diff --git a/.gitattributes b/.gitattributes index 3fe7db6c11538d0d6ecf4ca359b3d358ca1a8982..89570f94b1ed38dae668d292c4bc96beaa0a128f 100644 --- a/.gitattributes +++ b/.gitattributes @@ -43,3 +43,6 @@ videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1704463460-eval/rl-video-ep videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index b9603a35ecf54b8c7c52e7fb2c9b24aa1e7f6b10..aa2af958e0caa17de81d322fc806b1358b69290c 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ model-index: type: HalfCheetah-v4 metrics: - type: mean_reward - value: 1763.10 +/- 18.91 + value: 2463.90 +/- 832.71 name: mean_reward verified: false --- diff --git a/events.out.tfevents.1705702843.3090-172.2624987.0 b/events.out.tfevents.1705702843.3090-172.2624987.0 deleted file mode 100644 index 152e533e574bfb28cd65088308c6a23bd673fd1a..0000000000000000000000000000000000000000 --- a/events.out.tfevents.1705702843.3090-172.2624987.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a4f921e935bbfeef7fb76c2064b5bc4882c62be8b9e3150a9e9f73b0dcc1091 -size 376394 diff --git a/events.out.tfevents.1705726157.4090-171.2582066.0 b/events.out.tfevents.1705726157.4090-171.2582066.0 new file mode 100644 index 0000000000000000000000000000000000000000..9530d2d5c33556d6df2881c711ff742d2dfc0a5c --- /dev/null +++ b/events.out.tfevents.1705726157.4090-171.2582066.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d5da02d10bb0725d347168b97c1fdc55dfd6f7110ad5d1d097af696eef1d61 +size 403054 diff --git a/ppo_fix_continuous_action-10000.cleanrl_model b/ppo_fix_continuous_action-10000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..ee757ca4ea7fb307459def7112b047aa1c39eab1 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..4eb24f668bc7c4c0256617c290abf01fc68e8c72 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..b1bb5084e09f8f4e931b7642bd507049d736bc5e 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..5d006a23f93c3b3c2600fc557e52a6fd584572e7 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..fa140d14f1d92f655c27f0f760e2924d1e2434ac 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..bc753eff1fa2e9399e6f6afececcc5c465255ae2 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..200e00e487321896ba5f8a8c156256a08e50acf0 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..7fce39e9039c37c04668930dc09ef9fa80bf87c0 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..c800ee36e2e5581b906b2b9a650753f67d839fa2 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..fd3b344452872df177a24f189730916f17e0a90d 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..bc4fbd34f4fad4f2d7398643d4369e54ae7f9645 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..0e9161506b3726104b5db55e3aa0ffc0a4c21d58 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..db93d48fb931766f5633e53e55917283d0f69d4d 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..11a7120034c89288377fcaa5463e90760315cc26 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..d5685e444f4cb191f69d7cd5ac5ba3f17279faf3 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..0445f0a6b27d5c3d2a9bf56062d97d1ba599cef1 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..9ee4dae91077ccc7314738a62802f6314db8f6e2 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..c7b9252929a73956c9c675c12061adb3ebacae99 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..1b38425061749c4c1b30a0f1b9832a5b35c5bea5 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..721c732679cd7ced310d463d7d06705954fe18e7 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..4c2b35cf0e872aa12ae4f189a819ab67dcf81711 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..7aa20bfb8e5a2aec747b994baff7d63b1cfc9a3e 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..4a2a597a899e48a52114ee23fb1df504a9dfe4ab 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..2a41daa133e88b6ef28ed038a3d1cb94fa6a9415 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..0970e9768adb4fb7aec01272ec6b83a015ff712e 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..84d9c4f5c56ce645ec0cb3c369702ae96ca54445 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..dc6cab861b81824549df10308485b3a1edaa4b16 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..eda66d7fa54c14eee05c5918dc9120fdc4b4ae48 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..00f81f757402b196438fa7ceae2dc54766bd8e6c 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..b1322af1c876db6f6a6c463e7db444ec64cde698 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..8072ec795511064c1415dc6c186483545a64dc60 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..03ab1df1c1e742de78afee9f1120919f46586f07 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..449f95855c425f925f843ef71b94445dfe5412a5 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..decd8e5462369c158032dd42a189712ec5f2c8f4 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..f8f0d671c56602deaa1b35d72c4bacbaa361887e 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..7d468dcdf1c37bf3a42af5679d3b7453b7ec04c9 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..d636341fd622509ba709fd5582f054cd91dd6cb3 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..62d4b4721ab7082942c8b5010c1bc64f0bdd0802 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..c9251f0a8ba5d231ea50ab5cc195670e70ba1a57 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..166546e26f97f24589eaba2c558c4affce6627fb 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..120d104b88b89efdf7f7c3dbece6d662ee3f61d7 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..78b6685bc797d4714a076682685c51eb8dd93c7a 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..d6ce05dac75c5206bc936439b895bc51020605eb 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..19b644e6b7e84824520c6c8081c3a8979aae5f09 