diff --git a/.gitattributes b/.gitattributes index 41e52fe712136bab65c4437d6333198fc5996844..19cc3ec10300a5a584de8e16f8b2773ed07b03a0 100644 --- a/.gitattributes +++ b/.gitattributes @@ -43,3 +43,4 @@ videos/Walker2d-v4__ppo_fix_continuous_action__5__1704498502-eval/rl-video-episo videos/Walker2d-v4__ppo_fix_continuous_action__5__1704498502-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text videos/Walker2d-v4__ppo_fix_continuous_action__5__1704498502-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text +videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 64d41d153a494166434ca881bfaf4d5a2e167d9e..b0b61be28b8d5ca94f126649ea3d55a59d6a3597 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ model-index: type: Walker2d-v4 metrics: - type: mean_reward - value: 1457.49 +/- 811.87 + value: 2666.63 +/- 826.90 name: mean_reward verified: false --- @@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-see curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed5/raw/main/pyproject.toml curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed5/raw/main/poetry.lock poetry install --all-extras -python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Walker2d-v4 --seed 5 --track --cuda False +python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Walker2d-v4 --seed 5 --track ``` # Hyperparameters @@ -56,7 +56,7 @@ python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpk 'capture_video': False, 'clip_coef': 0.2, 'clip_vloss': True, - 'cuda': False, + 'cuda': True, 'ent_coef': 0.0, 'env_id': 'Walker2d-v4', 'exp_name': 'ppo_fix_continuous_action', diff --git a/events.out.tfevents.1705721030.3090-172.2802263.0 b/events.out.tfevents.1705721030.3090-172.2802263.0 deleted file mode 100644 index 39b98c5f19476a66b934dbbdecae289846d21dda..0000000000000000000000000000000000000000 --- a/events.out.tfevents.1705721030.3090-172.2802263.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6279a7e79abe1861119b9dd2611ab27766decc58ba4c1098c0a8b49a29c29239 -size 791356 diff --git a/events.out.tfevents.1705732450.4090-171.2644324.0 b/events.out.tfevents.1705732450.4090-171.2644324.0 new file mode 100644 index 0000000000000000000000000000000000000000..b5048bbf4a005154b92aa87e650bca4be67e9a7c --- /dev/null +++ b/events.out.tfevents.1705732450.4090-171.2644324.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c766e39ff03dbc64dc240ad423f87df6d25e04a5303f040a11068c24fe5c93 +size 790627 diff --git a/ppo_fix_continuous_action-10000.cleanrl_model b/ppo_fix_continuous_action-10000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9167502a4dcbc16fcc7b3c0d6d114f71b6dab530 Binary files /dev/null and b/ppo_fix_continuous_action-10000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-100000.cleanrl_model b/ppo_fix_continuous_action-100000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..406ef058571b102cb8637812dbf6372ae093d92f Binary files /dev/null and b/ppo_fix_continuous_action-100000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-105000.cleanrl_model b/ppo_fix_continuous_action-105000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..759150fd287edae884658edf8a2d0ca2d9f33ea7 Binary files /dev/null and b/ppo_fix_continuous_action-105000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-110000.cleanrl_model b/ppo_fix_continuous_action-110000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e46eb44516a84c6501af14f4431e8c67a921f003 Binary files /dev/null and b/ppo_fix_continuous_action-110000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-115000.cleanrl_model b/ppo_fix_continuous_action-115000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a5d184cadce6c65d088285169de81fa8e00ff545 Binary files /dev/null and b/ppo_fix_continuous_action-115000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-120000.cleanrl_model b/ppo_fix_continuous_action-120000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..85ee0cfd048431caeb4d88e805430a364d0f4bd4 Binary files /dev/null and b/ppo_fix_continuous_action-120000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-125000.cleanrl_model b/ppo_fix_continuous_action-125000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a88e085d43d525a165bbf9adf4b520c6722fe4e8 Binary files /dev/null and b/ppo_fix_continuous_action-125000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-130000.cleanrl_model b/ppo_fix_continuous_action-130000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ddead151adc1cac649a725a207e704abb087f62a Binary files /dev/null and b/ppo_fix_continuous_action-130000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-135000.cleanrl_model b/ppo_fix_continuous_action-135000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..25d984e5475c2452a3d83b8586af1b7dbe9493aa Binary files /dev/null and b/ppo_fix_continuous_action-135000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-140000.cleanrl_model b/ppo_fix_continuous_action-140000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..3e23a313ad15843de61cb5738ef776a70f213b80 Binary files /dev/null and b/ppo_fix_continuous_action-140000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-145000.cleanrl_model b/ppo_fix_continuous_action-145000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..af7708f51e89147dbf9bc55b2123de3648c09edc Binary files /dev/null and b/ppo_fix_continuous_action-145000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-15000.cleanrl_model b/ppo_fix_continuous_action-15000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e4bc8c1fd2640360b58bc43234a7c17838211f8c Binary files /dev/null and b/ppo_fix_continuous_action-15000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-150000.cleanrl_model b/ppo_fix_continuous_action-150000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0169dda9a15c842b696e6caa6e252889bf686093 Binary files /dev/null and b/ppo_fix_continuous_action-150000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-155000.cleanrl_model b/ppo_fix_continuous_action-155000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0f7f942ff50765dd4f34d00ea5403f52ac2e121c Binary files /dev/null and b/ppo_fix_continuous_action-155000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-160000.cleanrl_model b/ppo_fix_continuous_action-160000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..519ae6bf6e20c390084498e4d959db84eb6f0253 Binary files /dev/null and b/ppo_fix_continuous_action-160000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-165000.cleanrl_model b/ppo_fix_continuous_action-165000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0498ec3a9ed32bb61adddaa06c675e6f624e26ea Binary files /dev/null and b/ppo_fix_continuous_action-165000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-170000.cleanrl_model b/ppo_fix_continuous_action-170000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..90fa758ab70213e3b2c44f480d13348d6a3762b5 Binary files /dev/null and b/ppo_fix_continuous_action-170000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-175000.cleanrl_model b/ppo_fix_continuous_action-175000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0d2c9574574e3974b67de2f33fe35b8ec59e3b1f Binary files /dev/null and b/ppo_fix_continuous_action-175000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-180000.cleanrl_model b/ppo_fix_continuous_action-180000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9e4ff1405b0e02929bec7cfd73ef2b5c87cb2ca5 Binary files /dev/null and b/ppo_fix_continuous_action-180000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-185000.cleanrl_model