sec: 38092.9, 60 sec: 37546.7, 300 sec: 35717.1). Total num frames: 3571712. Throughput: 0: 9494.8. Samples: 885926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
[2024-09-30 00:27:59,557][1149865] Avg episode reward: [(0, '21.345')]
[2024-09-30 00:28:00,433][1150139] Updated weights for policy 0, policy_version 880 (0.0006)
[2024-09-30 00:28:01,499][1150139] Updated weights for policy 0, policy_version 890 (0.0006)
[2024-09-30 00:28:02,611][1150139] Updated weights for policy 0, policy_version 900 (0.0006)
[2024-09-30 00:28:03,681][1150139] Updated weights for policy 0, policy_version 910 (0.0006)
[2024-09-30 00:28:04,557][1149865] Fps is (10 sec: 38092.8, 60 sec: 37683.2, 300 sec: 35810.7). Total num frames: 3760128. Throughput: 0: 9499.9. Samples: 914232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-09-30 00:28:04,557][1149865] Avg episode reward: [(0, '25.023')]
[2024-09-30 00:28:04,751][1150139] Updated weights for policy 0, policy_version 920 (0.0006)
[2024-09-30 00:28:05,834][1150139] Updated weights for policy 0, policy_version 930 (0.0006)
[2024-09-30 00:28:07,053][1150139] Updated weights for policy 0, policy_version 940 (0.0006)
[2024-09-30 00:28:08,307][1150139] Updated weights for policy 0, policy_version 950 (0.0006)
[2024-09-30 00:28:09,418][1150139] Updated weights for policy 0, policy_version 960 (0.0006)
[2024-09-30 00:28:09,557][1149865] Fps is (10 sec: 36453.7, 60 sec: 37614.8, 300 sec: 35784.1). Total num frames: 3936256. Throughput: 0: 9452.1. Samples: 968808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
[2024-09-30 00:28:09,558][1149865] Avg episode reward: [(0, '26.893')]
[2024-09-30 00:28:09,558][1150061] Saving new best policy, reward=26.893!
[2024-09-30 00:28:10,576][1150139] Updated weights for policy 0, policy_version 970 (0.0006)
[2024-09-30 00:28:11,497][1149865] Component Batcher_0 stopped!
[2024-09-30 00:28:11,497][1150061] Stopping Batcher_0...
[2024-09-30 00:28:11,497][1149865] Component RolloutWorker_w0 process died already! Don't wait for it.
[2024-09-30 00:28:11,497][1150061] Saving /home/luyang/workspace/rl/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-09-30 00:28:11,498][1150061] Loop batcher_evt_loop terminating...
[2024-09-30 00:28:11,513][1150139] Weights refcount: 2 0
[2024-09-30 00:28:11,514][1150139] Stopping InferenceWorker_p0-w0...
[2024-09-30 00:28:11,514][1150139] Loop inference_proc0-0_evt_loop terminating...
[2024-09-30 00:28:11,514][1149865] Component InferenceWorker_p0-w0 stopped!
[2024-09-30 00:28:11,527][1150138] Stopping RolloutWorker_w2...
[2024-09-30 00:28:11,527][1149865] Component RolloutWorker_w2 stopped!
[2024-09-30 00:28:11,528][1150138] Loop rollout_proc2_evt_loop terminating...
[2024-09-30 00:28:11,530][1150142] Stopping RolloutWorker_w3...
[2024-09-30 00:28:11,530][1149865] Component RolloutWorker_w3 stopped!
[2024-09-30 00:28:11,530][1150142] Loop rollout_proc3_evt_loop terminating...
[2024-09-30 00:28:11,531][1149865] Component RolloutWorker_w5 stopped!
[2024-09-30 00:28:11,531][1150137] Stopping RolloutWorker_w5...
[2024-09-30 00:28:11,531][1149865] Component RolloutWorker_w6 stopped!
[2024-09-30 00:28:11,531][1150145] Stopping RolloutWorker_w6...
[2024-09-30 00:28:11,531][1150137] Loop rollout_proc5_evt_loop terminating...
[2024-09-30 00:28:11,531][1150145] Loop rollout_proc6_evt_loop terminating...
[2024-09-30 00:28:11,532][1149865] Component RolloutWorker_w1 stopped!
[2024-09-30 00:28:11,532][1150143] Stopping RolloutWorker_w1...
