File size: 67,497 Bytes
c81c30d |
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 |
diff --git a/notebooks/unit8/unit8_part2.ipynb b/notebooks/unit8/unit8_part2.ipynb
index b36924a..d7fd26d 100644
--- a/notebooks/unit8/unit8_part2.ipynb
+++ b/notebooks/unit8/unit8_part2.ipynb
@@ -3,8 +3,8 @@
{
"cell_type": "markdown",
"metadata": {
- "id": "view-in-github",
- "colab_type": "text"
+ "colab_type": "text",
+ "id": "view-in-github"
},
"source": [
"<a href=\"https://colab.research.google.com/github/huggingface/deep-rl-class/blob/EdBeeching%2FPPOPart2/notebooks/unit8/unit8_part2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
@@ -202,11 +202,26 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {
"id": "RJMxkaldwIVx"
},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "CalledProcessError",
+ "evalue": "Command 'b'# Install ViZDoom deps from \\n# https://github.com/mwydmuch/ViZDoom/blob/master/doc/Building.md#-linux\\n\\napt-get install build-essential zlib1g-dev libsdl2-dev libjpeg-dev \\\\\\nnasm tar libbz2-dev libgtk2.0-dev cmake git libfluidsynth-dev libgme-dev \\\\\\nlibopenal-dev timidity libwildmidi-dev unzip ffmpeg\\n\\n# Boost libraries\\napt-get install libboost-all-dev\\n\\n# Lua binding dependencies\\napt-get install liblua5.1-dev\\n'' returned non-zero exit status 100.",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mCalledProcessError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m get_ipython()\u001b[39m.\u001b[39;49mrun_cell_magic(\u001b[39m'\u001b[39;49m\u001b[39mbash\u001b[39;49m\u001b[39m'\u001b[39;49m, \u001b[39m'\u001b[39;49m\u001b[39m'\u001b[39;49m, \u001b[39m'\u001b[39;49m\u001b[39m# Install ViZDoom deps from \u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39m# https://github.com/mwydmuch/ViZDoom/blob/master/doc/Building.md#-linux\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39m\\n\u001b[39;49;00m\u001b[39mapt-get install build-essential zlib1g-dev libsdl2-dev libjpeg-dev \u001b[39;49m\u001b[39m\\\\\u001b[39;49;00m\u001b[39m\\n\u001b[39;49;00m\u001b[39mnasm tar libbz2-dev libgtk2.0-dev cmake git libfluidsynth-dev libgme-dev \u001b[39;49m\u001b[39m\\\\\u001b[39;49;00m\u001b[39m\\n\u001b[39;49;00m\u001b[39mlibopenal-dev timidity libwildmidi-dev unzip ffmpeg\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39m\\n\u001b[39;49;00m\u001b[39m# Boost libraries\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39mapt-get install libboost-all-dev\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39m\\n\u001b[39;49;00m\u001b[39m# Lua binding dependencies\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39mapt-get install liblua5.1-dev\u001b[39;49m\u001b[39m\\n\u001b[39;49;00m\u001b[39m'\u001b[39;49m)\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/IPython/core/interactiveshell.py:2430\u001b[0m, in \u001b[0;36mInteractiveShell.run_cell_magic\u001b[0;34m(self, magic_name, line, cell)\u001b[0m\n\u001b[1;32m 2428\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mbuiltin_trap:\n\u001b[1;32m 2429\u001b[0m args \u001b[39m=\u001b[39m (magic_arg_s, cell)\n\u001b[0;32m-> 2430\u001b[0m result \u001b[39m=\u001b[39m fn(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n\u001b[1;32m 2432\u001b[0m \u001b[39m# The code below prevents the output from being displayed\u001b[39;00m\n\u001b[1;32m 2433\u001b[0m \u001b[39m# when using magics with decodator @output_can_be_silenced\u001b[39;00m\n\u001b[1;32m 2434\u001b[0m \u001b[39m# when the last Python token in the expression is a ';'.\u001b[39;00m\n\u001b[1;32m 2435\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mgetattr\u001b[39m(fn, magic\u001b[39m.\u001b[39mMAGIC_OUTPUT_CAN_BE_SILENCED, \u001b[39mFalse\u001b[39;00m):\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/IPython/core/magics/script.py:153\u001b[0m, in \u001b[0;36mScriptMagics._make_script_magic.<locals>.named_script_magic\u001b[0;34m(line, cell)\u001b[0m\n\u001b[1;32m 151\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m 152\u001b[0m line \u001b[39m=\u001b[39m script\n\u001b[0;32m--> 153\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mshebang(line, cell)\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/IPython/core/magics/script.py:305\u001b[0m, in \u001b[0;36mScriptMagics.shebang\u001b[0;34m(self, line, cell)\u001b[0m\n\u001b[1;32m 300\u001b[0m \u001b[39mif\u001b[39;00m args\u001b[39m.\u001b[39mraise_error \u001b[39mand\u001b[39;00m p\u001b[39m.\u001b[39mreturncode \u001b[39m!=\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[1;32m 301\u001b[0m \u001b[39m# If we get here and p.returncode is still None, we must have\u001b[39;00m\n\u001b[1;32m 302\u001b[0m \u001b[39m# killed it but not yet seen its return code. We don't wait for it,\u001b[39;00m\n\u001b[1;32m 303\u001b[0m \u001b[39m# in case it's stuck in uninterruptible sleep. -9 = SIGKILL\u001b[39;00m\n\u001b[1;32m 304\u001b[0m rc \u001b[39m=\u001b[39m p\u001b[39m.\u001b[39mreturncode \u001b[39mor\u001b[39;00m \u001b[39m-\u001b[39m\u001b[39m9\u001b[39m\n\u001b[0;32m--> 305\u001b[0m \u001b[39mraise\u001b[39;00m CalledProcessError(rc, cell)\n",
+ "\u001b[0;31mCalledProcessError\u001b[0m: Command 'b'# Install ViZDoom deps from \\n# https://github.com/mwydmuch/ViZDoom/blob/master/doc/Building.md#-linux\\n\\napt-get install build-essential zlib1g-dev libsdl2-dev libjpeg-dev \\\\\\nnasm tar libbz2-dev libgtk2.0-dev cmake git libfluidsynth-dev libgme-dev \\\\\\nlibopenal-dev timidity libwildmidi-dev unzip ffmpeg\\n\\n# Boost libraries\\napt-get install libboost-all-dev\\n\\n# Lua binding dependencies\\napt-get install liblua5.1-dev\\n'' returned non-zero exit status 100."
