Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677225979.pop-os

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da32336adbc8b063c28050a14266b1d5270cfaf6e167b384f8a25317ea9d801e
+size 36926

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 5.12 +/- 1.18
+      value: 8.70 +/- 5.10
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000000389_1593344_reward_13.989.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dc1f8b4841de7b74b7b7e54da8194d1454e88edf7c65acff4b373abfbb15ca
+size 34928806

checkpoint_p0/checkpoint_000000403_1650688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81321e38ba47c35d8fb2fcc7d27b5979c7e799aaa693a854fbd7a5a77202564
+size 34929220

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
+  "train_for_env_steps": 40000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

git.diff

@@ -0,0 +1,759 @@
+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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\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%|▍         | 1.42M/34.9M [00:00<00:10, 3.29MB/s]\n",
++            "events.out.tfevents.1677225358.pop-os: 100%|██████████| 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%|█         | 3.80M/34.9M [00:01<00:11, 2.67MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  13%|█▎        | 4.55M/34.9M [00:02<00:11, 2.55MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  15%|█▌        | 5.37M/34.9M [00:02<00:13, 2.27MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  21%|██        | 7.19M/34.9M [00:03<00:11, 2.47MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  23%|██▎       | 7.95M/34.9M [00:03<00:11, 2.41MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  27%|██▋       | 9.45M/34.9M [00:04<00:10, 2.32MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  29%|██▉       | 10.2M/34.9M [00:04<00:10, 2.30MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  34%|███▎      | 11.8M/34.9M [00:05<00:09, 2.33MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  36%|███▌      | 12.6M/34.9M [00:05<00:09, 2.35MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  38%|███▊      | 13.4M/34.9M [00:05<00:09, 2.36MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  41%|████      | 14.2M/34.9M [00:06<00:08, 2.34MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  43%|████▎     | 14.9M/34.9M [00:06<00:08, 2.33MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  47%|████▋     | 16.4M/34.9M [00:07<00:08, 2.28MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  49%|████▉     | 17.2M/34.9M [00:07<00:07, 2.29MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  51%|█████▏    | 17.9M/34.9M [00:07<00:07, 2.27MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  53%|█████▎    | 18.7M/34.9M [00:08<00:07, 2.27MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  58%|█████▊    | 20.2M/34.9M [00:08<00:06, 2.24MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  60%|█████▉    | 20.9M/34.9M [00:09<00:06, 2.22MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  62%|██████▏   | 21.8M/34.9M [00:09<00:06, 2.20MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  64%|██████▍   | 22.5M/34.9M [00:10<00:05, 2.09MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  67%|██████▋   | 23.3M/34.9M [00:10<00:05, 2.04MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  69%|██████▉   | 24.0M/34.9M [00:10<00:05, 1.98MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  71%|███████   | 24.8M/34.9M [00:11<00:05, 1.94MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  73%|███████▎  | 25.5M/34.9M [00:11<00:04, 1.90MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  75%|███████▌  | 26.3M/34.9M [00:12<00:04, 1.84MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  77%|███████▋  | 27.0M/34.9M [00:12<00:04, 1.81MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  80%|███████▉  | 27.8M/34.9M [00:12<00:03, 1.79MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  82%|████████▏ | 28.5M/34.9M [00:13<00:03, 1.76MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  84%|████████▍ | 29.3M/34.9M [00:13<00:03, 1.75MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  86%|████████▌ | 30.0M/34.9M [00:14<00:02, 1.74MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  88%|████████▊ | 30.8M/34.9M [00:14<00:02, 1.73MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  90%|█████████ | 31.6M/34.9M [00:15<00:01, 1.72MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  93%|█████████▎| 32.3M/34.9M [00:15<00:01, 1.71MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  95%|█████████▍| 33.1M/34.9M [00:16<00:01, 1.70MB/s]\n",
++            "best_000000254_1040384_reward_6.010.pth:  97%|█████████▋| 33.8M/34.9M [00:16<00:00, 1.70MB/s]\n",
++            "\u001b[A\n",
++            "best_000000254_1040384_reward_6.010.pth:  99%|█████████▉| 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%|██████████| 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%|██████████| 34.9M/34.9M [00:23<00:00, 1.49MB/s]\n",
++            "\n",
++            "\n",
++            "Upload 3 LFS files: 100%|██████████| 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 🏆: 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 🤗 Hub!** Let’s download the model and visualize the agent’s 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 🤞**"
+-      ],
+-      "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! 🤗 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 🤗"
+-      ],
+-      "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
+-}
+
++}

sf_log.txt

@@ -426,3 +426,408 @@ main_loop: 82.2510
 [2023-02-24 07:58:44,250][784615] Avg episode rewards: #0: 7.220, true rewards: #0: 5.120
 [2023-02-24 07:58:44,250][784615] Avg episode reward: 7.220, avg true_objective: 5.120
 [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!