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..2e0d46ae146ea4165cee9ff44c66f3de1cd374a1 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..a9ee9b01315592ffda4fc0406a18651209a696ae 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..1ed2de7dc6b508527c923443b30cae57010f17a3 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..b8f19ea7fe4a18f518a2beac8f381195c9504197 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..6ea5c4809e6b61777825e17423cff8ffe8a9fb45 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..9ef0bbf9b0077a20a70d0b21306d2b1885c1240a 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..44fdc5c3d62b1e24036b227a53f8b37ce29378d3 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..8734a29ee88a43f91905dabb611a60f13d632c2b 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..8e2ff6a665db6a0601d1083bc5c0994d6e20d9eb 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..fdbad8fd73369644a3fe3f6b9d8d14f0327f40e5 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..6ef60055d8bce2f606f02168fa21af8dedf6469b 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..e36dacd9f32ded22aade37fb87d273e3be6f9f56 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..703f063a23d2f86a8d788b004139ce70ed7c4b82 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..b7280750aabbd3e1a1b69c3948db89b5af466300 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..955d267be8056ccad30015cca218d6a54792c119 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..54158436f0abb57e495b89c71e661f1ae1f354ad 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..f6ad75de3e3295df01c99a52316ab5644cbfcd89 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..480a6099771590c90057bb68436d1d3791ca5b6d 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..9ffc06ed6341eba76a0651fe18be9794fedaa386 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..d7c641398a260d67210c683f664652f67a32b9c5 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..c3fb7194770de983f5f617480b48cdb3d3119eee 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..502f0430f345ce9ec148264a9bc627b1e70a5747 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..39e76aa61b345065175bb185a9d2f978b7a5a781 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..34f13b594d04431b7061c32f2d46e65fbe3c6a84 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..6ba4cff869d34439495dcd4834fb7c576e02b757 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..dec90c2ef111516f477381961e084141754ef098 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..1a42e8b42c135704dc04b83a5bbe3b14aa58e830 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..581979b39a520261f2c2d1f261addde4d11ddbd0 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..87c27bbe1d2bea9d5749780aceb6b2fbb86e64fb 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..34e72a2b4b3418bb794de5f497b6e7d497d62b21 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..76f42a7552b20110cd69f4ddc4e65a543eb693f9 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..0e52ab7d0e0f328d60527899c124029ba73ec991 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..26be805a836d65d8992cab7bd90874553e1e4998 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..9e1dd179d6ce5c6fd242e2c5051e97d17b52bfeb 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..c0ac4cdd0319fe8dfcfa50b7ece42eaca8711174 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..220fd9a867e6cf70c0f1e81177a5077b06ba67e6 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..bad102d5cad67bf9c6f779a62b50f42859dac71d 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..12cfef1854edbe07e5cdded2b41fc36ed1daaefb 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..9ddaa87640e83a76f5be41e9a4eb5393d88d9997 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..41c96bd6b857b87b2209e3cde80d1ed651d4387d 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..1aba5b2ed68741d443df5ee97707b7f4f37209ed 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..bd5b7c4ed2e8ace8efe2343f7d138ddc84307cda 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..b6234e67a7ccb363c0283cf124ef4f4bc3555933 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..c733a64df613db15bcc56d798775de78a8c90aac 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..c9f570d4f9009e11f96101087bdbcf84ee05d403 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..8a0ca121fea1c387361b140d5e5bc1d81c56adb2 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..26b4c1301935b89eb1f5e5313a54d49111523e82 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..2c547df0e91d22dd3628222cf6b23f25cba5c186 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..a74f18e07b851dfd650262a61f805e0b91f04cf2 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..2ff4bf92249c22e4e69e6ed9e3daa84a711cecb0 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..b059e0c4d4e5cd729d9d6dedb22a9ae5b6e67bb9 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..7dfa5f0c15cb292eda555f75adf588407b31272a 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..6b310d3b563734e051989da98d5436d2f9f8e890 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..38ed7e8609b8bbd84580325a8fc7bcff03f1a6d0 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..ef8cd6eae11e5d7624e39f0987ef351b6fb12035 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..805ab6d9bf33fdb87ebd119657ad12185e592888 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..647349267caf3a72c3d6fe707c2366f4f3abd08e 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..5d3feff08fa015a428a75c1afea4cd43203cba77 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..5f7be40cb1ef3db931b6ac4de6653a60c58c11c9 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..33c281c8a28f2f8dec6e28a36fe341860ec5aef1 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..fcffd1e769cbc61cb0d03650bf318f1864fccc17 