+ ]
+ }
+ ],
"source": [
"%%capture\n",
"%%bash\n",
@@ -236,11 +251,162 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {
"id": "bbqfPZnIsvA6"
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Collecting sample-factory\n",
+ " Downloading sample_factory-2.0.3-py3-none-any.whl (9.0 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m9.0/9.0 MB\u001b[0m \u001b[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0mm\n",
+ "\u001b[?25hCollecting huggingface-hub<1.0,>=0.10.0\n",
+ " Downloading huggingface_hub-0.12.1-py3-none-any.whl (190 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m190.3/190.3 kB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting gym<1.0,>=0.26.1\n",
+ " Downloading gym-0.26.2.tar.gz (721 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m721.7/721.7 kB\u001b[0m \u001b[31m26.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
+ "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
+ "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25hCollecting colorlog\n",
+ " Downloading colorlog-6.7.0-py2.py3-none-any.whl (11 kB)\n",
+ "Collecting filelock\n",
+ " Using cached filelock-3.9.0-py3-none-any.whl (9.7 kB)\n",
+ "Requirement already satisfied: psutil>=5.7.0 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from sample-factory) (5.9.0)\n",
+ "Collecting faster-fifo<2.0,>=1.4.2\n",
+ " Downloading faster-fifo-1.4.2.tar.gz (84 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m84.6/84.6 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
+ "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
+ "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25hCollecting pyglet\n",
+ " Downloading pyglet-2.0.4-py3-none-any.whl (831 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m831.0/831.0 kB\u001b[0m \u001b[31m39.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: torch!=1.13.0,<2.0,>=1.9 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from sample-factory) (1.13.1)\n",
+ "Collecting threadpoolctl>=2.0.0\n",
+ " Using cached threadpoolctl-3.1.0-py3-none-any.whl (14 kB)\n",
+ "Collecting signal-slot-mp<2.0,>=1.0.3\n",
+ " Downloading signal_slot_mp-1.0.3-py3-none-any.whl (11 kB)\n",
+ "Collecting opencv-python!=3.4.18.65\n",
+ " Downloading opencv_python-4.7.0.72-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (61.8 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m61.8/61.8 MB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
+ "\u001b[?25hCollecting wandb>=0.12.9\n",
+ " Downloading wandb-0.13.10-py3-none-any.whl (2.0 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m29.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: numpy<2.0,>=1.18.1 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from sample-factory) (1.23.5)\n",
+ "Collecting tensorboard>=1.15.0\n",
+ " Using cached tensorboard-2.12.0-py3-none-any.whl (5.6 MB)\n",
+ "Collecting tensorboardx>=2.0\n",
+ " Downloading tensorboardX-2.6-py2.py3-none-any.whl (114 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hRequirement already satisfied: setuptools>=45.2.0 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from faster-fifo<2.0,>=1.4.2->sample-factory) (65.6.3)\n",
+ "Collecting cython>=0.29\n",
+ " Using cached Cython-0.29.33-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (1.9 MB)\n",
+ "Collecting gym-notices>=0.0.4\n",
+ " Downloading gym_notices-0.0.8-py3-none-any.whl (3.0 kB)\n",
+ "Collecting cloudpickle>=1.2.0\n",
+ " Downloading cloudpickle-2.2.1-py3-none-any.whl (25 kB)\n",
+ "Collecting tqdm>=4.42.1\n",
+ " Using cached tqdm-4.64.1-py2.py3-none-any.whl (78 kB)\n",
+ "Collecting pyyaml>=5.1\n",
+ " Using cached PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (682 kB)\n",
+ "Requirement already satisfied: packaging>=20.9 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.10.0->sample-factory) (22.0)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.10.0->sample-factory) (4.4.0)\n",
+ "Requirement already satisfied: requests in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.10.0->sample-factory) (2.28.1)\n",
+ "Collecting absl-py>=0.4\n",
+ " Using cached absl_py-1.4.0-py3-none-any.whl (126 kB)\n",
+ "Collecting tensorboard-plugin-wit>=1.6.0\n",
+ " Using cached tensorboard_plugin_wit-1.8.1-py3-none-any.whl (781 kB)\n",
+ "Collecting markdown>=2.6.8\n",
+ " Using cached Markdown-3.4.1-py3-none-any.whl (93 kB)\n",
+ "Requirement already satisfied: wheel>=0.26 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from tensorboard>=1.15.0->sample-factory) (0.38.4)\n",
+ "Collecting google-auth-oauthlib<0.5,>=0.4.1\n",
+ " Using cached google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)\n",
+ "Collecting google-auth<3,>=1.6.3\n",
+ " Downloading google_auth-2.16.1-py2.py3-none-any.whl (177 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m177.2/177.2 kB\u001b[0m \u001b[31m19.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting tensorboard-data-server<0.8.0,>=0.7.0\n",
+ " Using cached tensorboard_data_server-0.7.0-py3-none-manylinux2014_x86_64.whl (6.6 MB)\n",
+ "Collecting grpcio>=1.48.2\n",
+ " Downloading grpcio-1.51.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.8 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m28.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
+ "\u001b[?25hCollecting werkzeug>=1.0.1\n",
+ " Downloading Werkzeug-2.2.3-py3-none-any.whl (233 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m233.6/233.6 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting protobuf>=3.19.6\n",
+ " Downloading protobuf-4.22.0-cp37-abi3-manylinux2014_x86_64.whl (302 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m302.4/302.4 kB\u001b[0m \u001b[31m23.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25h Using cached protobuf-3.20.3-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.1 MB)\n",
+ "Collecting GitPython>=1.0.0\n",
+ " Downloading GitPython-3.1.31-py3-none-any.whl (184 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m184.3/184.3 kB\u001b[0m \u001b[31m18.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting docker-pycreds>=0.4.0\n",