[2024-09-30 00:28:11,533][1150143] Loop rollout_proc1_evt_loop terminating...
[2024-09-30 00:28:11,533][1149865] Component RolloutWorker_w4 stopped!
[2024-09-30 00:28:11,533][1150141] Stopping RolloutWorker_w4...
[2024-09-30 00:28:11,533][1150141] Loop rollout_proc4_evt_loop terminating...
[2024-09-30 00:28:11,536][1149865] Component RolloutWorker_w7 stopped!
[2024-09-30 00:28:11,536][1150140] Stopping RolloutWorker_w7...
[2024-09-30 00:28:11,536][1150140] Loop rollout_proc7_evt_loop terminating...
[2024-09-30 00:28:11,548][1150061] Saving /home/luyang/workspace/rl/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-09-30 00:28:11,677][1150061] Stopping LearnerWorker_p0...
[2024-09-30 00:28:11,677][1150061] Loop learner_proc0_evt_loop terminating...
[2024-09-30 00:28:11,677][1149865] Component LearnerWorker_p0 stopped!
[2024-09-30 00:28:11,678][1149865] Waiting for process learner_proc0 to stop...
[2024-09-30 00:28:12,213][1149865] Waiting for process inference_proc0-0 to join...
[2024-09-30 00:28:12,214][1149865] Waiting for process rollout_proc0 to join...
[2024-09-30 00:28:12,214][1149865] Waiting for process rollout_proc1 to join...
[2024-09-30 00:28:12,214][1149865] Waiting for process rollout_proc2 to join...
[2024-09-30 00:28:12,214][1149865] Waiting for process rollout_proc3 to join...
[2024-09-30 00:28:12,214][1149865] Waiting for process rollout_proc4 to join...
[2024-09-30 00:28:12,215][1149865] Waiting for process rollout_proc5 to join...
[2024-09-30 00:28:12,215][1149865] Waiting for process rollout_proc6 to join...
[2024-09-30 00:28:12,215][1149865] Waiting for process rollout_proc7 to join...
[2024-09-30 00:28:12,215][1149865] Batcher 0 profile tree view:
batching: 8.1702, releasing_batches: 0.0148
[2024-09-30 00:28:12,215][1149865] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0000
wait_policy_total: 2.2430
update_model: 1.6718
weight_update: 0.0006
one_step: 0.0013
handle_policy_step: 101.6105
deserialize: 4.2527, stack: 0.5251, obs_to_device_normalize: 21.3149, forward: 52.1177, send_messages: 6.7725
prepare_outputs: 11.8901
to_cpu: 6.4354
[2024-09-30 00:28:12,216][1149865] Learner 0 profile tree view:
misc: 0.0031, prepare_batch: 4.0428
train: 10.3860
epoch_init: 0.0033, minibatch_init: 0.0037, losses_postprocess: 0.1662, kl_divergence: 0.2113, after_optimizer: 0.8304
calculate_losses: 4.6270
losses_init: 0.0020, forward_head: 0.3762, bptt_initial: 2.3802, tail: 0.3318, advantages_returns: 0.0873, losses: 0.6229
bptt: 0.7209
bptt_forward_core: 0.6909
update: 4.3204
clip: 0.4495
[2024-09-30 00:28:12,216][1149865] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.0819, enqueue_policy_requests: 4.5546, env_step: 67.0989, overhead: 3.2408, complete_rollouts: 0.1226
save_policy_outputs: 5.6070
split_output_tensors: 1.8787
[2024-09-30 00:28:12,216][1149865] Loop Runner_EvtLoop terminating...
[2024-09-30 00:28:12,216][1149865] Runner profile tree view:
main_loop: 115.9303
[2024-09-30 00:28:12,216][1149865] Collected {0: 4005888}, FPS: 34554.3
[2024-09-30 00:28:12,419][1149865] Loading existing experiment configuration from /home/luyang/workspace/rl/train_dir/default_experiment/config.json
[2024-09-30 00:28:12,419][1149865] Overriding arg 'num_workers' with value 1 passed from command line
[2024-09-30 00:28:12,420][1149865] Adding new argument 'no_render'=True that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'save_video'=True that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'video_name'=None that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'push_to_hub'=True that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'hf_repository'='esperesa/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'policy_index'=0 that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'train_script'=None that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Adding new argument 'enjoy_script'=None that is not in the saved config file!