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..68796a50b3c3afeb18aa56a02df72e8ed5a2284b 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..cfe24b6cee6596d8c9b02c69729834ee17b193d4 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..131e2966f3e079f3b088731bdd9a805aba578785 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..0d872641b614d25189a697f00065a3e9c267166c 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..cc7a1ca9cefdafefcaa01fbe97c74459b1d12b8d 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..bf44db96a35bfe7a6df358d7d79652c56e106caf 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..1eb9c3fe5cbeb3df10ad5960611e4fd2a06fbd8c 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..1e1d1078a200d305cfd8f8393fa4578392367169 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..3fc5c12e858fcb3c56d4d31cd1dc33924923b827 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..a0eba7e4eca323ba99706c06f29ecff75eca7821 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..92ed9fe25ae010587b17ad01c3a88a311179f66b 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..491e3e5a640d02a7b11bc02f9a5985de97ebc845 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..1b5a8c5ae689c2ac65fb86b2f4f94030fc1b42a4 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..d67bf6ac6459603b1918dd61b7b4a173b1702e4a 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..03b1e162a4985b7b44d747faa7c8212e2b4860a2 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..2a92bc0e5bf809b93c65a52686a14217cad9e927 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..96bc7fd492c00bb2994d8583f4d998625350616b 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..ba2bde2b537e9707b124d199cba6039c96c075d7 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..45ec58de86f94f6e8a314ace6017868f869e3a37 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..2228785502bdd0b68db39bda0c9dc468c0d109b3 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..ff06cd69a9ec46a61d1ec401d20a5e8ea769c504 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..cb095a32a4901345f4f2d02b2e9a11ad86ffa9d3 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..c155609fa45a70874d3c7d6419acc9d51351c636 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..a509a02409f2b88f87b5ea875c4840009a79ff48 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..81632c9b022b6f5694bb46423c484dcdf26a3813 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..ae689318167552b2e50bcdb68a97eb201951d8e9 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..2972a49bae373b33de7507c46d4edaa1aae50937 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..409c748719e7c338c73447a27a45ebc80db3fdb4 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..77aeed48c3975149ba5974e29efd1c81f6c2a554 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..87ddf490a31422b35ff983a869537251c702227c 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..aa506bdd159cdba026ca8043ca651c55a5e43bef 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..e1f6d2fec54743f454c8d9b4095ba92099e41075 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..f86673f48d309e5f01a4a4f251db72041e4671cd 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..5284fb2072475286145acca7a4303b423dd4dbce 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..8ab87183e7fb5e08e7d82237b2c603cf7e73f631 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..e7e3c392fbd6e02dba4903f95d024834668d4e39 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..da4cb5f66ddb7a067a375de53557c713934c3b8b 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..dec2935c79c798bc022e8a6791e37d129e3a11d4 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..96fc35e6c16b6410ce5df4763841f52483730955 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..ccbb759353d7781b1b02c874500f017946ed3c8e 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..21472b3bf05b9cab08f0212c996212922deb1a75 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..4f09823fb09e83aaaac1675a8fefabb399aca2e0 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..c49c975262e02e5f5c75fae7706182c18e83b9c4 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..911877ddbe4fc711583fea8208c476dc1d44f8b0 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..1fde368a0eb863f201876e9803314eb2a56cb838 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..f9cd070758f13e2c7084bea88e98bf1290a70af1 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..cc50c1f7df819752ccbcbcadde632e9ed3518e7f 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..f42f90089f2566430da57730e1d7bcb249a9d49f 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..651e930dc978e04ee84a07e2eea1736ff1a10be4 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..4f8d69b5ef4c3fdf52b47ea904079b95bd67e8f8 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..73ffba48da07db2698ad22eabda4be40f338bdc1 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..d778affc3fe93ec28d6e8d75fb1eef5de5022200 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..7c4bccb205eea80cc385d12ef1189b26d8978e0b 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..5d6882d84d519c87664e5a54afb962580119570b 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..03c239a7b4d63cf4416de2dbe5b636ce27a59998 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..7272aefa1612cbdfebc8a0f3abc3bd011601b01c 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..8c1fd8ff122b7f3b25c1c132fa3fcf6e114c1eb7 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..10b6c5ab52d3e9550a4c1c038cbc3bd0dfd836f6 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..7fa2e20bb576047178148a92b1d6f5355620376d 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..15b8844b26da6cf385256d3b20ded8a84f39c986 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..4023f0023c0214ae3a42c5c20164c9644744f185 