+ " Using cached docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
+ "Collecting pathtools\n",
+ " Using cached pathtools-0.1.2-py3-none-any.whl\n",
+ "Collecting sentry-sdk>=1.0.0\n",
+ " Downloading sentry_sdk-1.15.0-py2.py3-none-any.whl (181 kB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m181.3/181.3 kB\u001b[0m \u001b[31m20.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+ "\u001b[?25hCollecting setproctitle\n",
+ " Using cached setproctitle-1.3.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)\n",
+ "Collecting appdirs>=1.4.3\n",
+ " Using cached appdirs-1.4.4-py2.py3-none-any.whl (9.6 kB)\n",
+ "Collecting Click!=8.0.0,>=7.0\n",
+ " Using cached click-8.1.3-py3-none-any.whl (96 kB)\n",
+ "Requirement already satisfied: six>=1.4.0 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from docker-pycreds>=0.4.0->wandb>=0.12.9->sample-factory) (1.16.0)\n",
+ "Collecting gitdb<5,>=4.0.1\n",
+ " Using cached gitdb-4.0.10-py3-none-any.whl (62 kB)\n",
+ "Collecting pyasn1-modules>=0.2.1\n",
+ " Using cached pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)\n",
+ "Collecting rsa<5,>=3.1.4\n",
+ " Using cached rsa-4.9-py3-none-any.whl (34 kB)\n",
+ "Collecting cachetools<6.0,>=2.0.0\n",
+ " Using cached cachetools-5.3.0-py3-none-any.whl (9.3 kB)\n",
+ "Collecting requests-oauthlib>=0.7.0\n",
+ " Using cached requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from requests->huggingface-hub<1.0,>=0.10.0->sample-factory) (1.26.14)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from requests->huggingface-hub<1.0,>=0.10.0->sample-factory) (2022.12.7)\n",
+ "Requirement already satisfied: charset-normalizer<3,>=2 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from requests->huggingface-hub<1.0,>=0.10.0->sample-factory) (2.0.4)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from requests->huggingface-hub<1.0,>=0.10.0->sample-factory) (3.4)\n",
+ "Collecting MarkupSafe>=2.1.1\n",
+ " Using cached MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)\n",
+ "Collecting smmap<6,>=3.0.1\n",
+ " Using cached smmap-5.0.0-py3-none-any.whl (24 kB)\n",
+ "Collecting pyasn1<0.5.0,>=0.4.6\n",
+ " Using cached pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)\n",
+ "Collecting oauthlib>=3.0.0\n",
+ " Using cached oauthlib-3.2.2-py3-none-any.whl (151 kB)\n",
+ "Building wheels for collected packages: faster-fifo, gym\n",
+ " Building wheel for faster-fifo (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25h Created wheel for faster-fifo: filename=faster_fifo-1.4.2-cp310-cp310-linux_x86_64.whl size=78864 sha256=db802db0bb9e4e639957e0cc929a5055871d73dac2a78aab10dd613331d4e086\n",
+ " Stored in directory: /home/chqma/.cache/pip/wheels/46/57/35/44590621055121fe1a2f1ae60846e531621498f6d6e48c8975\n",
+ " Building wheel for gym (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25h Created wheel for gym: filename=gym-0.26.2-py3-none-any.whl size=827634 sha256=2ecaeda2a512edc3ad62eb999df1ba486447df53cdcd38d3cd5acc3b0b013d44\n",
+ " Stored in directory: /home/chqma/.cache/pip/wheels/ae/5f/67/64914473eb34e9ba89dbc7eefe7e9be8f6673fbc6f0273b29f\n",
+ "Successfully built faster-fifo gym\n",
+ "Installing collected packages: tensorboard-plugin-wit, pyglet, pyasn1, pathtools, gym-notices, appdirs, tqdm, threadpoolctl, tensorboard-data-server, smmap, setproctitle, sentry-sdk, rsa, pyyaml, pyasn1-modules, protobuf, opencv-python, oauthlib, MarkupSafe, markdown, grpcio, filelock, docker-pycreds, cython, colorlog, cloudpickle, Click, cachetools, absl-py, werkzeug, tensorboardx, requests-oauthlib, huggingface-hub, gym, google-auth, gitdb, faster-fifo, signal-slot-mp, google-auth-oauthlib, GitPython, wandb, tensorboard, sample-factory\n",
+ "Successfully installed Click-8.1.3 GitPython-3.1.31 MarkupSafe-2.1.2 absl-py-1.4.0 appdirs-1.4.4 cachetools-5.3.0 cloudpickle-2.2.1 colorlog-6.7.0 cython-0.29.33 docker-pycreds-0.4.0 faster-fifo-1.4.2 filelock-3.9.0 gitdb-4.0.10 google-auth-2.16.1 google-auth-oauthlib-0.4.6 grpcio-1.51.3 gym-0.26.2 gym-notices-0.0.8 huggingface-hub-0.12.1 markdown-3.4.1 oauthlib-3.2.2 opencv-python-4.7.0.72 pathtools-0.1.2 protobuf-3.20.3 pyasn1-0.4.8 pyasn1-modules-0.2.8 pyglet-2.0.4 pyyaml-6.0 requests-oauthlib-1.3.1 rsa-4.9 sample-factory-2.0.3 sentry-sdk-1.15.0 setproctitle-1.3.2 signal-slot-mp-1.0.3 smmap-5.0.0 tensorboard-2.12.0 tensorboard-data-server-0.7.0 tensorboard-plugin-wit-1.8.1 tensorboardx-2.6 threadpoolctl-3.1.0 tqdm-4.64.1 wandb-0.13.10 werkzeug-2.2.3\n",
+ "Collecting vizdoom\n",
+ " Downloading vizdoom-1.1.14.tar.gz (15.7 MB)\n",
+ "\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
+ "\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
+ "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
+ "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25hRequirement already satisfied: numpy in /home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages (from vizdoom) (1.23.5)\n",
+ "Building wheels for collected packages: vizdoom\n",
+ " Building wheel for vizdoom (pyproject.toml) ... \u001b[?25ldone\n",
+ "\u001b[?25h Created wheel for vizdoom: filename=vizdoom-1.1.14-cp310-cp310-linux_x86_64.whl size=14192416 sha256=732a3631973e8da574807abc6da03d63e48238fdf6024c6f34c11e5c4dcf2056\n",
+ " Stored in directory: /home/chqma/.cache/pip/wheels/a4/13/80/6927dae582137aef0836f48491051c797a5de184891b8ca6c5\n",
+ "Successfully built vizdoom\n",
+ "Installing collected packages: vizdoom\n",
+ "Successfully installed vizdoom-1.1.14\n"
+ ]
+ }
+ ],
"source": [
"# install python libraries\n",
"!pip install sample-factory\n",
@@ -258,24 +424,24 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {
"id": "bCgZbeiavcDU"
},
"outputs": [],
"source": [
"import functools\n",
- "\n",
+ "from encoder import make_vizdoom_encoder\n",
"from sample_factory.algo.utils.context import global_model_factory\n",
"from sample_factory.cfg.arguments import parse_full_cfg, parse_sf_args\n",
"from sample_factory.envs.env_utils import register_env\n",
"from sample_factory.train import run_rl\n",