b/ppo_fix_continuous_action-185000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9f6e8f885c524869555b23ce9e43fe42751ce9d5 Binary files /dev/null and b/ppo_fix_continuous_action-185000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-190000.cleanrl_model b/ppo_fix_continuous_action-190000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..760d87fe9be6fb2c684a6fbfaeb4931d29ed1249 Binary files /dev/null and b/ppo_fix_continuous_action-190000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-195000.cleanrl_model b/ppo_fix_continuous_action-195000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ee1e9942127ca7c8aeb3772eaf94bf131e233f5f Binary files /dev/null and b/ppo_fix_continuous_action-195000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-20000.cleanrl_model b/ppo_fix_continuous_action-20000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..82a91f2203b8e1bae859bc221e47f700630d99d9 Binary files /dev/null and b/ppo_fix_continuous_action-20000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-200000.cleanrl_model b/ppo_fix_continuous_action-200000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ae75e6cbfc9cd0b6f8e9ad4ef2659e82c691c6d1 Binary files /dev/null and b/ppo_fix_continuous_action-200000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-205000.cleanrl_model b/ppo_fix_continuous_action-205000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..cb2860ede24ed4bd79c962a59e6f0227448fa246 Binary files /dev/null and b/ppo_fix_continuous_action-205000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-210000.cleanrl_model b/ppo_fix_continuous_action-210000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6f1adbceeef3f46b2382d6c354d1569fe8257d8a Binary files /dev/null and b/ppo_fix_continuous_action-210000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-215000.cleanrl_model b/ppo_fix_continuous_action-215000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..471165b5e6da755618ff0256752c0de5872ca592 Binary files /dev/null and b/ppo_fix_continuous_action-215000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-220000.cleanrl_model b/ppo_fix_continuous_action-220000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1465bb44bd17a65a22dd4035511ee753436e09ba Binary files /dev/null and b/ppo_fix_continuous_action-220000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-225000.cleanrl_model b/ppo_fix_continuous_action-225000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2bd41d5a595f82fc2498fa28d31b75799a2f345e Binary files /dev/null and b/ppo_fix_continuous_action-225000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-230000.cleanrl_model b/ppo_fix_continuous_action-230000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..891262c83253e0aada82ff1aa89bd511e05b62f9 Binary files /dev/null and b/ppo_fix_continuous_action-230000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-235000.cleanrl_model b/ppo_fix_continuous_action-235000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..17078e8759b8b0a918222649a6311a85ea9a3065 Binary files /dev/null and b/ppo_fix_continuous_action-235000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-240000.cleanrl_model b/ppo_fix_continuous_action-240000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a8564f85be396a3d1f256946b098c2c6b6cd09d0 Binary files /dev/null and b/ppo_fix_continuous_action-240000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-245000.cleanrl_model b/ppo_fix_continuous_action-245000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8faca9ed45c74b84866101d0233e7dbeb8a70fba Binary files /dev/null and b/ppo_fix_continuous_action-245000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-25000.cleanrl_model b/ppo_fix_continuous_action-25000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e3a70a0129c783e2ab4f9697c1de41091a4892d0 Binary files /dev/null and b/ppo_fix_continuous_action-25000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-250000.cleanrl_model b/ppo_fix_continuous_action-250000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..f4566a34c4b742b123fbbf96d53f7ae91901a5f6 Binary files /dev/null and b/ppo_fix_continuous_action-250000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-255000.cleanrl_model b/ppo_fix_continuous_action-255000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..27bce414dca191a08ffced26a07ee5f09b683a35 Binary files /dev/null and b/ppo_fix_continuous_action-255000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-260000.cleanrl_model b/ppo_fix_continuous_action-260000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..f6ef30cda120855e05eb597a0fd7697b811bac3e Binary files /dev/null and b/ppo_fix_continuous_action-260000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-265000.cleanrl_model b/ppo_fix_continuous_action-265000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4bb6fa567df4cc741099714daf1f08a2c4320010 Binary files /dev/null and b/ppo_fix_continuous_action-265000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-270000.cleanrl_model b/ppo_fix_continuous_action-270000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..22d534579bfb7b9b73b762ef27de8ef48a397db1 Binary files /dev/null and b/ppo_fix_continuous_action-270000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-275000.cleanrl_model b/ppo_fix_continuous_action-275000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..5e5b21722ff66b3bac114bbdf28a9932cda16f76 Binary files /dev/null and b/ppo_fix_continuous_action-275000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-280000.cleanrl_model b/ppo_fix_continuous_action-280000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2609ea693596e21857d74fb81f8b1811ab928cdb Binary files /dev/null and b/ppo_fix_continuous_action-280000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-285000.cleanrl_model b/ppo_fix_continuous_action-285000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..bbc4e8f3787fc292e2ec7e71da826d07a83c71cf Binary files /dev/null and b/ppo_fix_continuous_action-285000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-290000.cleanrl_model b/ppo_fix_continuous_action-290000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..bd5393267b9952b544ec35f4ea17f5fc07c00dfb Binary files /dev/null and b/ppo_fix_continuous_action-290000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-295000.cleanrl_model b/ppo_fix_continuous_action-295000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6233738cabedf227d4a292652bb62862ee2d16e3 Binary files /dev/null and b/ppo_fix_continuous_action-295000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-30000.cleanrl_model b/ppo_fix_continuous_action-30000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..96bd68b4bb061d621a1977026144051364b653a8 Binary files /dev/null and b/ppo_fix_continuous_action-30000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-300000.cleanrl_model b/ppo_fix_continuous_action-300000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e0b865d65e5c64208aa11893b267a8dcb359b078 Binary files /dev/null and b/ppo_fix_continuous_action-300000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-305000.cleanrl_model b/ppo_fix_continuous_action-305000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9d569cc55f414e1b9345f8009a882777af683632 Binary files /dev/null and b/ppo_fix_continuous_action-305000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-310000.cleanrl_model b/ppo_fix_continuous_action-310000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2835824d27b8a73e5be01563ef23a056934fc954 