A2C playing HalfCheetahBulletEnv-v0 from https://github.com/sgoodfriend/rl-algo-impls/tree/2067e21d62fff5db60168687e7d9e89019a8bfc0

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 2405.83 +/- 43.64
+      value: 2387.86 +/- 51.81
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -31,9 +31,9 @@ This model was trained from 3 trainings of **A2C** agents using different initia
 
 | algo   | env                     |   seed |   reward_mean |   reward_std |   eval_episodes | best   | wandb_url                                                                    |
 |:-------|:------------------------|-------:|--------------:|-------------:|----------------:|:-------|:-----------------------------------------------------------------------------|
-| a2c    | HalfCheetahBulletEnv-v0 |      1 |       1561.66 |      29.2954 |              12 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/gcz6tqfi) |
-| a2c    | HalfCheetahBulletEnv-v0 |      2 |       2346.67 |      53.5202 |              12 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/pgcystet) |
-| a2c    | HalfCheetahBulletEnv-v0 |      3 |       2405.83 |      43.6383 |              12 | *      | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/ngr2j7of) |
+| a2c    | HalfCheetahBulletEnv-v0 |      1 |       1554.89 |      32.0864 |              12 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/gcz6tqfi) |
+| a2c    | HalfCheetahBulletEnv-v0 |      2 |       2343.9  |      58.7541 |              12 |        | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/pgcystet) |
+| a2c    | HalfCheetahBulletEnv-v0 |      3 |       2387.86 |      51.8069 |              12 | *      | [wandb](https://wandb.ai/sgoodfriend/rl-algo-impls-benchmarks/runs/ngr2j7of) |
 
 
 ### Prerequisites: Weights & Biases (WandB)

replay.meta.json

@@ -1 +1 @@
-{"content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 5.1.2 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with clang version 14.0.6\\nconfiguration: --prefix=/Users/runner/miniforge3/conda-bld/ffmpeg_1674566267822/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_pl --cc=arm64-apple-darwin20.0.0-clang --cxx=arm64-apple-darwin20.0.0-clang++ --nm=arm64-apple-darwin20.0.0-nm --ar=arm64-apple-darwin20.0.0-ar --disable-doc --disable-openssl --enable-demuxer=dash --enable-hardcoded-tables --enable-libfreetype --enable-libfontconfig --enable-libopenh264 --enable-cross-compile --arch=arm64 --target-os=darwin --cross-prefix=arm64-apple-darwin20.0.0- --host-cc=/Users/runner/miniforge3/conda-bld/ffmpeg_1674566267822/_build_env/bin/x86_64-apple-darwin13.4.0-clang --enable-neon --enable-gnutls --enable-libmp3lame --enable-libvpx --enable-pthreads --enable-gpl --enable-libx264 --enable-libx265 --enable-libaom --enable-libsvtav1 --enable-libxml2 --enable-pic --enable-shared --disable-static --enable-version3 --enable-zlib --enable-libopus --pkg-config=/Users/runner/miniforge3/conda-bld/ffmpeg_1674566267822/_build_env/bin/pkg-config\\nlibavutil      57. 28.100 / 57. 28.100\\nlibavcodec     59. 37.100 / 59. 37.100\\nlibavformat    59. 27.100 / 59. 27.100\\nlibavdevice    59.  7.100 / 59.  7.100\\nlibavfilter     8. 44.100 /  8. 44.100\\nlibswscale      6.  7.100 /  6.  7.100\\nlibswresample   4.  7.100 /  4.  7.100\\nlibpostproc    56.  6.100 / 56.  6.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "320x240", "-pix_fmt", "rgb24", "-framerate", "60", "-i", "-", "-vf", "scale=trunc(iw/2)*2:trunc(ih/2)*2", "-vcodec", "libx264", "-pix_fmt", "yuv420p", "-r", "60", "/var/folders/9g/my5557_91xddp6lx00nkzly80000gn/T/tmpooxy24i1/a2c-HalfCheetahBulletEnv-v0/replay.mp4"]}, "episode": {"r": 2432.32421875, "l": 1000, "t": 10.061669}}
+{"content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)\\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\\nlibavutil      56. 31.100 / 56. 31.100\\nlibavcodec     58. 54.100 / 58. 54.100\\nlibavformat    58. 29.100 / 58. 29.100\\nlibavdevice    58.  8.100 / 58.  8.100\\nlibavfilter     7. 57.100 /  7. 57.100\\nlibavresample   4.  0.  0 /  4.  0.  0\\nlibswscale      5.  5.100 /  5.  5.100\\nlibswresample   3.  5.100 /  3.  5.100\\nlibpostproc    55.  5.100 / 55.  5.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "320x240", "-pix_fmt", "rgb24", "-framerate", "60", "-i", "-", "-vf", "scale=trunc(iw/2)*2:trunc(ih/2)*2", "-vcodec", "libx264", "-pix_fmt", "yuv420p", "-r", "60", "/tmp/tmpx0g2whn6/a2c-HalfCheetahBulletEnv-v0/replay.mp4"]}, "episode": {"r": 2429.250244140625, "l": 1000, "t": 29.19781}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4940ad5e28e815c91a799551d7aaf41add0cdb4e7238a7d9c5fb77f874781bc
-size 980124
+oid sha256:f074adf13778ee701016cbb226a4fe154826f6a898a0f814529ea72e313f4aae
+size 985254

rl_algo_impls/benchmark_publish.py

@@ -54,8 +54,8 @@ def benchmark_publish() -> None:
         "--virtual-display", action="store_true", help="Use headless virtual display"
     )
     # parser.set_defaults(
-    #     wandb_tags=["benchmark_e47a44c", "host_129-146-2-230"],
-    #     wandb_report_url="https://api.wandb.ai/links/sgoodfriend/v4wd7cp5",
+    #     wandb_tags=["benchmark_2067e21", "host_155-248-199-228"],
+    #     wandb_report_url="https://api.wandb.ai/links/sgoodfriend/09frjfcs",
     #     envs=[],
     #     exclude_envs=[],
     # )