"\n",
- "from sf_examples.vizdoom.doom.doom_model import make_vizdoom_encoder\n",
"from sf_examples.vizdoom.doom.doom_params import add_doom_env_args, doom_override_defaults\n",
"from sf_examples.vizdoom.doom.doom_utils import DOOM_ENVS, make_doom_env_from_spec\n",
"\n",
"\n",
+ "\n",
"# Registers all the ViZDoom environments\n",
"def register_vizdoom_envs():\n",
" for env_spec in DOOM_ENVS:\n",
@@ -346,11 +512,88 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "env: CUDA_VISIBLE_DEVICES=1\n"
+ ]
+ }
+ ],
+ "source": [
+ "%env CUDA_VISIBLE_DEVICES=1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
"metadata": {
"id": "y_TeicMvyKHP"
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[33m[2023-02-24 08:05:26,614][795538] Environment doom_basic already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,616][795538] Environment doom_two_colors_easy already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,617][795538] Environment doom_two_colors_hard already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,619][795538] Environment doom_dm already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,619][795538] Environment doom_dwango5 already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,620][795538] Environment doom_my_way_home_flat_actions already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,621][795538] Environment doom_defend_the_center_flat_actions already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,621][795538] Environment doom_my_way_home already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,623][795538] Environment doom_deadly_corridor already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,623][795538] Environment doom_defend_the_center already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,624][795538] Environment doom_defend_the_line already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,624][795538] Environment doom_health_gathering already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,625][795538] Environment doom_health_gathering_supreme already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,625][795538] Environment doom_battle already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,626][795538] Environment doom_battle2 already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,626][795538] Environment doom_duel_bots already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,627][795538] Environment doom_deathmatch_bots already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,628][795538] Environment doom_duel already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,628][795538] Environment doom_deathmatch_full already registered, overwriting...\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,629][795538] Environment doom_benchmark already registered, overwriting...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 08:05:26,629][795538] register_encoder_factory: <function make_vizdoom_encoder at 0x7efc41caae60>\u001b[0m\n",
+ "\u001b[33m[2023-02-24 08:05:26,640][795538] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json\u001b[0m\n",
+ "\u001b[36m[2023-02-24 08:05:26,640][795538] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line\u001b[0m\n",
+ "\u001b[36m[2023-02-24 08:05:26,645][795538] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 08:05:26,646][795538] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 08:05:26,646][795538] Weights and Biases integration disabled\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 08:05:26,649][795538] Environment var CUDA_VISIBLE_DEVICES is 1\u001b[0m\n",
+ "Traceback (most recent call last):\n",
+ " File \"<string>\", line 1, in <module>\n",
+ " File \"/home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/spawn.py\", line 116, in spawn_main\n",
+ " exitcode = _main(fd, parent_sentinel)\n",
+ " File \"/home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/spawn.py\", line 126, in _main\n",
+ " self = reduction.pickle.load(from_parent)\n",
+ "AttributeError: Can't get attribute 'make_vizdoom_encoder' on <module '__main__' (built-in)>\n"
+ ]
+ },
+ {
+ "ename": "KeyboardInterrupt",
+ "evalue": "",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[5], line 9\u001b[0m\n\u001b[1;32m 6\u001b[0m env \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mdoom_health_gathering_supreme\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 7\u001b[0m cfg \u001b[39m=\u001b[39m parse_vizdoom_cfg(argv\u001b[39m=\u001b[39m[\u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m--env=\u001b[39m\u001b[39m{\u001b[39;00menv\u001b[39m}\u001b[39;00m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39m--num_workers=8\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39m--num_envs_per_worker=4\u001b[39m\u001b[39m\"\u001b[39m, \u001b[39m\"\u001b[39m\u001b[39m--train_for_env_steps=40000000\u001b[39m\u001b[39m\"\u001b[39m])\n\u001b[0;32m----> 9\u001b[0m status \u001b[39m=\u001b[39m run_rl(cfg)\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/sample_factory/train.py:37\u001b[0m, in \u001b[0;36mrun_rl\u001b[0;34m(cfg)\u001b[0m\n\u001b[1;32m 32\u001b[0m cfg, runner \u001b[39m=\u001b[39m make_runner(cfg)\n\u001b[1;32m 34\u001b[0m \u001b[39m# here we can register additional message or summary handlers\u001b[39;00m\n\u001b[1;32m 35\u001b[0m \u001b[39m# see sf_examples/dmlab/train_dmlab.py for example\u001b[39;00m\n\u001b[0;32m---> 37\u001b[0m status \u001b[39m=\u001b[39m runner\u001b[39m.\u001b[39;49minit()\n\u001b[1;32m 38\u001b[0m \u001b[39mif\u001b[39;00m status \u001b[39m==\u001b[39m ExperimentStatus\u001b[39m.\u001b[39mSUCCESS:\n\u001b[1;32m 39\u001b[0m status \u001b[39m=\u001b[39m runner\u001b[39m.\u001b[39mrun()\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/sample_factory/algo/runners/runner_parallel.py:21\u001b[0m, in \u001b[0;36mParallelRunner.init\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39minit\u001b[39m(\u001b[39mself\u001b[39m) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m StatusCode:\n\u001b[0;32m---> 21\u001b[0m status \u001b[39m=\u001b[39m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49minit()\n\u001b[1;32m 22\u001b[0m \u001b[39mif\u001b[39;00m status \u001b[39m!