Binary files /dev/null and b/ppo_fix_continuous_action-310000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-315000.cleanrl_model b/ppo_fix_continuous_action-315000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..3495b6eb986347db97318a4cb1b58449f0244803 Binary files /dev/null and b/ppo_fix_continuous_action-315000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-320000.cleanrl_model b/ppo_fix_continuous_action-320000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..11834eb2ce1a2f35bc3b25b51ec3e1b338e314be Binary files /dev/null and b/ppo_fix_continuous_action-320000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-325000.cleanrl_model b/ppo_fix_continuous_action-325000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..92fc7ff5d3441ee276ce9e1f8873ecba0323ebb9 Binary files /dev/null and b/ppo_fix_continuous_action-325000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-330000.cleanrl_model b/ppo_fix_continuous_action-330000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e6127abe629d5fd3b0cbe187c7d4465fa628bd09 Binary files /dev/null and b/ppo_fix_continuous_action-330000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-335000.cleanrl_model b/ppo_fix_continuous_action-335000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9af1711aaffabb73333d11adf1634bab81a9715e Binary files /dev/null and b/ppo_fix_continuous_action-335000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-340000.cleanrl_model b/ppo_fix_continuous_action-340000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a08bb998ea1eaafaadfa108606492143c54f6617 Binary files /dev/null and b/ppo_fix_continuous_action-340000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-345000.cleanrl_model b/ppo_fix_continuous_action-345000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4f180d5af8fdc81ababd65304d5af2f0391d87bc Binary files /dev/null and b/ppo_fix_continuous_action-345000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-35000.cleanrl_model b/ppo_fix_continuous_action-35000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ecabb5c54e26f0a9d32a7329ddb47293a668752b Binary files /dev/null and b/ppo_fix_continuous_action-35000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-350000.cleanrl_model b/ppo_fix_continuous_action-350000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..cd9915c883dec4c2aca5d25cc624e69dcf5471be Binary files /dev/null and b/ppo_fix_continuous_action-350000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-355000.cleanrl_model b/ppo_fix_continuous_action-355000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..eb8f10992bf364088244e567d715bb06b2296e72 Binary files /dev/null and b/ppo_fix_continuous_action-355000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-360000.cleanrl_model b/ppo_fix_continuous_action-360000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e92d62d1828ae3c3457d58419dc187f580aaaf6c Binary files /dev/null and b/ppo_fix_continuous_action-360000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-365000.cleanrl_model b/ppo_fix_continuous_action-365000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..64e6d1d8cdfed074ec668afd8bd46242d45ae696 Binary files /dev/null and b/ppo_fix_continuous_action-365000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-370000.cleanrl_model b/ppo_fix_continuous_action-370000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..678cf0a3d6d076175c5f127a0546a11d3c4f37e3 Binary files /dev/null and b/ppo_fix_continuous_action-370000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-375000.cleanrl_model b/ppo_fix_continuous_action-375000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..edc23fee76d9b9b9c03b4cf351894465015ba2ef Binary files /dev/null and b/ppo_fix_continuous_action-375000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-380000.cleanrl_model b/ppo_fix_continuous_action-380000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e427e1e9275753137c99b4b5eb982b230379a7c7 Binary files /dev/null and b/ppo_fix_continuous_action-380000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-385000.cleanrl_model b/ppo_fix_continuous_action-385000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c1ed791a85735915458f03c7408ed1eaf9e63ad7 Binary files /dev/null and b/ppo_fix_continuous_action-385000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-390000.cleanrl_model b/ppo_fix_continuous_action-390000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..5fef60b660da6064f27b837064855b4ba82f3572 Binary files /dev/null and b/ppo_fix_continuous_action-390000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-395000.cleanrl_model b/ppo_fix_continuous_action-395000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9624ce1641dd095aa213a00ce8f04a484fe8ba9e Binary files /dev/null and b/ppo_fix_continuous_action-395000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-40000.cleanrl_model b/ppo_fix_continuous_action-40000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..96b6433bd2e0d5bfb5f412da0ebfdefd29dfeeec Binary files /dev/null and b/ppo_fix_continuous_action-40000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-400000.cleanrl_model b/ppo_fix_continuous_action-400000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c4fa6eb9080b4b1503709afa1abff70f9fa649fb Binary files /dev/null and b/ppo_fix_continuous_action-400000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-405000.cleanrl_model b/ppo_fix_continuous_action-405000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4dfdbb4ec6809bf8442ede1788f7ee707221781b Binary files /dev/null and b/ppo_fix_continuous_action-405000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-410000.cleanrl_model b/ppo_fix_continuous_action-410000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ec247fb07294bcf4912eb849653813b5011d8fe4 Binary files /dev/null and b/ppo_fix_continuous_action-410000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-415000.cleanrl_model b/ppo_fix_continuous_action-415000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..dbad604cea855c771a379d3bd7dcfdccd918dd65 Binary files /dev/null and b/ppo_fix_continuous_action-415000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-420000.cleanrl_model b/ppo_fix_continuous_action-420000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e456a22ef0db695c0a79cecbbcb701fde81baac5 Binary files /dev/null and b/ppo_fix_continuous_action-420000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-425000.cleanrl_model b/ppo_fix_continuous_action-425000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..aa1126ca072c559ca2a0198c1f13533be735b15f Binary files /dev/null and b/ppo_fix_continuous_action-425000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-430000.cleanrl_model b/ppo_fix_continuous_action-430000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..3bff3b2b4d9808fe9ec5af181e1d52ce485bb8ea Binary files /dev/null and b/ppo_fix_continuous_action-430000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-435000.cleanrl_model b/ppo_fix_continuous_action-435000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a2f571939a3cbe7f80078b0c1f70d55307d64560 Binary files /dev/null and b/ppo_fix_continuous_action-435000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-440000.cleanrl_model b/ppo_fix_continuous_action-440000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..fa1f4bd27a1ca17254e301fb10d8c621a146c3c7 Binary files /dev/null and