+[2023-02-24 07:59:12,402][784615] The model has been pushed to https://huggingface.co/chqmatteo/rl_course_vizdoom_health_gathering_supreme
+[2023-02-24 08:02:31,136][784615] Environment doom_basic already registered, overwriting...
+[2023-02-24 08:02:31,137][784615] Environment doom_two_colors_easy already registered, overwriting...
+[2023-02-24 08:02:31,137][784615] Environment doom_two_colors_hard already registered, overwriting...
+[2023-02-24 08:02:31,138][784615] Environment doom_dm already registered, overwriting...
+[2023-02-24 08:02:31,138][784615] Environment doom_dwango5 already registered, overwriting...
+[2023-02-24 08:02:31,139][784615] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-02-24 08:02:31,139][784615] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-02-24 08:02:31,139][784615] Environment doom_my_way_home already registered, overwriting...
+[2023-02-24 08:02:31,140][784615] Environment doom_deadly_corridor already registered, overwriting...
+[2023-02-24 08:02:31,140][784615] Environment doom_defend_the_center already registered, overwriting...
+[2023-02-24 08:02:31,140][784615] Environment doom_defend_the_line already registered, overwriting...
+[2023-02-24 08:02:31,141][784615] Environment doom_health_gathering already registered, overwriting...
+[2023-02-24 08:02:31,141][784615] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-02-24 08:02:31,142][784615] Environment doom_battle already registered, overwriting...
+[2023-02-24 08:02:31,142][784615] Environment doom_battle2 already registered, overwriting...
+[2023-02-24 08:02:31,142][784615] Environment doom_duel_bots already registered, overwriting...
+[2023-02-24 08:02:31,142][784615] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-02-24 08:02:31,143][784615] Environment doom_duel already registered, overwriting...
+[2023-02-24 08:02:31,143][784615] Environment doom_deathmatch_full already registered, overwriting...
+[2023-02-24 08:02:31,143][784615] Environment doom_benchmark already registered, overwriting...
+[2023-02-24 08:02:31,144][784615] register_encoder_factory: <function make_vizdoom_encoder at 0x7f9fbe7ae680>
+[2023-02-24 08:02:31,153][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
+[2023-02-24 08:02:31,154][784615] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line
+[2023-02-24 08:02:31,157][784615] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
+[2023-02-24 08:02:31,158][784615] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
+[2023-02-24 08:02:31,158][784615] Weights and Biases integration disabled
+[2023-02-24 08:02:31,159][784615] Environment var CUDA_VISIBLE_DEVICES is 1
+[2023-02-24 08:03:09,472][784615] Environment doom_basic already registered, overwriting...
+[2023-02-24 08:03:09,474][784615] Environment doom_two_colors_easy already registered, overwriting...
+[2023-02-24 08:03:09,475][784615] Environment doom_two_colors_hard already registered, overwriting...
+[2023-02-24 08:03:09,476][784615] Environment doom_dm already registered, overwriting...
+[2023-02-24 08:03:09,477][784615] Environment doom_dwango5 already registered, overwriting...
+[2023-02-24 08:03:09,477][784615] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-02-24 08:03:09,478][784615] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-02-24 08:03:09,478][784615] Environment doom_my_way_home already registered, overwriting...
+[2023-02-24 08:03:09,479][784615] Environment doom_deadly_corridor already registered, overwriting...
+[2023-02-24 08:03:09,479][784615] Environment doom_defend_the_center already registered, overwriting...
+[2023-02-24 08:03:09,480][784615] Environment doom_defend_the_line already registered, overwriting...