=\u001b[39m ExperimentStatus\u001b[39m.\u001b[39mSUCCESS:\n\u001b[1;32m 23\u001b[0m \u001b[39mreturn\u001b[39;00m status\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/sample_factory/algo/runners/runner.py:542\u001b[0m, in \u001b[0;36mRunner.init\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 540\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39minit\u001b[39m(\u001b[39mself\u001b[39m) \u001b[39m-\u001b[39m\u001b[39m>\u001b[39m StatusCode:\n\u001b[1;32m 541\u001b[0m set_global_cuda_envvars(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcfg)\n\u001b[0;32m--> 542\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39menv_info \u001b[39m=\u001b[39m obtain_env_info_in_a_separate_process(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mcfg)\n\u001b[1;32m 544\u001b[0m \u001b[39mfor\u001b[39;00m policy_id \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mcfg\u001b[39m.\u001b[39mnum_policies):\n\u001b[1;32m 545\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mreward_shaping[policy_id] \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39menv_info\u001b[39m.\u001b[39mreward_shaping_scheme\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/sample_factory/algo/utils/env_info.py:127\u001b[0m, in \u001b[0;36mobtain_env_info_in_a_separate_process\u001b[0;34m(cfg)\u001b[0m\n\u001b[1;32m 124\u001b[0m p \u001b[39m=\u001b[39m ctx\u001b[39m.\u001b[39mProcess(target\u001b[39m=\u001b[39mspawn_tmp_env_and_get_info, args\u001b[39m=\u001b[39m(sf_context, q, cfg))\n\u001b[1;32m 125\u001b[0m p\u001b[39m.\u001b[39mstart()\n\u001b[0;32m--> 127\u001b[0m env_info \u001b[39m=\u001b[39m q\u001b[39m.\u001b[39;49mget()\n\u001b[1;32m 128\u001b[0m p\u001b[39m.\u001b[39mjoin()\n\u001b[1;32m 130\u001b[0m \u001b[39mif\u001b[39;00m cfg\u001b[39m.\u001b[39muse_env_info_cache:\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/queues.py:103\u001b[0m, in \u001b[0;36mQueue.get\u001b[0;34m(self, block, timeout)\u001b[0m\n\u001b[1;32m 101\u001b[0m \u001b[39mif\u001b[39;00m block \u001b[39mand\u001b[39;00m timeout \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m 102\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_rlock:\n\u001b[0;32m--> 103\u001b[0m res \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_recv_bytes()\n\u001b[1;32m 104\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_sem\u001b[39m.\u001b[39mrelease()\n\u001b[1;32m 105\u001b[0m \u001b[39melse\u001b[39;00m:\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/connection.py:216\u001b[0m, in \u001b[0;36m_ConnectionBase.recv_bytes\u001b[0;34m(self, maxlength)\u001b[0m\n\u001b[1;32m 214\u001b[0m \u001b[39mif\u001b[39;00m maxlength \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m \u001b[39mand\u001b[39;00m maxlength \u001b[39m<\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[1;32m 215\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mnegative maxlength\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m--> 216\u001b[0m buf \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_recv_bytes(maxlength)\n\u001b[1;32m 217\u001b[0m \u001b[39mif\u001b[39;00m buf \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m 218\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_bad_message_length()\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/connection.py:414\u001b[0m, in \u001b[0;36mConnection._recv_bytes\u001b[0;34m(self, maxsize)\u001b[0m\n\u001b[1;32m 413\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_recv_bytes\u001b[39m(\u001b[39mself\u001b[39m, maxsize\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m):\n\u001b[0;32m--> 414\u001b[0m buf \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_recv(\u001b[39m4\u001b[39;49m)\n\u001b[1;32m 415\u001b[0m size, \u001b[39m=\u001b[39m struct\u001b[39m.\u001b[39munpack(\u001b[39m\"\u001b[39m\u001b[39m!i\u001b[39m\u001b[39m\"\u001b[39m, buf\u001b[39m.\u001b[39mgetvalue())\n\u001b[1;32m 416\u001b[0m \u001b[39mif\u001b[39;00m size \u001b[39m==\u001b[39m \u001b[39m-\u001b[39m\u001b[39m1\u001b[39m:\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/multiprocessing/connection.py:379\u001b[0m, in \u001b[0;36mConnection._recv\u001b[0;34m(self, size, read)\u001b[0m\n\u001b[1;32m 377\u001b[0m remaining \u001b[39m=\u001b[39m size\n\u001b[1;32m 378\u001b[0m \u001b[39mwhile\u001b[39;00m remaining \u001b[39m>\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[0;32m--> 379\u001b[0m chunk \u001b[39m=\u001b[39m read(handle, remaining)\n\u001b[1;32m 380\u001b[0m n \u001b[39m=\u001b[39m \u001b[39mlen\u001b[39m(chunk)\n\u001b[1;32m 381\u001b[0m \u001b[39mif\u001b[39;00m n \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m:\n",
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+ ]
+ }
+ ],
"source": [
"## Start the training, this should take around 15 minutes\n",
"register_vizdoom_components()\n",
@@ -358,7 +601,7 @@
"# The scenario we train on today is health gathering\n",
"# other scenarios include \"doom_basic\", \"doom_two_colors_easy\", \"doom_dm\", \"doom_dwango5\", \"doom_my_way_home\", \"doom_deadly_corridor\", \"doom_defend_the_center\", \"doom_defend_the_line\"\n",
"env = \"doom_health_gathering_supreme\"\n",
- "cfg = parse_vizdoom_cfg(argv=[f\"--env={env}\", \"--num_workers=8\", \"--num_envs_per_worker=4\", \"--train_for_env_steps=4000000\"])\n",
+ "cfg = parse_vizdoom_cfg(argv=[f\"--env={env}\", \"--num_workers=8\", \"--num_envs_per_worker=4\", \"--train_for_env_steps=40000000\"])\n",
"\n",
"status = run_rl(cfg)"
]
@@ -416,12 +659,12 @@
},
{
"cell_type": "markdown",
- "source": [
- "The agent has learned something, but its performance could be better. We would clearly need to train for longer. But let's upload this model to the Hub."
- ],
"metadata": {
"id": "2A4pf_1VwPqR"
- }
+ },
+ "source": [
+ "The agent has learned something, but its performance could be better. We would clearly need to train for longer. But let's upload this model to the Hub."