b/ppo_fix_continuous_action-440000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-445000.cleanrl_model b/ppo_fix_continuous_action-445000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0ec6a0ffbdb4002591a7b42424e3218cb87390d0 Binary files /dev/null and b/ppo_fix_continuous_action-445000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-45000.cleanrl_model b/ppo_fix_continuous_action-45000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8a4e1c82f846ec460158c846294ec6539bc91244 Binary files /dev/null and b/ppo_fix_continuous_action-45000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-450000.cleanrl_model b/ppo_fix_continuous_action-450000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..330a72cff5db80384465392da4ba27a2a8c1a16d Binary files /dev/null and b/ppo_fix_continuous_action-450000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-455000.cleanrl_model b/ppo_fix_continuous_action-455000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8f709dc84ad1bf8dcf3e6b3de3cccbac56dfc1fe Binary files /dev/null and b/ppo_fix_continuous_action-455000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-460000.cleanrl_model b/ppo_fix_continuous_action-460000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2df137c9c1ec513be1d8f12915e24a505ba9fe2a Binary files /dev/null and b/ppo_fix_continuous_action-460000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-465000.cleanrl_model b/ppo_fix_continuous_action-465000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..949118a708d6fe69827325a0b24ae398a596c3f4 Binary files /dev/null and b/ppo_fix_continuous_action-465000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-470000.cleanrl_model b/ppo_fix_continuous_action-470000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4ccb9e76b7263ff676ef744bf1293c071f14f1a4 Binary files /dev/null and b/ppo_fix_continuous_action-470000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-475000.cleanrl_model b/ppo_fix_continuous_action-475000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6cc8666ef6cab42e595c1d849b38e3b84fd5c28f Binary files /dev/null and b/ppo_fix_continuous_action-475000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-480000.cleanrl_model b/ppo_fix_continuous_action-480000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2d5991a3bb2ef5e60a6f7f79da16f3839d5c52e4 Binary files /dev/null and b/ppo_fix_continuous_action-480000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-485000.cleanrl_model b/ppo_fix_continuous_action-485000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6a0bc5f6902861e71201867471963ef0c3492653 Binary files /dev/null and b/ppo_fix_continuous_action-485000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-490000.cleanrl_model b/ppo_fix_continuous_action-490000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4a78e310b174dd4b3c92ab7f203dd874922a872e Binary files /dev/null and b/ppo_fix_continuous_action-490000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-495000.cleanrl_model b/ppo_fix_continuous_action-495000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a48555e184673240cc34b405112dbd2deb48a09e Binary files /dev/null and b/ppo_fix_continuous_action-495000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-5000.cleanrl_model b/ppo_fix_continuous_action-5000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..260be92cbe792a36d8dae396806d33f6e7eb6c61 Binary files /dev/null and b/ppo_fix_continuous_action-5000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-50000.cleanrl_model b/ppo_fix_continuous_action-50000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8e8e9f15ca52b52d57b865f1cf049828e2d73ee4 Binary files /dev/null and b/ppo_fix_continuous_action-50000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-500000.cleanrl_model b/ppo_fix_continuous_action-500000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2e1f1915f38e15cce4d8f26fdba7fc927ed54011 Binary files /dev/null and b/ppo_fix_continuous_action-500000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-505000.cleanrl_model b/ppo_fix_continuous_action-505000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4ff246f61b115bce34b1920c6e1ea35142d3f705 Binary files /dev/null and b/ppo_fix_continuous_action-505000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-510000.cleanrl_model b/ppo_fix_continuous_action-510000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..28063744210bb767faf2cb8c9dbf5c0f192029f9 Binary files /dev/null and b/ppo_fix_continuous_action-510000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-515000.cleanrl_model b/ppo_fix_continuous_action-515000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c53071aa824989b3a60d68ee4ecb27a3e15909d1 Binary files /dev/null and b/ppo_fix_continuous_action-515000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-520000.cleanrl_model b/ppo_fix_continuous_action-520000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..f3bd6484e989febde719df9cb000f11f54bc8e52 Binary files /dev/null and b/ppo_fix_continuous_action-520000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-525000.cleanrl_model b/ppo_fix_continuous_action-525000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..7a0bae66767e889cf38e0725e20471324b481a34 Binary files /dev/null and b/ppo_fix_continuous_action-525000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-530000.cleanrl_model b/ppo_fix_continuous_action-530000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..44c410776c896b50cf03a1c072ae3716818d672a Binary files /dev/null and b/ppo_fix_continuous_action-530000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-535000.cleanrl_model b/ppo_fix_continuous_action-535000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e8f5ae8d8a74f6ad467340e4735a5b325350afb8 Binary files /dev/null and b/ppo_fix_continuous_action-535000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-540000.cleanrl_model b/ppo_fix_continuous_action-540000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..256016ed99f84e1fda11ceb43c0d78e2b984ecc2 Binary files /dev/null and b/ppo_fix_continuous_action-540000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-545000.cleanrl_model b/ppo_fix_continuous_action-545000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..f4b5de74921bbc667df6d717b962a83694904b73 Binary files /dev/null and b/ppo_fix_continuous_action-545000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-55000.cleanrl_model b/ppo_fix_continuous_action-55000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..04673f6b0ce76d5804e42b9c2ea23b4b5e8c218c Binary files /dev/null and b/ppo_fix_continuous_action-55000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-550000.cleanrl_model b/ppo_fix_continuous_action-550000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2c44991e75d02609dda8300c9c31434178cf2110 Binary files /dev/null and b/ppo_fix_continuous_action-550000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-555000.cleanrl_model b/ppo_fix_continuous_action-555000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..89e50ebadc9441341b14e3070adf360cf52892f9 Binary files /dev/null and b/ppo_fix_continuous_action-555000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-560000.cleanrl_model b/ppo_fix_continuous_action-560000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..b04b75dc6c29ca022b0a18db5ea76153f60b8eac Binary files /dev/null and b/ppo_fix_continuous_action-560000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-565000.cleanrl_model