[2024-09-30 00:28:12,420][1149865] Using frameskip 1 and render_action_repeat=4 for evaluation
[2024-09-30 00:28:12,441][1149865] Doom resolution: 160x120, resize resolution: (128, 72)
[2024-09-30 00:28:12,443][1149865] RunningMeanStd input shape: (3, 72, 128)
[2024-09-30 00:28:12,443][1149865] RunningMeanStd input shape: (1,)
[2024-09-30 00:28:12,452][1149865] ConvEncoder: input_channels=3
[2024-09-30 00:28:12,522][1149865] Conv encoder output size: 512
[2024-09-30 00:28:12,522][1149865] Policy head output size: 512
[2024-09-30 00:28:12,681][1149865] Loading state from checkpoint /home/luyang/workspace/rl/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
[2024-09-30 00:28:13,271][1149865] Num frames 100...
[2024-09-30 00:28:13,350][1149865] Num frames 200...
[2024-09-30 00:28:13,427][1149865] Num frames 300...
[2024-09-30 00:28:13,503][1149865] Num frames 400...
[2024-09-30 00:28:13,581][1149865] Num frames 500...
[2024-09-30 00:28:13,659][1149865] Num frames 600...
[2024-09-30 00:28:13,738][1149865] Num frames 700...
[2024-09-30 00:28:13,815][1149865] Num frames 800...
[2024-09-30 00:28:13,894][1149865] Num frames 900...
[2024-09-30 00:28:13,973][1149865] Num frames 1000...
[2024-09-30 00:28:14,052][1149865] Num frames 1100...
[2024-09-30 00:28:14,132][1149865] Num frames 1200...
[2024-09-30 00:28:14,208][1149865] Num frames 1300...
[2024-09-30 00:28:14,285][1149865] Num frames 1400...
[2024-09-30 00:28:14,364][1149865] Num frames 1500...
[2024-09-30 00:28:14,445][1149865] Avg episode rewards: #0: 34.360, true rewards: #0: 15.360
[2024-09-30 00:28:14,445][1149865] Avg episode reward: 34.360, avg true_objective: 15.360
[2024-09-30 00:28:14,497][1149865] Num frames 1600...
[2024-09-30 00:28:14,575][1149865] Num frames 1700...
[2024-09-30 00:28:14,654][1149865] Num frames 1800...
[2024-09-30 00:28:14,733][1149865] Num frames 1900...
[2024-09-30 00:28:14,811][1149865] Num frames 2000...
[2024-09-30 00:28:14,891][1149865] Num frames 2100...
[2024-09-30 00:28:14,967][1149865] Num frames 2200...
[2024-09-30 00:28:15,045][1149865] Num frames 2300...
[2024-09-30 00:28:15,125][1149865] Num frames 2400...
[2024-09-30 00:28:15,204][1149865] Num frames 2500...
[2024-09-30 00:28:15,283][1149865] Num frames 2600...
[2024-09-30 00:28:15,363][1149865] Num frames 2700...
[2024-09-30 00:28:15,443][1149865] Num frames 2800...
[2024-09-30 00:28:15,523][1149865] Num frames 2900...
[2024-09-30 00:28:15,602][1149865] Num frames 3000...
[2024-09-30 00:28:15,681][1149865] Num frames 3100...
[2024-09-30 00:28:15,758][1149865] Num frames 3200...
[2024-09-30 00:28:15,834][1149865] Num frames 3300...
[2024-09-30 00:28:15,958][1149865] Avg episode rewards: #0: 40.959, true rewards: #0: 16.960
[2024-09-30 00:28:15,958][1149865] Avg episode reward: 40.959, avg true_objective: 16.960
[2024-09-30 00:28:15,966][1149865] Num frames 3400...
[2024-09-30 00:28:16,049][1149865] Num frames 3500...
[2024-09-30 00:28:16,127][1149865] Num frames 3600...
[2024-09-30 00:28:16,205][1149865] Num frames 3700...
[2024-09-30 00:28:16,284][1149865] Num frames 3800...
[2024-09-30 00:28:16,363][1149865] Num frames 3900...
[2024-09-30 00:28:16,443][1149865] Num frames 4000...
[2024-09-30 00:28:16,521][1149865] Num frames 4100...
[2024-09-30 00:28:16,598][1149865] Num frames 4200...
[2024-09-30 00:28:16,675][1149865] Num frames 4300...