+ ]
},
{
"cell_type": "markdown",
@@ -464,11 +707,28 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 6,
"metadata": {
"id": "GoQm_jYSOts0"
},
- "outputs": [],
+ "outputs": [
+ {
+ "ename": "ImportError",
+ "evalue": "The `notebook_login` function can only be used in a notebook (Jupyter or Colab) and you need the `ipywidgets` module: `pip install ipywidgets`.",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/huggingface_hub/_login.py:188\u001b[0m, in \u001b[0;36mnotebook_login\u001b[0;34m()\u001b[0m\n\u001b[1;32m 187\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m--> 188\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mipywidgets\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mwidgets\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mwidgets\u001b[39;00m \u001b[39m# type: ignore\u001b[39;00m\n\u001b[1;32m 189\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mIPython\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mdisplay\u001b[39;00m \u001b[39mimport\u001b[39;00m clear_output, display \u001b[39m# type: ignore\u001b[39;00m\n",
+ "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'ipywidgets'",
+ "\nDuring handling of the above exception, another exception occurred:\n",
+ "\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[6], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mhuggingface_hub\u001b[39;00m \u001b[39mimport\u001b[39;00m notebook_login\n\u001b[0;32m----> 2\u001b[0m notebook_login()\n\u001b[1;32m 3\u001b[0m get_ipython()\u001b[39m.\u001b[39msystem(\u001b[39m'\u001b[39m\u001b[39mgit config --global credential.helper store\u001b[39m\u001b[39m'\u001b[39m)\n",
+ "File \u001b[0;32m~/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/huggingface_hub/_login.py:191\u001b[0m, in \u001b[0;36mnotebook_login\u001b[0;34m()\u001b[0m\n\u001b[1;32m 189\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mIPython\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mdisplay\u001b[39;00m \u001b[39mimport\u001b[39;00m clear_output, display \u001b[39m# type: ignore\u001b[39;00m\n\u001b[1;32m 190\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mImportError\u001b[39;00m:\n\u001b[0;32m--> 191\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mImportError\u001b[39;00m(\n\u001b[1;32m 192\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mThe `notebook_login` function can only be used in a notebook (Jupyter or\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 193\u001b[0m \u001b[39m\"\u001b[39m\u001b[39m Colab) and you need the `ipywidgets` module: `pip install ipywidgets`.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 194\u001b[0m )\n\u001b[1;32m 196\u001b[0m box_layout \u001b[39m=\u001b[39m widgets\u001b[39m.\u001b[39mLayout(\n\u001b[1;32m 197\u001b[0m display\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mflex\u001b[39m\u001b[39m\"\u001b[39m, flex_flow\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mcolumn\u001b[39m\u001b[39m\"\u001b[39m, align_items\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mcenter\u001b[39m\u001b[39m\"\u001b[39m, width\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m50\u001b[39m\u001b[39m%\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m 198\u001b[0m )\n\u001b[1;32m 200\u001b[0m token_widget \u001b[39m=\u001b[39m widgets\u001b[39m.\u001b[39mPassword(description\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mToken:\u001b[39m\u001b[39m\"\u001b[39m)\n",
+ "\u001b[0;31mImportError\u001b[0m: The `notebook_login` function can only be used in a notebook (Jupyter or Colab) and you need the `ipywidgets` module: `pip install ipywidgets`."
+ ]
+ }
+ ],
"source": [
"from huggingface_hub import notebook_login\n",
"notebook_login()\n",
@@ -477,15 +737,231 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 8,
"metadata": {
"id": "sEawW_i0OvJV"
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[33m[2023-02-24 07:58:39,896][784615] Loading existing experiment configuration from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,896][784615] Overriding arg 'num_workers' with value 1 passed from command line\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,897][784615] Adding new argument 'no_render'=True that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,897][784615] Adding new argument 'save_video'=True that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,898][784615] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,898][784615] Adding new argument 'video_name'=None that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,899][784615] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,899][784615] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,900][784615] Adding new argument 'push_to_hub'=True that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,900][784615] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,900][784615] Adding new argument 'policy_index'=0 that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,901][784615] Adding new argument 'eval_deterministic'=False that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,901][784615] Adding new argument 'train_script'=None that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,902][784615] Adding new argument 'enjoy_script'=None that is not in the saved config file!\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,902][784615] Using frameskip 1 and render_action_repeat=4 for evaluation\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,911][784615] RunningMeanStd input shape: (3, 72, 128)\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,912][784615] RunningMeanStd input shape: (1,)\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,919][784615] ConvEncoder: input_channels=3\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,943][784615] Conv encoder output size: 512\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:39,944][784615] Policy head output size: 512\u001b[0m\n",
+ "\u001b[33m[2023-02-24 07:58:39,980][784615] Loading state from checkpoint /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000268_1097728.pth...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,400][784615] Num frames 100...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,470][784615] Num frames 200...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,530][784615] Num frames 300...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,596][784615] Num frames 400...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:40,684][784615] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:40,685][784615] Avg episode reward: 5.480, avg true_objective: 4.480\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,719][784615] Num frames 500...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,787][784615] Num frames 600...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,850][784615] Num frames 700...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:40,918][784615] Num frames 800...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,005][784615] Num frames 900...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:41,078][784615] Avg episode rewards: #0: 6.640, true rewards: #0: 4.640\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:41,079][784615] Avg episode reward: 6.640, avg true_objective: 4.640\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,129][784615] Num frames 1000...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,202][784615] Num frames 1100...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,276][784615] Num frames 1200...