diff --git a/.gitattributes b/.gitattributes index 1107a0aedcc7e51d5c034a18bd69df1d4f57a3b6..c832425bcf7ef50369d45ae9c66b44678089cb91 100644 --- a/.gitattributes +++ b/.gitattributes @@ -45,3 +45,6 @@ videos/Walker2d-v4__ppo_fix_continuous_action__3__1704498496-eval/rl-video-episo videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text +videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index a97fa794a63055b1464f42d24d2a8e67b37514cf..85951f11a6e28c2d58145d6ed924a5e2aa5744a8 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ model-index: type: Walker2d-v4 metrics: - type: mean_reward - value: 3846.11 +/- 1428.36 + value: 4226.01 +/- 769.18 name: mean_reward verified: false --- diff --git a/events.out.tfevents.1705694963.3090-172.2566081.0 b/events.out.tfevents.1705694963.3090-172.2566081.0 deleted file mode 100644 index d5bc73ce2047fdf21b58fddbaa925845b6204d82..0000000000000000000000000000000000000000 --- a/events.out.tfevents.1705694963.3090-172.2566081.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5605694337b97bd8662283f8eec6162c80eca6bd603c6892339911049cf9aade -size 600311 diff --git a/events.out.tfevents.1705732309.4090-171.2642765.0 b/events.out.tfevents.1705732309.4090-171.2642765.0 new file mode 100644 index 0000000000000000000000000000000000000000..5206d4cdd2c06778a89693f4609cb6a4b793b6e3 --- /dev/null +++ b/events.out.tfevents.1705732309.4090-171.2642765.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74852eb467ee383fb6e8c7b7edc1d649bc494b70c6e97135ff014ca402daa197 +size 688879 diff --git a/ppo_fix_continuous_action-10000.cleanrl_model b/ppo_fix_continuous_action-10000.cleanrl_model new file mode 100644 index 0000000000000000000000000000000000000000..c343027871e181cdbe959fa56531b8c142ffb46f 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..7dc38a3f89ce411bb5ff536d9a05b89cb4bcf44e 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..11f66da902e746a8e91028c35451f4d184784e1b 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..5301c4b4104658925a09fa26391aefd77f67378a 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..2d69173ef71edebcb81c72d7b70edcbc7c18518f 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..50ce60471d132118f48395dff273b1d77e36db17 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..ed15b028bfab4d2eac076153d7424887289ed74f 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..d01eb0a9898fd29a07023b0e5b1440aaa663995f 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..4cb62a18905a6875cfd1a4e99afc952cb982c918 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..f147b6332dd7d1d87f97386a0dea021268544deb 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..9c4a54a27297ed571b8f2e74a87e1d2f10ad6916 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..5b9bcce63d3d753f411bdd4a7ffb36e59e8a4c15 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..b4c7809de28ac0345abbf307bc2727553687f6a1 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..d03e54caeac984fb3263dbad3ba7aecccea92f5a 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..abd01505fa4db4ac18abe78d1c8fa4c7253c68ae 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..9eabfa53c7244e870029efd65b1b5721366c21b6 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..5d2660376629dce61694a3a44f7431e9573cbf73 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..73d161428ab65167b15a24274adf8c4000b8089b 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..8248d431e4a1cecbcd31e27ddd24a8fa1b2345bf 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..d00612a1b9ad730b0a1e425739be08d15523c8bb 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..c0e33a9d650d2dfbe2136e61e62faf9a174ae40b 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..9ea6b908b013b0a133576aa48f5fb1b5c01ffc78 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..1cbde48e53f64fad39ca6bce5c92c69a2d790ffa 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..c4a5cf2bcbd674a10845589f207d6b7b60ba1649 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..a31812e3528a114e461924e8ae92f64b9d3f1664 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..efd462a3ee655803d88ec35a18e93fb053c7c90a 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..b3c4548218447212a49306294d1915db8a8e0ffe 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..4501031cc05b58212ec4ab1cd1a94cb228baf8fa 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..4ff7f6b9befe6e43a41f39c2fff314ac8d35f255 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..582c130d91459ff8ca615a92c6de4922539e0677 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..e93e05ca8619c0f3ba396ef9f1a9a816b1f78bac 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..deab6e2e35a2c15d5f9efec353f68698fc0e0ff7 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..ff4bb6a80ea853dbaf502b1fca1b125674af4aa5 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..ad2cea0ea311b4102c3d3b93c0b2fcf61cf013ab 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..13c6ddd31c68efaa721556357cb6a1c3c15fa9b9 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..e569aa15ef30b3b38bb25475e95b3ad3dc2997d3 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..089ea2836f897b1d48591828bb7a02e04468deac 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..34a821988f371c9c039da726c4bf12b0b6655e44 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..e4dc0938dd0874f2a4d2b4f0fad7898201027339 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..e116fc60ca8b6b4fa4f72ab63271c40d6c223098 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..cd6ac4aad92cb1e2ba41ee00bf63bf3ea0ea3c29 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..1baf106fffc75bfaf7ecc518047b44b8f3e48bd1 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..4b498afb0359f9b664f4d0a56cbe4882c39d7c0a 