b/ppo_fix_continuous_action-565000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e0abfe8f9dfba9bb69d89a27139b54d58fd9dc4a Binary files /dev/null and b/ppo_fix_continuous_action-565000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-570000.cleanrl_model b/ppo_fix_continuous_action-570000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..5973daf055d22c6ddf1e937cdcce003eef63444f Binary files /dev/null and b/ppo_fix_continuous_action-570000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-575000.cleanrl_model b/ppo_fix_continuous_action-575000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..098089f6ae3e50946b244ee44964479c878f90d6 Binary files /dev/null and b/ppo_fix_continuous_action-575000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-580000.cleanrl_model b/ppo_fix_continuous_action-580000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..3b97bd0574e9a757894a819dcbf5f25d96131f04 Binary files /dev/null and b/ppo_fix_continuous_action-580000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-585000.cleanrl_model b/ppo_fix_continuous_action-585000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..dce92e45cd8ebd5c7477efad1c8e05943c7016c0 Binary files /dev/null and b/ppo_fix_continuous_action-585000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-590000.cleanrl_model b/ppo_fix_continuous_action-590000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..d2349ea338b90f8d370835e1851d143bf32bf842 Binary files /dev/null and b/ppo_fix_continuous_action-590000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-595000.cleanrl_model b/ppo_fix_continuous_action-595000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8ce4db3264d5c37a6ec3b26ce1c52fbea48eebb1 Binary files /dev/null and b/ppo_fix_continuous_action-595000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-60000.cleanrl_model b/ppo_fix_continuous_action-60000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..5dd4a9fb461c180cd7e66239650d50a837644248 Binary files /dev/null and b/ppo_fix_continuous_action-60000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-600000.cleanrl_model b/ppo_fix_continuous_action-600000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..356bbdf981cbea588763cf9d30ee68be2068157c Binary files /dev/null and b/ppo_fix_continuous_action-600000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-605000.cleanrl_model b/ppo_fix_continuous_action-605000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..689f5e1401158331d450a573f8eb3b60207da8e8 Binary files /dev/null and b/ppo_fix_continuous_action-605000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-610000.cleanrl_model b/ppo_fix_continuous_action-610000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..62be581100e5b82c7338df2c916f4b64efaced2a Binary files /dev/null and b/ppo_fix_continuous_action-610000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-615000.cleanrl_model b/ppo_fix_continuous_action-615000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8bdd25e998b52939e3be952257eea49d01691e23 Binary files /dev/null and b/ppo_fix_continuous_action-615000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-620000.cleanrl_model b/ppo_fix_continuous_action-620000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..eb4c16d22c1132deac63839ce419c768a167c82e Binary files /dev/null and b/ppo_fix_continuous_action-620000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-625000.cleanrl_model b/ppo_fix_continuous_action-625000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4f92f03030a4a2ccc93f6bf7b1e7bced318e4034 Binary files /dev/null and b/ppo_fix_continuous_action-625000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-630000.cleanrl_model b/ppo_fix_continuous_action-630000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..287f24125807bc05ca618f082c7bb4dd42eef6d4 Binary files /dev/null and b/ppo_fix_continuous_action-630000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-635000.cleanrl_model b/ppo_fix_continuous_action-635000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..884f5654d1c22fd5ad192f4f69c81ca957bcc26a Binary files /dev/null and b/ppo_fix_continuous_action-635000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-640000.cleanrl_model b/ppo_fix_continuous_action-640000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..63af3b60f2692579102709c35e6472a2ca9e3640 Binary files /dev/null and b/ppo_fix_continuous_action-640000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-645000.cleanrl_model b/ppo_fix_continuous_action-645000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2df895730b25833b29c550425912ccf9ed4d1387 Binary files /dev/null and b/ppo_fix_continuous_action-645000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-65000.cleanrl_model b/ppo_fix_continuous_action-65000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..998986009661badfc4ecc122484bf3ea92137ec5 Binary files /dev/null and b/ppo_fix_continuous_action-65000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-650000.cleanrl_model b/ppo_fix_continuous_action-650000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..534e1121d732dd3a30667300dc51d6ea0a78970a Binary files /dev/null and b/ppo_fix_continuous_action-650000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-655000.cleanrl_model b/ppo_fix_continuous_action-655000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8d581bd663a5405f414b8130783fcc9b5f66b523 Binary files /dev/null and b/ppo_fix_continuous_action-655000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-660000.cleanrl_model b/ppo_fix_continuous_action-660000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..792a51bf10b3ae28317d60ef49eb01f1620874a4 Binary files /dev/null and b/ppo_fix_continuous_action-660000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-665000.cleanrl_model b/ppo_fix_continuous_action-665000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..02fb63fd74aeb04753a20657c421da9cbd288c3b Binary files /dev/null and b/ppo_fix_continuous_action-665000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-670000.cleanrl_model b/ppo_fix_continuous_action-670000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0a35bfc018d8629b460f3928158fa591a97733ef Binary files /dev/null and b/ppo_fix_continuous_action-670000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-675000.cleanrl_model b/ppo_fix_continuous_action-675000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8ef5d9f3c04a3ddcb90d98c0bb816eccef90a1bf Binary files /dev/null and b/ppo_fix_continuous_action-675000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-680000.cleanrl_model b/ppo_fix_continuous_action-680000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..bfdb04ecbe996ee2167ce62947e130e4ae05b90c Binary files /dev/null and b/ppo_fix_continuous_action-680000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-685000.cleanrl_model b/ppo_fix_continuous_action-685000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..887c5e013a1e16b2cb79353f1fac3fa42cfb5a98 Binary files /dev/null and b/ppo_fix_continuous_action-685000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-690000.cleanrl_model b/ppo_fix_continuous_action-690000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..29948097aa660aa65281f067ab2b4087f1fabef6 Binary files /dev/null and b/ppo_fix_continuous_action-690000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-695000.cleanrl_model b/ppo_fix_continuous_action-695000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..aac7a0d5761fdb59dab5566d72efd8ec4f9b335a