+[2023-02-24 08:03:09,480][784615] Environment doom_health_gathering already registered, overwriting...
+[2023-02-24 08:03:09,481][784615] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-02-24 08:03:09,481][784615] Environment doom_battle already registered, overwriting...
+[2023-02-24 08:03:09,482][784615] Environment doom_battle2 already registered, overwriting...
+[2023-02-24 08:03:09,482][784615] Environment doom_duel_bots already registered, overwriting...
+[2023-02-24 08:03:09,483][784615] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-02-24 08:03:09,483][784615] Environment doom_duel already registered, overwriting...
+[2023-02-24 08:03:09,483][784615] Environment doom_deathmatch_full already registered, overwriting...
+[2023-02-24 08:03:09,484][784615] Environment doom_benchmark already registered, overwriting...
+[2023-02-24 08:03:09,484][784615] register_encoder_factory: <function make_vizdoom_encoder at 0x7f9fbe7ae680>
+[2023-02-24 08:03:09,494][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
+[2023-02-24 08:03:09,495][784615] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line
+[2023-02-24 08:03:09,498][784615] Experiment dir /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment already exists!
+[2023-02-24 08:03:09,499][784615] Resuming existing experiment from /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment...
+[2023-02-24 08:03:09,499][784615] Weights and Biases integration disabled
+[2023-02-24 08:03:09,500][784615] Environment var CUDA_VISIBLE_DEVICES is 1
+[2023-02-24 08:06:20,559][795538] Saving configuration to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json...
+[2023-02-24 08:06:20,725][795538] Rollout worker 0 uses device cpu
+[2023-02-24 08:06:20,726][795538] Rollout worker 1 uses device cpu
+[2023-02-24 08:06:20,726][795538] Rollout worker 2 uses device cpu
+[2023-02-24 08:06:20,727][795538] Rollout worker 3 uses device cpu
+[2023-02-24 08:06:20,727][795538] Rollout worker 4 uses device cpu
+[2023-02-24 08:06:20,727][795538] Rollout worker 5 uses device cpu
+[2023-02-24 08:06:20,728][795538] Rollout worker 6 uses device cpu
+[2023-02-24 08:06:20,728][795538] Rollout worker 7 uses device cpu
+[2023-02-24 08:06:20,767][795538] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:06:20,768][795538] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-24 08:06:20,819][795538] Starting all processes...
+[2023-02-24 08:06:20,820][795538] Starting process learner_proc0
+[2023-02-24 08:06:20,869][795538] Starting all processes...
+[2023-02-24 08:06:20,872][795538] Starting process inference_proc0-0
+[2023-02-24 08:06:20,873][795538] Starting process rollout_proc0
+[2023-02-24 08:06:20,873][795538] Starting process rollout_proc1
+[2023-02-24 08:06:20,873][795538] Starting process rollout_proc2
+[2023-02-24 08:06:20,873][795538] Starting process rollout_proc3
+[2023-02-24 08:06:20,874][795538] Starting process rollout_proc4
+[2023-02-24 08:06:20,874][795538] Starting process rollout_proc5
+[2023-02-24 08:06:20,874][795538] Starting process rollout_proc6
+[2023-02-24 08:06:20,875][795538] Starting process rollout_proc7
+[2023-02-24 08:06:22,179][795628] Worker 1 uses CPU cores [1]
+[2023-02-24 08:06:22,214][795634] Worker 6 uses CPU cores [6]
+[2023-02-24 08:06:22,319][795626] Low niceness requires sudo!
+[2023-02-24 08:06:22,319][795626] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:06:22,319][795626] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for inference process 0
+[2023-02-24 08:06:22,336][795626] Num visible devices: 1
+[2023-02-24 08:06:22,343][795613] Low niceness requires sudo!