[2024-09-30 00:28:16,754][1149865] Num frames 4400...
[2024-09-30 00:28:16,832][1149865] Num frames 4500...
[2024-09-30 00:28:16,919][1149865] Avg episode rewards: #0: 36.480, true rewards: #0: 15.147
[2024-09-30 00:28:16,919][1149865] Avg episode reward: 36.480, avg true_objective: 15.147
[2024-09-30 00:28:16,968][1149865] Num frames 4600...
[2024-09-30 00:28:17,047][1149865] Num frames 4700...
[2024-09-30 00:28:17,126][1149865] Num frames 4800...
[2024-09-30 00:28:17,206][1149865] Num frames 4900...
[2024-09-30 00:28:17,282][1149865] Num frames 5000...
[2024-09-30 00:28:17,358][1149865] Num frames 5100...
[2024-09-30 00:28:17,470][1149865] Avg episode rewards: #0: 31.192, true rewards: #0: 12.942
[2024-09-30 00:28:17,471][1149865] Avg episode reward: 31.192, avg true_objective: 12.942
[2024-09-30 00:28:17,490][1149865] Num frames 5200...
[2024-09-30 00:28:17,569][1149865] Num frames 5300...
[2024-09-30 00:28:17,649][1149865] Num frames 5400...
[2024-09-30 00:28:17,729][1149865] Num frames 5500...
[2024-09-30 00:28:17,807][1149865] Num frames 5600...
[2024-09-30 00:28:17,887][1149865] Num frames 5700...
[2024-09-30 00:28:17,966][1149865] Num frames 5800...
[2024-09-30 00:28:18,043][1149865] Num frames 5900...
[2024-09-30 00:28:18,120][1149865] Num frames 6000...
[2024-09-30 00:28:18,196][1149865] Num frames 6100...
[2024-09-30 00:28:18,274][1149865] Num frames 6200...
[2024-09-30 00:28:18,352][1149865] Num frames 6300...
[2024-09-30 00:28:18,477][1149865] Avg episode rewards: #0: 30.786, true rewards: #0: 12.786
[2024-09-30 00:28:18,477][1149865] Avg episode reward: 30.786, avg true_objective: 12.786
[2024-09-30 00:28:18,484][1149865] Num frames 6400...
[2024-09-30 00:28:18,564][1149865] Num frames 6500...
[2024-09-30 00:28:18,643][1149865] Num frames 6600...
[2024-09-30 00:28:18,723][1149865] Num frames 6700...
[2024-09-30 00:28:18,803][1149865] Num frames 6800...
[2024-09-30 00:28:18,879][1149865] Num frames 6900...
[2024-09-30 00:28:18,957][1149865] Num frames 7000...
[2024-09-30 00:28:19,033][1149865] Num frames 7100...
[2024-09-30 00:28:19,110][1149865] Num frames 7200...
[2024-09-30 00:28:19,190][1149865] Num frames 7300...
[2024-09-30 00:28:19,271][1149865] Num frames 7400...
[2024-09-30 00:28:19,353][1149865] Num frames 7500...
[2024-09-30 00:28:19,443][1149865] Num frames 7600...
[2024-09-30 00:28:19,538][1149865] Num frames 7700...
[2024-09-30 00:28:19,630][1149865] Num frames 7800...
[2024-09-30 00:28:19,721][1149865] Num frames 7900...
[2024-09-30 00:28:19,817][1149865] Num frames 8000...
[2024-09-30 00:28:19,910][1149865] Num frames 8100...
[2024-09-30 00:28:20,014][1149865] Avg episode rewards: #0: 33.588, true rewards: #0: 13.588
[2024-09-30 00:28:20,015][1149865] Avg episode reward: 33.588, avg true_objective: 13.588
[2024-09-30 00:28:20,062][1149865] Num frames 8200...
[2024-09-30 00:28:20,156][1149865] Num frames 8300...
[2024-09-30 00:28:20,246][1149865] Num frames 8400...
[2024-09-30 00:28:20,341][1149865] Num frames 8500...
[2024-09-30 00:28:20,433][1149865] Num frames 8600...
[2024-09-30 00:28:20,523][1149865] Num frames 8700...
[2024-09-30 00:28:20,616][1149865] Num frames 8800...
[2024-09-30 00:28:20,707][1149865] Num frames 8900...