Binary files /dev/null and b/ppo_fix_continuous_action-695000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-70000.cleanrl_model b/ppo_fix_continuous_action-70000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..05b295f01746dd08d2a509e0dc95712dc291cdcd Binary files /dev/null and b/ppo_fix_continuous_action-70000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-700000.cleanrl_model b/ppo_fix_continuous_action-700000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6fbe27951c3577c0358f835215e335b1c47d4dac Binary files /dev/null and b/ppo_fix_continuous_action-700000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-705000.cleanrl_model b/ppo_fix_continuous_action-705000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..d87d3656aeb4f8a51759128abd69fc4d55cdebef Binary files /dev/null and b/ppo_fix_continuous_action-705000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-710000.cleanrl_model b/ppo_fix_continuous_action-710000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..01750f02d378ca94edc982cc154c0b02514d276f Binary files /dev/null and b/ppo_fix_continuous_action-710000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-715000.cleanrl_model b/ppo_fix_continuous_action-715000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0fe853ab639dd8658d4ddd05012d199b3af0bea9 Binary files /dev/null and b/ppo_fix_continuous_action-715000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-720000.cleanrl_model b/ppo_fix_continuous_action-720000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..b927381455dc4fc053c11a79c356d1483f27827c Binary files /dev/null and b/ppo_fix_continuous_action-720000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-725000.cleanrl_model b/ppo_fix_continuous_action-725000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..cb99b690a33402bf3ae1be61bc0ba1173bf365d5 Binary files /dev/null and b/ppo_fix_continuous_action-725000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-730000.cleanrl_model b/ppo_fix_continuous_action-730000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c20f797170b30952e8529878e71f0bb5136f5cff Binary files /dev/null and b/ppo_fix_continuous_action-730000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-735000.cleanrl_model b/ppo_fix_continuous_action-735000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..147a885d11a8e3dac58254b206e031c0903772e0 Binary files /dev/null and b/ppo_fix_continuous_action-735000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-740000.cleanrl_model b/ppo_fix_continuous_action-740000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..69bd050a2727507e696ed71f62e5c87429afbb97 Binary files /dev/null and b/ppo_fix_continuous_action-740000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-745000.cleanrl_model b/ppo_fix_continuous_action-745000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1ab1b661640869c3558b81817fe4fcb57c4707a8 Binary files /dev/null and b/ppo_fix_continuous_action-745000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-75000.cleanrl_model b/ppo_fix_continuous_action-75000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c95b37f0cb3ca8c3c2cc2600f0db8ef53d2e43f9 Binary files /dev/null and b/ppo_fix_continuous_action-75000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-750000.cleanrl_model b/ppo_fix_continuous_action-750000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..bf5d860ddd31789d660e5f40b31a20c787940353 Binary files /dev/null and b/ppo_fix_continuous_action-750000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-755000.cleanrl_model b/ppo_fix_continuous_action-755000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..541269c6a34dfe30bfa835b3c4928d6dcaa54da0 Binary files /dev/null and b/ppo_fix_continuous_action-755000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-760000.cleanrl_model b/ppo_fix_continuous_action-760000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1b04221afbce52709e1c4445864f856cd68ca1b3 Binary files /dev/null and b/ppo_fix_continuous_action-760000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-765000.cleanrl_model b/ppo_fix_continuous_action-765000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c9a3411e36575bc76976e80d23f7407657118bc7 Binary files /dev/null and b/ppo_fix_continuous_action-765000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-770000.cleanrl_model b/ppo_fix_continuous_action-770000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e9470c5a93178c9d5d54fe7ad9f3a1e8f3110ba3 Binary files /dev/null and b/ppo_fix_continuous_action-770000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-775000.cleanrl_model b/ppo_fix_continuous_action-775000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..59a615377fe1ba7f2c4ed1dd41360c575ab45a1d Binary files /dev/null and b/ppo_fix_continuous_action-775000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-780000.cleanrl_model b/ppo_fix_continuous_action-780000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a892b32174472704804e4a6a5e0cef24646ab376 Binary files /dev/null and b/ppo_fix_continuous_action-780000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-785000.cleanrl_model b/ppo_fix_continuous_action-785000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..96e2c0b896b8c16a35cf460913fa52ebaff15d9a Binary files /dev/null and b/ppo_fix_continuous_action-785000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-790000.cleanrl_model b/ppo_fix_continuous_action-790000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..742839873c62a292f22f4cbf40905a8871373a1c Binary files /dev/null and b/ppo_fix_continuous_action-790000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-795000.cleanrl_model b/ppo_fix_continuous_action-795000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..d2b4f115cc6132d1aef7a309341d8c2134521b3e Binary files /dev/null and b/ppo_fix_continuous_action-795000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-80000.cleanrl_model b/ppo_fix_continuous_action-80000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..8ff61aea5767bfd4f5545b52333b17ff866554d2 Binary files /dev/null and b/ppo_fix_continuous_action-80000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-800000.cleanrl_model b/ppo_fix_continuous_action-800000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..382f3695573afd869d8d0879e79854e929621e02 Binary files /dev/null and b/ppo_fix_continuous_action-800000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-805000.cleanrl_model b/ppo_fix_continuous_action-805000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..3d772c5c0829769dc6c7d1c38386afc833fb46e6 Binary files /dev/null and b/ppo_fix_continuous_action-805000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-810000.cleanrl_model b/ppo_fix_continuous_action-810000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..b40896b48c7546ad5755c119fd6f2ae9b6d56f36 Binary files /dev/null and b/ppo_fix_continuous_action-810000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-815000.cleanrl_model b/ppo_fix_continuous_action-815000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c8f0a5ba9cc43c2a3c0a53d63e4b0ea9e185e541 Binary files /dev/null and b/ppo_fix_continuous_action-815000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-820000.cleanrl_model b/ppo_fix_continuous_action-820000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..fc8c3010c010647c1de0374380827fe61ee237db Binary files /dev/null and