+[2023-02-24 08:06:22,343][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:06:22,344][795613] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [0]) for learning process 0
+[2023-02-24 08:06:22,361][795613] Num visible devices: 1
+[2023-02-24 08:06:22,366][795632] Worker 5 uses CPU cores [5]
+[2023-02-24 08:06:22,394][795613] Starting seed is not provided
+[2023-02-24 08:06:22,394][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:06:22,394][795613] Initializing actor-critic model on device cuda:0
+[2023-02-24 08:06:22,395][795613] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:06:22,395][795613] RunningMeanStd input shape: (1,)
+[2023-02-24 08:06:22,409][795613] ConvEncoder: input_channels=3
+[2023-02-24 08:06:22,497][795613] Conv encoder output size: 512
+[2023-02-24 08:06:22,497][795613] Policy head output size: 512
+[2023-02-24 08:06:22,506][795613] Created Actor Critic model with architecture:
+[2023-02-24 08:06:22,507][795613] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2023-02-24 08:06:22,514][795631] Worker 4 uses CPU cores [4]
+[2023-02-24 08:06:22,542][795633] Worker 7 uses CPU cores [7]
+[2023-02-24 08:06:22,548][795630] Worker 3 uses CPU cores [3]
+[2023-02-24 08:06:22,590][795629] Worker 2 uses CPU cores [2]
+[2023-02-24 08:06:22,604][795627] Worker 0 uses CPU cores [0]
+[2023-02-24 08:06:25,136][795613] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-24 08:06:25,137][795613] 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...
+[2023-02-24 08:06:25,196][795613] Loading model from checkpoint
+[2023-02-24 08:06:25,198][795613] Loaded experiment state at self.train_step=268, self.env_steps=1097728
+[2023-02-24 08:06:25,198][795613] Initialized policy 0 weights for model version 268
+[2023-02-24 08:06:25,199][795613] LearnerWorker_p0 finished initialization!
+[2023-02-24 08:06:25,199][795613] Using GPUs [0] for process 0 (actually maps to GPUs [1])
+[2023-02-24 08:06:26,272][795626] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:06:26,272][795626] RunningMeanStd input shape: (1,)
+[2023-02-24 08:06:26,280][795626] ConvEncoder: input_channels=3
+[2023-02-24 08:06:26,341][795626] Conv encoder output size: 512
+[2023-02-24 08:06:26,342][795626] Policy head output size: 512
+[2023-02-24 08:06:27,341][795538] Inference worker 0-0 is ready!
+[2023-02-24 08:06:27,341][795538] All inference workers are ready! Signal rollout workers to start!
+[2023-02-24 08:06:27,358][795628] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,358][795631] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,358][795627] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,359][795629] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,364][795634] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,381][795632] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,380][795630] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,394][795633] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:06:27,569][795627] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:27,619][795634] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:27,650][795629] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:27,665][795630] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:27,805][795634] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:27,881][795630] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:27,882][795627] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:27,882][795632] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:28,090][795630] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:28,092][795632] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:28,106][795627] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:28,308][795632] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:28,376][795628] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:28,383][795630] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:28,383][795629] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:28,395][795627] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:28,625][795628] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:28,660][795633] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:28,720][795632] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:28,729][795631] Decorrelating experience for 0 frames...
+[2023-02-24 08:06:28,907][795633] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:28,955][795628] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:28,975][795634] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:29,141][795633] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:29,169][795631] Decorrelating experience for 32 frames...
+[2023-02-24 08:06:29,237][795628] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:29,253][795629] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:29,425][795631] Decorrelating experience for 64 frames...
+[2023-02-24 08:06:29,531][795629] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:29,537][795634] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:29,541][795633] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:29,684][795631] Decorrelating experience for 96 frames...
+[2023-02-24 08:06:29,698][795538] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 1097728. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 08:06:30,658][795613] Signal inference workers to stop experience collection...
+[2023-02-24 08:06:30,662][795626] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-24 08:06:32,942][795613] Signal inference workers to resume experience collection...
+[2023-02-24 08:06:32,942][795626] InferenceWorker_p0-w0: resuming experience collection
+[2023-02-24 08:06:34,697][795538] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 1126400. Throughput: 0: 628.8. Samples: 3144. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2023-02-24 08:06:34,699][795538] Avg episode reward: [(0, '5.223')]
+[2023-02-24 08:06:35,433][795626] Updated weights for policy 0, policy_version 278 (0.0234)
+[2023-02-24 08:06:38,065][795626] Updated weights for policy 0, policy_version 288 (0.0006)
+[2023-02-24 08:06:39,698][795538] Fps is (10 sec: 10649.4, 60 sec: 10649.4, 300 sec: 10649.4). Total num frames: 1204224. Throughput: 0: 2626.3. Samples: 26264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2023-02-24 08:06:39,699][795538] Avg episode reward: [(0, '6.797')]
+[2023-02-24 08:06:39,702][795613] Saving new best policy, reward=6.797!