[2024-09-30 00:28:20,800][1149865] Num frames 9000...
[2024-09-30 00:28:20,892][1149865] Num frames 9100...
[2024-09-30 00:28:20,986][1149865] Num frames 9200...
[2024-09-30 00:28:21,079][1149865] Num frames 9300...
[2024-09-30 00:28:21,172][1149865] Num frames 9400...
[2024-09-30 00:28:21,264][1149865] Num frames 9500...
[2024-09-30 00:28:21,356][1149865] Num frames 9600...
[2024-09-30 00:28:21,451][1149865] Num frames 9700...
[2024-09-30 00:28:21,526][1149865] Avg episode rewards: #0: 34.030, true rewards: #0: 13.887
[2024-09-30 00:28:21,526][1149865] Avg episode reward: 34.030, avg true_objective: 13.887
[2024-09-30 00:28:21,591][1149865] Num frames 9800...
[2024-09-30 00:28:21,672][1149865] Num frames 9900...
[2024-09-30 00:28:21,757][1149865] Num frames 10000...
[2024-09-30 00:28:21,850][1149865] Num frames 10100...
[2024-09-30 00:28:21,945][1149865] Num frames 10200...
[2024-09-30 00:28:22,035][1149865] Num frames 10300...
[2024-09-30 00:28:22,128][1149865] Num frames 10400...
[2024-09-30 00:28:22,220][1149865] Num frames 10500...
[2024-09-30 00:28:22,312][1149865] Num frames 10600...
[2024-09-30 00:28:22,393][1149865] Num frames 10700...
[2024-09-30 00:28:22,474][1149865] Num frames 10800...
[2024-09-30 00:28:22,537][1149865] Avg episode rewards: #0: 32.886, true rewards: #0: 13.511
[2024-09-30 00:28:22,537][1149865] Avg episode reward: 32.886, avg true_objective: 13.511
[2024-09-30 00:28:22,621][1149865] Num frames 10900...
[2024-09-30 00:28:22,714][1149865] Num frames 11000...
[2024-09-30 00:28:22,806][1149865] Num frames 11100...
[2024-09-30 00:28:22,898][1149865] Num frames 11200...
[2024-09-30 00:28:22,990][1149865] Num frames 11300...
[2024-09-30 00:28:23,082][1149865] Num frames 11400...
[2024-09-30 00:28:23,165][1149865] Num frames 11500...
[2024-09-30 00:28:23,247][1149865] Num frames 11600...
[2024-09-30 00:28:23,338][1149865] Num frames 11700...
[2024-09-30 00:28:23,432][1149865] Num frames 11800...
[2024-09-30 00:28:23,522][1149865] Num frames 11900...
[2024-09-30 00:28:23,616][1149865] Num frames 12000...
[2024-09-30 00:28:23,730][1149865] Num frames 12100...
[2024-09-30 00:28:23,823][1149865] Num frames 12200...
[2024-09-30 00:28:23,904][1149865] Num frames 12300...
[2024-09-30 00:28:23,983][1149865] Num frames 12400...
[2024-09-30 00:28:24,063][1149865] Num frames 12500...
[2024-09-30 00:28:24,150][1149865] Num frames 12600...
[2024-09-30 00:28:24,230][1149865] Num frames 12700...
[2024-09-30 00:28:24,306][1149865] Num frames 12800...
[2024-09-30 00:28:24,390][1149865] Avg episode rewards: #0: 35.268, true rewards: #0: 14.268
[2024-09-30 00:28:24,391][1149865] Avg episode reward: 35.268, avg true_objective: 14.268
[2024-09-30 00:28:24,438][1149865] Num frames 12900...
[2024-09-30 00:28:24,516][1149865] Num frames 13000...
[2024-09-30 00:28:24,594][1149865] Num frames 13100...
[2024-09-30 00:28:24,675][1149865] Num frames 13200...
[2024-09-30 00:28:24,755][1149865] Num frames 13300...
[2024-09-30 00:28:24,833][1149865] Num frames 13400...
[2024-09-30 00:28:24,946][1149865] Avg episode rewards: #0: 33.076, true rewards: #0: 13.476
[2024-09-30 00:28:24,946][1149865] Avg episode reward: 33.076, avg true_objective: 13.476
[2024-09-30 00:28:42,313][1149865] Replay video saved to /home/luyang/workspace/rl/train_dir/default_experiment/replay.mp4!
|