b/ppo_fix_continuous_action-820000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-825000.cleanrl_model b/ppo_fix_continuous_action-825000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..d04bb7cb73544366654712ce74ee1e655cc956c9 Binary files /dev/null and b/ppo_fix_continuous_action-825000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-830000.cleanrl_model b/ppo_fix_continuous_action-830000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..4e5a8e515a4d87ccc85b3efb0e4e432dfde5fe9c Binary files /dev/null and b/ppo_fix_continuous_action-830000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-835000.cleanrl_model b/ppo_fix_continuous_action-835000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1b6c26458653af75658668d3316f097bec1b280b Binary files /dev/null and b/ppo_fix_continuous_action-835000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-840000.cleanrl_model b/ppo_fix_continuous_action-840000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..90333e7b257554d1ddcac87c568b5f07d16b8bd6 Binary files /dev/null and b/ppo_fix_continuous_action-840000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-845000.cleanrl_model b/ppo_fix_continuous_action-845000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..bf3ce12d32dd087920e081dc6eed37cd96fc9fc7 Binary files /dev/null and b/ppo_fix_continuous_action-845000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-85000.cleanrl_model b/ppo_fix_continuous_action-85000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..dbe5e7e971d25a9532694700932b9f9f5dc0ed50 Binary files /dev/null and b/ppo_fix_continuous_action-85000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-850000.cleanrl_model b/ppo_fix_continuous_action-850000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..70073bb757ea98220eb602be420a658cc8cfc66c Binary files /dev/null and b/ppo_fix_continuous_action-850000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-855000.cleanrl_model b/ppo_fix_continuous_action-855000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..863895916556f97bdb04510e5ec870c04a9450bb Binary files /dev/null and b/ppo_fix_continuous_action-855000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-860000.cleanrl_model b/ppo_fix_continuous_action-860000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..46048c7999ea8fc75314a4cbb36186c6b7b2e380 Binary files /dev/null and b/ppo_fix_continuous_action-860000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-865000.cleanrl_model b/ppo_fix_continuous_action-865000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..7b72219d4020bf0de8cda2e44b21df814dd8fc71 Binary files /dev/null and b/ppo_fix_continuous_action-865000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-870000.cleanrl_model b/ppo_fix_continuous_action-870000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..b3dc3ebcb4bb7c2fb2c69a30dd04b7d0c4dbe344 Binary files /dev/null and b/ppo_fix_continuous_action-870000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-875000.cleanrl_model b/ppo_fix_continuous_action-875000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c12925e39c0838eddc87a5163fd5501b7ace961a Binary files /dev/null and b/ppo_fix_continuous_action-875000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-880000.cleanrl_model b/ppo_fix_continuous_action-880000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c6f1920cdae25e7f2283baca63873cccab26950a Binary files /dev/null and b/ppo_fix_continuous_action-880000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-885000.cleanrl_model b/ppo_fix_continuous_action-885000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2c7899140898b7c0c4808e4136e0b735c1695638 Binary files /dev/null and b/ppo_fix_continuous_action-885000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-890000.cleanrl_model b/ppo_fix_continuous_action-890000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..a9dc53b521d9686fd8b2182e563dfdb3a1246b44 Binary files /dev/null and b/ppo_fix_continuous_action-890000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-895000.cleanrl_model b/ppo_fix_continuous_action-895000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ca72e45a99559be5a62fbe317ac3685e9b02202a Binary files /dev/null and b/ppo_fix_continuous_action-895000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-90000.cleanrl_model b/ppo_fix_continuous_action-90000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..d26cf1289c2156415b217626af57dbeee7c3f0e5 Binary files /dev/null and b/ppo_fix_continuous_action-90000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-900000.cleanrl_model b/ppo_fix_continuous_action-900000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..77c9e53e88207cc0c358c7b5cc87e2d7441a00d0 Binary files /dev/null and b/ppo_fix_continuous_action-900000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-905000.cleanrl_model b/ppo_fix_continuous_action-905000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..219530363ea05f82259ca35376dc4c54c010d8fb Binary files /dev/null and b/ppo_fix_continuous_action-905000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-910000.cleanrl_model b/ppo_fix_continuous_action-910000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e1174ed99294ba1a79c816f28e7a93af2e1a613a Binary files /dev/null and b/ppo_fix_continuous_action-910000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-915000.cleanrl_model b/ppo_fix_continuous_action-915000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c94bb3dd59b6e4f1f923a48011bb0821fca5ce32 Binary files /dev/null and b/ppo_fix_continuous_action-915000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-920000.cleanrl_model b/ppo_fix_continuous_action-920000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..02c50e289d9e675e1b8e900efaa4beeab07e9371 Binary files /dev/null and b/ppo_fix_continuous_action-920000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-925000.cleanrl_model b/ppo_fix_continuous_action-925000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..49ad49831d1c74094c30a78d58e98e78443b1fe4 Binary files /dev/null and b/ppo_fix_continuous_action-925000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-930000.cleanrl_model b/ppo_fix_continuous_action-930000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..002205c5eb208732a60ae364d6c3f7558d0eac58 Binary files /dev/null and b/ppo_fix_continuous_action-930000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-935000.cleanrl_model b/ppo_fix_continuous_action-935000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2728cd028412754fb796928227a1d12c822d3e18 Binary files /dev/null and b/ppo_fix_continuous_action-935000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-940000.cleanrl_model b/ppo_fix_continuous_action-940000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..6c3ab09ef0ea07eaf25f24fd190f74293cf05699 Binary files /dev/null and b/ppo_fix_continuous_action-940000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-945000.cleanrl_model b/ppo_fix_continuous_action-945000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..747ad837904aced46b13ef241bff5a8b375bf434 Binary files /dev/null and b/ppo_fix_continuous_action-945000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-95000.cleanrl_model b/ppo_fix_continuous_action-95000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..e2381a902cc94a8309f4d24dde31844c296bd1c1 Binary files /dev/null and b/ppo_fix_continuous_action-95000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-950000.cleanrl_model