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,360][784615] Num frames 1300...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,429][784615] Num frames 1400...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,493][784615] Num frames 1500...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,554][784615] Num frames 1600...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:41,667][784615] Avg episode rewards: #0: 8.653, true rewards: #0: 5.653\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:41,668][784615] Avg episode reward: 8.653, avg true_objective: 5.653\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,673][784615] Num frames 1700...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,734][784615] Num frames 1800...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,791][784615] Num frames 1900...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,848][784615] Num frames 2000...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,905][784615] Num frames 2100...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:41,961][784615] Num frames 2200...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,055][784615] Avg episode rewards: #0: 8.680, true rewards: #0: 5.680\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,056][784615] Avg episode reward: 8.680, avg true_objective: 5.680\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,077][784615] Num frames 2300...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,141][784615] Num frames 2400...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,203][784615] Num frames 2500...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,260][784615] Num frames 2600...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,346][784615] Avg episode rewards: #0: 7.712, true rewards: #0: 5.312\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,348][784615] Avg episode reward: 7.712, avg true_objective: 5.312\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,385][784615] Num frames 2700...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,449][784615] Num frames 2800...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,506][784615] Num frames 2900...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,563][784615] Num frames 3000...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,621][784615] Num frames 3100...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,688][784615] Num frames 3200...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,788][784615] Avg episode rewards: #0: 7.940, true rewards: #0: 5.440\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:42,788][784615] Avg episode reward: 7.940, avg true_objective: 5.440\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,817][784615] Num frames 3300...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,890][784615] Num frames 3400...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:42,964][784615] Num frames 3500...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,040][784615] Num frames 3600...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,128][784615] Avg episode rewards: #0: 7.354, true rewards: #0: 5.211\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,130][784615] Avg episode reward: 7.354, avg true_objective: 5.211\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,174][784615] Num frames 3700...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,248][784615] Num frames 3800...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,316][784615] Num frames 3900...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,383][784615] Num frames 4000...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,475][784615] Avg episode rewards: #0: 7.205, true rewards: #0: 5.080\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,476][784615] Avg episode reward: 7.205, avg true_objective: 5.080\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,498][784615] Num frames 4100...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,556][784615] Num frames 4200...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,614][784615] Num frames 4300...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,670][784615] Num frames 4400...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,727][784615] Num frames 4500...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,790][784615] Num frames 4600...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,891][784615] Avg episode rewards: #0: 7.413, true rewards: #0: 5.191\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:43,891][784615] Avg episode reward: 7.413, avg true_objective: 5.191\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,912][784615] Num frames 4700...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:43,982][784615] Num frames 4800...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:44,049][784615] Num frames 4900...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:44,117][784615] Num frames 5000...\u001b[0m\n",
+ "\u001b[36m[2023-02-24 07:58:44,184][784615] Num frames 5100...\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:44,250][784615] Avg episode rewards: #0: 7.220, true rewards: #0: 5.120\u001b[0m\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:58:44,250][784615] Avg episode reward: 7.220, avg true_objective: 5.120\u001b[0m\n",
+ "ffmpeg version 4.3 Copyright (c) 2000-2020 the FFmpeg developers\n",
+ " built with gcc 7.3.0 (crosstool-NG 1.23.0.449-a04d0)\n",
+ " configuration: --prefix=/opt/conda/conda-bld/ffmpeg_1597178665428/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeh --cc=/opt/conda/conda-bld/ffmpeg_1597178665428/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc --disable-doc --disable-openssl --enable-avresample --enable-gnutls --enable-hardcoded-tables --enable-libfreetype --enable-libopenh264 --enable-pic --enable-pthreads --enable-shared --disable-static --enable-version3 --enable-zlib --enable-libmp3lame\n",
+ " libavutil 56. 51.100 / 56. 51.100\n",
+ " libavcodec 58. 91.100 / 58. 91.100\n",
+ " libavformat 58. 45.100 / 58. 45.100\n",
+ " libavdevice 58. 10.100 / 58. 10.100\n",
+ " libavfilter 7. 85.100 / 7. 85.100\n",
+ " libavresample 4. 0. 0 / 4. 0. 0\n",
+ " libswscale 5. 7.100 / 5. 7.100\n",
+ " libswresample 3. 7.100 / 3. 7.100\n",
+ "Input #0, mov,mp4,m4a,3gp,3g2,mj2, from '/tmp/sf2_chqma/replay.mp4':\n",
+ " Metadata:\n",
+ " major_brand : isom\n",
+ " minor_version : 512\n",
+ " compatible_brands: isomiso2mp41\n",
+ " encoder : Lavf59.27.100\n",
+ " Duration: 00:02:26.57, start: 0.000000, bitrate: 1521 kb/s\n",
+ " Stream #0:0(und): Video: mpeg4 (Simple Profile) (mp4v / 0x7634706D), yuv420p, 240x180 [SAR 1:1 DAR 4:3], 1519 kb/s, 35 fps, 35 tbr, 17920 tbn, 35 tbc (default)\n",
+ " Metadata:\n",
+ " handler_name : VideoHandler\n",
+ "Unknown encoder 'libx264'\n",
+ "\u001b[36m[2023-02-24 07:58:46,584][784615] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!\u001b[0m\n",
+ "/home/chqma/miniconda3/envs/deep-rl-class/lib/python3.10/site-packages/huggingface_hub/_commit_api.py:493: UserWarning: About to commit an empty file: 'git.diff'. Are you sure this is intended?\n",
+ " warnings.warn(\n",
+ "\n",
+ "\u001b[A\n",
+ "\n",
+ "best_000000254_1040384_reward_6.010.pth: 0%| | 0.00/34.9M [00:00<?, ?B/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 0%| | 123k/34.9M [00:00<01:35, 364kB/s] \n",
+ "best_000000254_1040384_reward_6.010.pth: 1%| | 279k/34.9M [00:00<01:00, 576kB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 4%|β | 1.42M/34.9M [00:00<00:10, 3.29MB/s]\n",