+[2023-02-24 08:06:40,702][795626] Updated weights for policy 0, policy_version 298 (0.0006)
+[2023-02-24 08:06:40,762][795538] Heartbeat connected on Batcher_0
+[2023-02-24 08:06:40,764][795538] Heartbeat connected on LearnerWorker_p0
+[2023-02-24 08:06:40,771][795538] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-24 08:06:40,775][795538] Heartbeat connected on RolloutWorker_w0
+[2023-02-24 08:06:40,777][795538] Heartbeat connected on RolloutWorker_w2
+[2023-02-24 08:06:40,778][795538] Heartbeat connected on RolloutWorker_w1
+[2023-02-24 08:06:40,779][795538] Heartbeat connected on RolloutWorker_w3
+[2023-02-24 08:06:40,783][795538] Heartbeat connected on RolloutWorker_w4
+[2023-02-24 08:06:40,784][795538] Heartbeat connected on RolloutWorker_w5
+[2023-02-24 08:06:40,819][795538] Heartbeat connected on RolloutWorker_w7
+[2023-02-24 08:06:40,825][795538] Heartbeat connected on RolloutWorker_w6
+[2023-02-24 08:06:43,242][795626] Updated weights for policy 0, policy_version 308 (0.0007)
+[2023-02-24 08:06:44,698][795538] Fps is (10 sec: 15564.8, 60 sec: 12288.0, 300 sec: 12288.0). Total num frames: 1282048. Throughput: 0: 2536.4. Samples: 38046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
+[2023-02-24 08:06:44,698][795538] Avg episode reward: [(0, '7.215')]
+[2023-02-24 08:06:44,700][795613] Saving new best policy, reward=7.215!
+[2023-02-24 08:06:45,889][795626] Updated weights for policy 0, policy_version 318 (0.0007)
+[2023-02-24 08:06:48,495][795626] Updated weights for policy 0, policy_version 328 (0.0007)
+[2023-02-24 08:06:49,698][795538] Fps is (10 sec: 15565.1, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 1359872. Throughput: 0: 3079.6. Samples: 61592. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2023-02-24 08:06:49,699][795538] Avg episode reward: [(0, '8.493')]
+[2023-02-24 08:06:49,702][795613] Saving new best policy, reward=8.493!
+[2023-02-24 08:06:51,107][795626] Updated weights for policy 0, policy_version 338 (0.0007)
+[2023-02-24 08:06:53,724][795626] Updated weights for policy 0, policy_version 348 (0.0007)
+[2023-02-24 08:06:54,698][795538] Fps is (10 sec: 15564.7, 60 sec: 13598.7, 300 sec: 13598.7). Total num frames: 1437696. Throughput: 0: 3404.3. Samples: 85108. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:06:54,699][795538] Avg episode reward: [(0, '10.669')]
+[2023-02-24 08:06:54,700][795613] Saving new best policy, reward=10.669!
+[2023-02-24 08:06:56,371][795626] Updated weights for policy 0, policy_version 358 (0.0007)
+[2023-02-24 08:06:58,972][795626] Updated weights for policy 0, policy_version 368 (0.0007)
+[2023-02-24 08:06:59,697][795538] Fps is (10 sec: 15564.8, 60 sec: 13926.4, 300 sec: 13926.4). Total num frames: 1515520. Throughput: 0: 3226.5. Samples: 96796. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2023-02-24 08:06:59,698][795538] Avg episode reward: [(0, '13.259')]
+[2023-02-24 08:06:59,701][795613] Saving new best policy, reward=13.259!
+[2023-02-24 08:07:01,613][795626] Updated weights for policy 0, policy_version 378 (0.0007)
+[2023-02-24 08:07:04,206][795626] Updated weights for policy 0, policy_version 388 (0.0007)
+[2023-02-24 08:07:04,698][795538] Fps is (10 sec: 15564.9, 60 sec: 14160.5, 300 sec: 14160.5). Total num frames: 1593344. Throughput: 0: 3437.5. Samples: 120312. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2023-02-24 08:07:04,698][795538] Avg episode reward: [(0, '13.989')]
+[2023-02-24 08:07:04,699][795613] Saving new best policy, reward=13.989!