b/ppo_fix_continuous_action-950000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c2a63659103c1fb135339f0851dfcab27eb11d4c Binary files /dev/null and b/ppo_fix_continuous_action-950000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-955000.cleanrl_model b/ppo_fix_continuous_action-955000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1950dff406360fd4f1959f8cc32519961b85f84f Binary files /dev/null and b/ppo_fix_continuous_action-955000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-960000.cleanrl_model b/ppo_fix_continuous_action-960000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..5b2cd161b92e7bec095b94f0e13b06301bfab498 Binary files /dev/null and b/ppo_fix_continuous_action-960000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-965000.cleanrl_model b/ppo_fix_continuous_action-965000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..cc75f7d5784c2067f0207bfdae3d74960fa04e77 Binary files /dev/null and b/ppo_fix_continuous_action-965000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-970000.cleanrl_model b/ppo_fix_continuous_action-970000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..0258cc4ab2a8ddd16888b34528bc0b56f88f7f8f Binary files /dev/null and b/ppo_fix_continuous_action-970000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-975000.cleanrl_model b/ppo_fix_continuous_action-975000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..1ecbb231e5479b326c8e89b019bc0cebab42c5b5 Binary files /dev/null and b/ppo_fix_continuous_action-975000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-980000.cleanrl_model b/ppo_fix_continuous_action-980000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..90f528a40026be5d7fc39d4706f70799e18d3009 Binary files /dev/null and b/ppo_fix_continuous_action-980000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-985000.cleanrl_model b/ppo_fix_continuous_action-985000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..2efc99dfa0e8c3a2f6441e168b67e82f3ca16df1 Binary files /dev/null and b/ppo_fix_continuous_action-985000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-990000.cleanrl_model b/ppo_fix_continuous_action-990000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..361746ea441e27702d5c0443a6571863b90442ec Binary files /dev/null and b/ppo_fix_continuous_action-990000.cleanrl_model differ diff --git a/ppo_fix_continuous_action-995000.cleanrl_model b/ppo_fix_continuous_action-995000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..9d1d0a447ce33c5ccaeccb8f248bfde2eea6bdc9 Binary files /dev/null and b/ppo_fix_continuous_action-995000.cleanrl_model differ diff --git a/ppo_fix_continuous_action.cleanrl_model b/ppo_fix_continuous_action.cleanrl_model index b965e2f45387fd1143bcd63b984b3d3e031e28d9..551c8205f24fd67ba8cdbbd57edb3191de777a58 100644 Binary files a/ppo_fix_continuous_action.cleanrl_model and b/ppo_fix_continuous_action.cleanrl_model differ diff --git a/ppo_fix_continuous_action.py b/ppo_fix_continuous_action.py index f204e4e83e13f5da11c5e6e100efdc9b35ea4674..0d9b7c61f4d8f53a5f7c70e7065fa07fe9ad7a57 100644 --- a/ppo_fix_continuous_action.py +++ b/ppo_fix_continuous_action.py @@ -229,7 +229,7 @@ def evaluate( envs = gym.vector.SyncVectorEnv([make_env(env_id, 0, capture_video, run_name, agent.obs_rms)]) obs, _ = envs.reset() - episodic_returns = [] + episodic_returns, episodic_lengths = [], [] while len(episodic_returns) < eval_episodes: actions, _, _, _ = agent.get_action_and_value(torch.Tensor(obs).to(device)) next_obs, _, _, _, infos = envs.step(actions.cpu().numpy()) @@ -239,9 +239,10 @@ def evaluate( continue print(f"eval_episode={len(episodic_returns)}, episodic_return={info['episode']['r']}") episodic_returns += [info["episode"]["r"]] + episodic_lengths += [info["episode"]["l"]] obs = next_obs - return episodic_returns + return episodic_returns, episodic_lengths def make_env(env_id, idx, capture_video, run_name, gamma): @@ -436,6 +437,28 @@ if __name__ == "__main__": terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0] rewards[step][idx] += args.gamma * terminal_value + if global_step % (5000 // args.num_envs * args.num_envs) == 0: + obs_rms, return_rms = get_rms(envs.envs[0]) + agent.obs_rms = copy.deepcopy(get_rms(envs.envs[0])[0]) + model_path = f"runs/{run_name}/{args.exp_name}-{global_step}.cleanrl_model" + torch.save(agent.state_dict(), model_path) + print(f"model saved to {model_path}") + + episodic_returns, episodic_lengths = evaluate( + model_path, + make_eval_env, + args.env_id, + eval_episodes=3, + run_name=f"{run_name}-eval", + Model=Agent, + device=device, + capture_video=False, + ) + + print(episodic_returns, episodic_lengths) + writer.add_scalar("charts/eval/episodic_return", np.mean(episodic_returns), global_step) + writer.add_scalar("charts/eval/episodic_length", np.mean(episodic_lengths), global_step) + # Only print when at least 1 env is done if "final_info" not in infos: continue @@ -549,7 +572,7 @@ if __name__ == "__main__": torch.save(agent.state_dict(), model_path) print(f"model saved to {model_path}") - episodic_returns = evaluate( + episodic_returns, episodic_lengths = evaluate( model_path, make_eval_env, args.env_id, diff --git a/replay.mp4 b/replay.mp4 index c03652d7c444c5ddebaf5c63e97380d57326cd4c..f64fe7aadbc34f9977d0f5b94dfa4615501da449 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8925ae3b805d55df0e466a055ad06056ffcbbe556795b353340370247e6fb683 -size 279554 +oid sha256:b28a16e7d8608f0270fc8eb40f7a2e96605477257b3c14838299593259d6e2c5 +size 1174608 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-0.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-0.mp4 deleted file mode 100644 index e9a62346fc0a7566fc415eba50dfbf2801d81b9a..0000000000000000000000000000000000000000 --- a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-0.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:690cb6a7c92c13cc9bd6b6c4934e39e0fb024837609dfa6ea9ca0c7b73cd40f4 -size 1325646 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-1.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-1.mp4 deleted file mode 100644 index e4d312c60c01dd5918cca02075b2943d53cda6ac..0000000000000000000000000000000000000000 Binary files a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-1.mp4 and /dev/null differ diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-8.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-8.mp4 deleted file mode 100644 index 885acbdba7e05b632fce3e90bc0d441f3710d060..0000000000000000000000000000000000000000 Binary files a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705721020-eval/rl-video-episode-8.mp4 and /dev/null differ diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-0.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..05261809eb92e66de21489a6e6269aae5507ea03 Binary files /dev/null and b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-0.mp4 differ diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-1.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..46178e87c1053ee3a07197152d4932db5c108bc9 Binary files /dev/null and b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-1.mp4 differ diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-8.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f64fe7aadbc34f9977d0f5b94dfa4615501da449 --- /dev/null +++ b/videos/Walker2d-v4__ppo_fix_continuous_action__5__1705732437-eval/rl-video-episode-8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b28a16e7d8608f0270fc8eb40f7a2e96605477257b3c14838299593259d6e2c5 +size 1174608