+ "events.out.tfevents.1677225358.pop-os: 100%|ββββββββββ| 72.8k/72.8k [00:01<00:00, 65.3kB/s]s]\n",
+ "\n",
+ "\n",
+ "\u001b[A\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 11%|β | 3.80M/34.9M [00:01<00:11, 2.67MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 13%|ββ | 4.55M/34.9M [00:02<00:11, 2.55MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 15%|ββ | 5.37M/34.9M [00:02<00:13, 2.27MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 21%|ββ | 7.19M/34.9M [00:03<00:11, 2.47MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 23%|βββ | 7.95M/34.9M [00:03<00:11, 2.41MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 27%|βββ | 9.45M/34.9M [00:04<00:10, 2.32MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 29%|βββ | 10.2M/34.9M [00:04<00:10, 2.30MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 34%|ββββ | 11.8M/34.9M [00:05<00:09, 2.33MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 36%|ββββ | 12.6M/34.9M [00:05<00:09, 2.35MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 38%|ββββ | 13.4M/34.9M [00:05<00:09, 2.36MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 41%|ββββ | 14.2M/34.9M [00:06<00:08, 2.34MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 43%|βββββ | 14.9M/34.9M [00:06<00:08, 2.33MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 47%|βββββ | 16.4M/34.9M [00:07<00:08, 2.28MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 49%|βββββ | 17.2M/34.9M [00:07<00:07, 2.29MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 51%|ββββββ | 17.9M/34.9M [00:07<00:07, 2.27MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 53%|ββββββ | 18.7M/34.9M [00:08<00:07, 2.27MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 58%|ββββββ | 20.2M/34.9M [00:08<00:06, 2.24MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 60%|ββββββ | 20.9M/34.9M [00:09<00:06, 2.22MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 62%|βββββββ | 21.8M/34.9M [00:09<00:06, 2.20MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 64%|βββββββ | 22.5M/34.9M [00:10<00:05, 2.09MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 67%|βββββββ | 23.3M/34.9M [00:10<00:05, 2.04MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 69%|βββββββ | 24.0M/34.9M [00:10<00:05, 1.98MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 71%|βββββββ | 24.8M/34.9M [00:11<00:05, 1.94MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 73%|ββββββββ | 25.5M/34.9M [00:11<00:04, 1.90MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 75%|ββββββββ | 26.3M/34.9M [00:12<00:04, 1.84MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 77%|ββββββββ | 27.0M/34.9M [00:12<00:04, 1.81MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 80%|ββββββββ | 27.8M/34.9M [00:12<00:03, 1.79MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 82%|βββββββββ | 28.5M/34.9M [00:13<00:03, 1.76MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 84%|βββββββββ | 29.3M/34.9M [00:13<00:03, 1.75MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 86%|βββββββββ | 30.0M/34.9M [00:14<00:02, 1.74MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 88%|βββββββββ | 30.8M/34.9M [00:14<00:02, 1.73MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 90%|βββββββββ | 31.6M/34.9M [00:15<00:01, 1.72MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 93%|ββββββββββ| 32.3M/34.9M [00:15<00:01, 1.71MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 95%|ββββββββββ| 33.1M/34.9M [00:16<00:01, 1.70MB/s]\n",
+ "best_000000254_1040384_reward_6.010.pth: 97%|ββββββββββ| 33.8M/34.9M [00:16<00:00, 1.70MB/s]\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 99%|ββββββββββ| 34.6M/34.9M [00:16<00:00, 1.70MB/s]\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "best_000000254_1040384_reward_6.010.pth: 100%|ββββββββββ| 34.9M/34.9M [00:18<00:00, 1.89MB/s]\n",
+ "\n",
+ "\n",
+ "\u001b[A\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "\u001b[A\n",
+ "checkpoint_000000268_1097728.pth: 100%|ββββββββββ| 34.9M/34.9M [00:23<00:00, 1.49MB/s]\n",
+ "\n",
+ "\n",
+ "Upload 3 LFS files: 100%|ββββββββββ| 3/3 [00:23<00:00, 7.81s/it]\n",
+ "\u001b[37m\u001b[1m[2023-02-24 07:59:12,402][784615] The model has been pushed to https://huggingface.co/chqmatteo/rl_course_vizdoom_health_gathering_supreme\u001b[0m\n"
+ ]
+ }
+ ],
"source": [
"from sample_factory.enjoy import enjoy\n",
"\n",
- "hf_username = \"ThomasSimonini\" # insert your HuggingFace username here\n",
+ "hf_username = \"chqmatteo\" # insert your HuggingFace username here\n",
"\n",
"cfg = parse_vizdoom_cfg(argv=[f\"--env={env}\", \"--num_workers=1\", \"--save_video\", \"--no_render\", \"--max_num_episodes=10\", \"--max_num_frames=100000\", \"--push_to_hub\", f\"--hf_repository={hf_username}/rl_course_vizdoom_health_gathering_supreme\"], evaluation=True)\n",
"status = enjoy(cfg)"
@@ -493,14 +969,14 @@
},
{
"cell_type": "markdown",
+ "metadata": {
+ "id": "9PzeXx-qxVvw"
+ },
"source": [
"## Let's load another model\n",
"\n",
"\n"
- ],
- "metadata": {
- "id": "9PzeXx-qxVvw"
- }
+ ]
},
{
"cell_type": "markdown",
@@ -566,16 +1042,16 @@
},
{
"cell_type": "markdown",
+ "metadata": {
+ "id": "ie5YWC3NyKO8"
+ },
"source": [
"## Some additional challenges π: Doom Deathmatch\n",
"\n",
"Training an agent to play a Doom deathmatch **takes many hours on a more beefy machine than is available in Colab**. \n",
"\n",
"Fortunately, we have have **already trained an agent in this scenario and it is available in the π€ Hub!** Letβs download the model and visualize the agentβs performance."
- ],
- "metadata": {
- "id": "ie5YWC3NyKO8"
- }
+ ]
},
{
"cell_type": "code",
@@ -591,12 +1067,12 @@
},
{
"cell_type": "markdown",
- "source": [
- "Given the agent plays for a long time the video generation can take **10 minutes**."
- ],
"metadata": {
"id": "7AX_LwxR2FQ0"
- }
+ },
+ "source": [
+ "Given the agent plays for a long time the video generation can take **10 minutes**."
+ ]
},
{
"cell_type": "code",
@@ -623,17 +1099,20 @@
},
{
"cell_type": "markdown",
+ "metadata": {
+ "id": "N6mEC-4zyihx"
+ },
"source": [
"\n",
"You **can try to train your agent in this environment** using the code above, but not on colab.\n",
"**Good luck π€**"
- ],
- "metadata": {
- "id": "N6mEC-4zyihx"
- }
+ ]
},
{
"cell_type": "markdown",
+ "metadata": {
+ "id": "YnDAngN6zeeI"
+ },
"source": [
"If you prefer an easier scenario, **why not try training in another ViZDoom scenario such as `doom_deadly_corridor` or `doom_defend_the_center`.**\n",
"\n",
@@ -645,34 +1124,46 @@
"This concludes the last unit. But we are not finished yet! π€ The following **bonus section include some of the most interesting, advanced and cutting edge work in Deep Reinforcement Learning**.\n",
"\n",
"## Keep learning, stay awesome π€"
- ],
- "metadata": {
- "id": "YnDAngN6zeeI"
- }
+ ]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
- "provenance": [],
"collapsed_sections": [
"PU4FVzaoM6fC",
"nB68Eb9UgC94",
"ez5UhUtYcWXF",
"sgRy6wnrgnij"
],
+ "include_colab_link": true,
"private_outputs": true,
- "include_colab_link": true
+ "provenance": []
},
"gpuClass": "standard",
"kernelspec": {
- "display_name": "Python 3",
+ "display_name": "deep-rl-class",
+ "language": "python",
"name": "python3"
},
"language_info": {
- "name": "python"
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.9"
+ },
+ "vscode": {
+ "interpreter": {
+ "hash": "da4ecdf31b09708386948f91c5b725d7113689587e88c28098219103c44ec57b"
+ }
}
},
"nbformat": 4,
"nbformat_minor": 0
-}
\ No newline at end of file
+}
|