+[2023-02-24 08:07:06,831][795626] Updated weights for policy 0, policy_version 398 (0.0007)
+[2023-02-24 08:07:08,206][795538] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 795538], exiting...
+[2023-02-24 08:07:08,207][795538] Runner profile tree view:
+main_loop: 47.3880
+[2023-02-24 08:07:08,208][795613] Stopping Batcher_0...
+[2023-02-24 08:07:08,208][795613] Loop batcher_evt_loop terminating...
+[2023-02-24 08:07:08,208][795538] Collected {0: 1650688}, FPS: 11668.8
+[2023-02-24 08:07:08,209][795613] Saving /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000403_1650688.pth...
+[2023-02-24 08:07:08,216][795632] Stopping RolloutWorker_w5...
+[2023-02-24 08:07:08,216][795632] Loop rollout_proc5_evt_loop terminating...
+[2023-02-24 08:07:08,218][795630] Stopping RolloutWorker_w3...
+[2023-02-24 08:07:08,218][795630] Loop rollout_proc3_evt_loop terminating...
+[2023-02-24 08:07:08,218][795628] Stopping RolloutWorker_w1...
+[2023-02-24 08:07:08,218][795633] Stopping RolloutWorker_w7...
+[2023-02-24 08:07:08,219][795628] Loop rollout_proc1_evt_loop terminating...
+[2023-02-24 08:07:08,219][795633] Loop rollout_proc7_evt_loop terminating...
+[2023-02-24 08:07:08,221][795631] Stopping RolloutWorker_w4...
+[2023-02-24 08:07:08,221][795631] Loop rollout_proc4_evt_loop terminating...
+[2023-02-24 08:07:08,228][795629] Stopping RolloutWorker_w2...
+[2023-02-24 08:07:08,228][795629] Loop rollout_proc2_evt_loop terminating...
+[2023-02-24 08:07:08,230][795627] Stopping RolloutWorker_w0...
+[2023-02-24 08:07:08,230][795634] Stopping RolloutWorker_w6...
+[2023-02-24 08:07:08,230][795634] Loop rollout_proc6_evt_loop terminating...
+[2023-02-24 08:07:08,230][795627] Loop rollout_proc0_evt_loop terminating...
+[2023-02-24 08:07:08,252][795626] Weights refcount: 2 0
+[2023-02-24 08:07:08,256][795626] Stopping InferenceWorker_p0-w0...
+[2023-02-24 08:07:08,260][795626] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-24 08:07:08,376][795613] Stopping LearnerWorker_p0...
+[2023-02-24 08:07:08,377][795613] Loop learner_proc0_evt_loop terminating...
+[2023-02-24 08:07:38,064][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
+[2023-02-24 08:07:38,065][795538] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 08:07:38,065][795538] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 08:07:38,065][795538] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 08:07:38,066][795538] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 08:07:38,066][795538] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 08:07:38,066][795538] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-24 08:07:38,067][795538] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 08:07:38,067][795538] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-24 08:07:38,068][795538] Adding new argument 'hf_repository'='chqmatteo/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-24 08:07:38,068][795538] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 08:07:38,068][795538] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 08:07:38,068][795538] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 08:07:38,069][795538] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 08:07:38,069][795538] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 08:07:38,076][795538] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 08:07:38,077][795538] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 08:07:38,078][795538] RunningMeanStd input shape: (1,)
+[2023-02-24 08:07:38,086][795538] ConvEncoder: input_channels=3
+[2023-02-24 08:07:38,169][795538] Conv encoder output size: 512
+[2023-02-24 08:07:38,170][795538] Policy head output size: 512
+[2023-02-24 08:07:40,757][795538] 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_000000403_1650688.pth...
+[2023-02-24 08:07:42,930][795538] Num frames 100...
+[2023-02-24 08:07:43,007][795538] Num frames 200...
+[2023-02-24 08:07:43,075][795538] Num frames 300...
+[2023-02-24 08:07:43,138][795538] Num frames 400...
+[2023-02-24 08:07:43,207][795538] Num frames 500...
+[2023-02-24 08:07:43,275][795538] Num frames 600...