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..903de3af2166b76554a467635ce33d0389efc573 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..200fd5e91904b5ff6ac9988007b1e26432215b81 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..f59f53a42347c1bfe1447ddaa93315299b306ff5 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..6f0eabd9dff74c2b401be004c578559eb1dd7f49 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..8bef4f879533274159529612d865ea124b9dc677 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..c0e6535cf9d051e491dbf82bf92e0a7fcda4acaa 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..cdb9e0f41498d737f7df69e695f98abc085d5d8a 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..faa3e630716e71785c721098159bfa522858ef61 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..025f23fd91283ab5172812b0f090b03d4fdbff86 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..e79fd7e57a5f34e2d969e96f1976b445160eb541 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..c6280c72ff11deffcf14f3e561ad727612fea340 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..83fd56dcdbb3765ae1db86349d6b6ae8db831175 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..d25496c47d6290a041deda0ea70e528649a8c226 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..c3714bd7f433f758d23d961597542dbbe778eb30 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..655141b967708c72a8c3820131f417bd4128ddf3 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..8e492b2f02fe7db5e4d9c03d9c7ede1c48025ce4 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..4f4dbf8bf5b12f7a86cce0724c51e9f7f4d96ada 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..69a6e8177d1aba34b33b9834c813489010ac95ec 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..a5d72af088552d416d58b4c941cbb904e8da6bba 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..06efdfb0a387561ad36f5c5aa1f54d7ab89384d6 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..3309ec6ba3f29522ee29b4486c67734644ab63bc 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..5dfdb82ee9a54c43132ccbeacfd9e6b4be5fc7d3 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..41460b22d89ccc54ccd8eec1a481d7c7dd01eeea 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..d9ec015bd4dd5edb9cc964d1eaabfb2fbf54ef33 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..5f08af47e645f8f20d61d53022a6dfce949faf31 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..711798af5686bc7ff8838689056cdd2f0be1c5e0 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..43c2ac2cb825079c3ba17cb8c7e84236fda9573a 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..e133c691fc76d9e25ece0e5fc8bc3fad898028bb 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..218a25c83c97f0d0ee20fdf9022fe56515d59e63 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..fbf318971492b2778252346f4376aa4992e91389 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..24d2114319500bfa7fb0dfc3ce8e177eeae293ec 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..b759f234ec0ec31cee6eb527dc17fa519dc3266e 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..1710ea4a99cf6c5acacb2d8aad7fb7c6957fee88 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 80b45d33583c44975394ee384f8d673e08ac0f8c..b72fd7487ebc0c7d68556d571cb5f7742d567b43 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 32b6ac5fa8a8926a56357ccaab4d71166779952d..e5a588527ff290bf5084b297de64bd870be2d356 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:adbdf4ed5e8f728c885b686d4b79b6c5fcc6ec8ab9f43fafcfa7f780fc7a1f42 -size 2207656 +oid sha256:3e87025ccde01c4a25243c6ed9d7aef5602d43fda0d5738889ef12b35831c017 +size 1766304 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-0.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-0.mp4 deleted file mode 100644 index 62fe5d96a9f68875f6be342070ab2b46b77663cc..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-0.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c28c729d9b7c3d529be88124be138d1fc7eabf41a77025be85bbf9fc2f9bb00 -size 2255078 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-1.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-1.mp4 deleted file mode 100644 index f871a35d4c6ec755440819658ec70e722b8bfbe7..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-1.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8d814156c7021c403c94877eeb0891f75268f42d1e21eb5704934f282961cf5c -size 2226897 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-8.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-8.mp4 deleted file mode 100644 index 32b6ac5fa8a8926a56357ccaab4d71166779952d..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705702836-eval/rl-video-episode-8.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:adbdf4ed5e8f728c885b686d4b79b6c5fcc6ec8ab9f43fafcfa7f780fc7a1f42 -size 2207656 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-0.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..b66c67e7feb9886d694609a140c98971a7ab0c3c --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e53457d7212a2c8c06597df752ab11a4e90f89a4867aa3d94f88979445572ff +size 1860308 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-1.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..0ff5ca8f871acdecf2c5a0e94299f9eb63a8c995 --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5399949d4426e86a25784446948266bd72053a0f2e6606acce9de58bb1e38e4d +size 1828491 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-8.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..e5a588527ff290bf5084b297de64bd870be2d356 --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__4__1705726140-eval/rl-video-episode-8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e87025ccde01c4a25243c6ed9d7aef5602d43fda0d5738889ef12b35831c017 +size 1766304