+[2023-02-24 08:07:43,349][795538] Num frames 700...
+[2023-02-24 08:07:43,409][795538] Avg episode rewards: #0: 16.090, true rewards: #0: 7.090
+[2023-02-24 08:07:43,410][795538] Avg episode reward: 16.090, avg true_objective: 7.090
+[2023-02-24 08:07:43,472][795538] Num frames 800...
+[2023-02-24 08:07:43,536][795538] Num frames 900...
+[2023-02-24 08:07:43,605][795538] Num frames 1000...
+[2023-02-24 08:07:43,689][795538] Num frames 1100...
+[2023-02-24 08:07:43,790][795538] Avg episode rewards: #0: 10.785, true rewards: #0: 5.785
+[2023-02-24 08:07:43,791][795538] Avg episode reward: 10.785, avg true_objective: 5.785
+[2023-02-24 08:07:43,819][795538] Num frames 1200...
+[2023-02-24 08:07:43,885][795538] Num frames 1300...
+[2023-02-24 08:07:43,956][795538] Num frames 1400...
+[2023-02-24 08:07:44,024][795538] Num frames 1500...
+[2023-02-24 08:07:44,102][795538] Num frames 1600...
+[2023-02-24 08:07:44,182][795538] Num frames 1700...
+[2023-02-24 08:07:44,280][795538] Avg episode rewards: #0: 10.217, true rewards: #0: 5.883
+[2023-02-24 08:07:44,280][795538] Avg episode reward: 10.217, avg true_objective: 5.883
+[2023-02-24 08:07:44,305][795538] Num frames 1800...
+[2023-02-24 08:07:44,373][795538] Num frames 1900...
+[2023-02-24 08:07:44,443][795538] Num frames 2000...
+[2023-02-24 08:07:44,519][795538] Num frames 2100...
+[2023-02-24 08:07:44,607][795538] Num frames 2200...
+[2023-02-24 08:07:44,678][795538] Num frames 2300...
+[2023-02-24 08:07:44,753][795538] Num frames 2400...
+[2023-02-24 08:07:44,838][795538] Num frames 2500...
+[2023-02-24 08:07:44,919][795538] Num frames 2600...
+[2023-02-24 08:07:45,012][795538] Avg episode rewards: #0: 12.653, true rewards: #0: 6.652
+[2023-02-24 08:07:45,013][795538] Avg episode reward: 12.653, avg true_objective: 6.652
+[2023-02-24 08:07:45,040][795538] Num frames 2700...
+[2023-02-24 08:07:45,115][795538] Num frames 2800...
+[2023-02-24 08:07:45,187][795538] Num frames 2900...
+[2023-02-24 08:07:45,261][795538] Num frames 3000...
+[2023-02-24 08:07:45,381][795538] Num frames 3100...
+[2023-02-24 08:07:45,448][795538] Num frames 3200...
+[2023-02-24 08:07:45,513][795538] Num frames 3300...
+[2023-02-24 08:07:45,581][795538] Num frames 3400...
+[2023-02-24 08:07:45,652][795538] Num frames 3500...
+[2023-02-24 08:07:45,717][795538] Num frames 3600...
+[2023-02-24 08:07:45,790][795538] Num frames 3700...
+[2023-02-24 08:07:45,860][795538] Num frames 3800...
+[2023-02-24 08:07:45,935][795538] Num frames 3900...
+[2023-02-24 08:07:46,006][795538] Num frames 4000...
+[2023-02-24 08:07:46,078][795538] Num frames 4100...
+[2023-02-24 08:07:46,213][795538] Avg episode rewards: #0: 17.194, true rewards: #0: 8.394
+[2023-02-24 08:07:46,214][795538] Avg episode reward: 17.194, avg true_objective: 8.394
+[2023-02-24 08:07:46,216][795538] Num frames 4200...
+[2023-02-24 08:07:46,291][795538] Num frames 4300...
+[2023-02-24 08:07:46,369][795538] Num frames 4400...
+[2023-02-24 08:07:46,449][795538] Num frames 4500...
+[2023-02-24 08:07:46,522][795538] Num frames 4600...
+[2023-02-24 08:07:46,591][795538] Num frames 4700...
+[2023-02-24 08:07:46,662][795538] Num frames 4800...
+[2023-02-24 08:07:46,732][795538] Num frames 4900...
+[2023-02-24 08:07:46,831][795538] Avg episode rewards: #0: 16.942, true rewards: #0: 8.275
+[2023-02-24 08:07:46,831][795538] Avg episode reward: 16.942, avg true_objective: 8.275
+[2023-02-24 08:07:46,855][795538] Num frames 5000...
+[2023-02-24 08:07:46,919][795538] Num frames 5100...
+[2023-02-24 08:07:46,986][795538] Num frames 5200...
+[2023-02-24 08:07:47,056][795538] Num frames 5300...
+[2023-02-24 08:07:47,141][795538] Num frames 5400...
+[2023-02-24 08:07:47,210][795538] Num frames 5500...
+[2023-02-24 08:07:47,278][795538] Num frames 5600...
+[2023-02-24 08:07:47,382][795538] Avg episode rewards: #0: 16.394, true rewards: #0: 8.109
+[2023-02-24 08:07:47,383][795538] Avg episode reward: 16.394, avg true_objective: 8.109
+[2023-02-24 08:07:47,406][795538] Num frames 5700...
+[2023-02-24 08:07:47,483][795538] Num frames 5800...
+[2023-02-24 08:07:47,567][795538] Num frames 5900...
+[2023-02-24 08:07:47,636][795538] Num frames 6000...
+[2023-02-24 08:07:47,706][795538] Num frames 6100...
+[2023-02-24 08:07:47,783][795538] Num frames 6200...
+[2023-02-24 08:07:47,861][795538] Num frames 6300...
+[2023-02-24 08:07:47,935][795538] Num frames 6400...
+[2023-02-24 08:07:48,009][795538] Num frames 6500...
+[2023-02-24 08:07:48,093][795538] Num frames 6600...
+[2023-02-24 08:07:48,166][795538] Num frames 6700...
+[2023-02-24 08:07:48,237][795538] Num frames 6800...
+[2023-02-24 08:07:48,313][795538] Num frames 6900...
+[2023-02-24 08:07:48,383][795538] Num frames 7000...
+[2023-02-24 08:07:48,450][795538] Num frames 7100...
+[2023-02-24 08:07:48,516][795538] Num frames 7200...
+[2023-02-24 08:07:48,594][795538] Num frames 7300...
+[2023-02-24 08:07:48,669][795538] Num frames 7400...
+[2023-02-24 08:07:48,742][795538] Num frames 7500...
+[2023-02-24 08:07:48,814][795538] Num frames 7600...
+[2023-02-24 08:07:48,895][795538] Num frames 7700...
+[2023-02-24 08:07:48,996][795538] Avg episode rewards: #0: 21.345, true rewards: #0: 9.720
+[2023-02-24 08:07:48,997][795538] Avg episode reward: 21.345, avg true_objective: 9.720
+[2023-02-24 08:07:49,018][795538] Num frames 7800...
+[2023-02-24 08:07:49,092][795538] Num frames 7900...
+[2023-02-24 08:07:49,171][795538] Num frames 8000...
+[2023-02-24 08:07:49,241][795538] Num frames 8100...
+[2023-02-24 08:07:49,311][795538] Num frames 8200...
+[2023-02-24 08:07:49,424][795538] Avg episode rewards: #0: 20.098, true rewards: #0: 9.209
+[2023-02-24 08:07:49,425][795538] Avg episode reward: 20.098, avg true_objective: 9.209
+[2023-02-24 08:07:49,434][795538] Num frames 8300...
+[2023-02-24 08:07:49,502][795538] Num frames 8400...
+[2023-02-24 08:07:49,568][795538] Num frames 8500...
+[2023-02-24 08:07:49,643][795538] Num frames 8600...
+[2023-02-24 08:07:49,707][795538] Num frames 8700...
+[2023-02-24 08:07:49,763][795538] Avg episode rewards: #0: 18.704, true rewards: #0: 8.704
+[2023-02-24 08:07:49,764][795538] Avg episode reward: 18.704, avg true_objective: 8.704
+[2023-02-24 08:07:53,791][795538] Replay video saved to /mnt/chqma/data-ssd-01/dataset/oss/RWKV-LM/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4!