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..edc7421212e0ad4133a91d077e42587826528da1 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..0efdcd144b18625d57035ab84d769fd8da19308e 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..4344206b79a6c52f09cc455dcb2f9f6e1a720e65 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..422e5397e6f34138c4591d50800e1088e5ea09fb 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..08cf7970601b8017aeeb2f876fc1e3fe3b8bd649 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..6881820f41f77c060e51ea4bc77f02418544336f 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..dac7bd96664356443e661a5ca42533eecd74e7ee 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..6f93357b61476214ea020a18e97ec6ff54f9ff62 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..f251ae8b7e002fd350012a966f4a7141f358c239 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..d22b771be61f4dcf6d7f02873a80ec2b115b636e 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..1657b00ac429abb42d2aefd8402b197a4dee121d 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..44f53681461611fb5d5f4b984986483da6b07fdb 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..1be905d682732279887e4c2ff3f1cba2b24ea26f 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..73547afc3473000eaa7c6956a8404d8d2fd920df 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..0fd4874850564ff953b431f460771757ec6fa2b2 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..7bea275451810e7fd3fad27f5db3c98795c396fd 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..75ca941b5a0446bdf638cfa2d0e00d234e89e633 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..be3b3757e78a024c6a36392daebfbd2e59c348ba 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..659db0712e21f9be08a0c0c7a7f7c14b59498894 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..44b4b4a28f0ebbb0ae5553e9a20113a9eaa952ad 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..8b475c3056ed1881ecd780121f47931759cd56ad 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..826f4be0e7834b57a9529716d6b932026e8ec9d6 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..2db989274c88b083dd2f4dfbbc2a74d929859902 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..e8acf3f25d38ce3b0c81e518d13c550a4609b1f7 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..0e2b719c6d62ed4f9d8871049b5e03ceb6013efb 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..046e8c3ec1b55c0c6635763bd78dc109c25bfcb2 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..2be332bb952baa86dcddcdcf85497b1b6946902a 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..fd8f0820eca5332a16d69c437882a559df3c1538 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..42ff45873ec77571c62feea3b4b434310883edef 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..106f5a488b424f3fee6ca05b37a97d187b609280 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..5029435143fb0d175e17f77ef1e51ef16a940c71 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..3cc4c0f5925de7b3206adfb5c0d9420a3df2104d 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..75cd33de457196c5fd2eab7cc6fc8355f3052b1d 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..6645815ab857036b5259874af69e4fdb90089242 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..640f6284a78c5fed5616d58921be8db07cc32316 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..1b084b5ec6080fc8bea2717867a4f10a72205152 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..e79d411fa9bdc2fd85f378f797b2da3cc62320c3 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..84fb4e9a3839397505b8c8383eb9a1e7a1fc6da0 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..c9ab5c442a515c8502e4ad326f105034bf4f18f7 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..72decec08ae5e6e71930966f1b4f0c8dae7e0a66 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..b3687e1aae4ad511dd96d07fba350d1ab55ddf72 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..60841fdf659278f113e38cb38f26c91c07092e78 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..54647c4ad6a325c943f2f13d0e4308a32ccbfdf1 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..156ddb92b40ae5573bfc651ecba7941f725ee154 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..a902706b9076ddc94e23e3401f0f3182aff39445 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..c7539e1642be9d7470392ed52329a485b189c799 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..00f7a4256435f1984de3108178a109a5595cbc70 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..0677606d97ccc7b070a7ea863768650278f2b91b 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..c244998969c080ee46bb84243269d1354544a138 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..c592f87b7e4fb1030514af12ea03a4555b841784 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..ce43aa6337fffdfd5928ea4f5d759e7bbc0cb7eb 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..9821af16c09c695cd60f05916324e539a5f3ba76 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..247389aaacc6eec08a3c277705c44a285048fe53 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..c3c21c824d4907a26f9b75592e4392384dd3d564 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..96b2c721f68e56208dab218830545350571ea006 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..ad9b0766e9a433156d5e0a4e8c544f48dd35f91f 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..bd8a6d9d0fcb4af121d7130d9855c70ed6e89a15 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..161343d163b0d472e4d5548475e151d25a6f4810 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..001f0b4bddcfb5cb1ce2a7488769b5379a52fb13 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..0e64302d970bb8c907410af6698707eb50a2a50a 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..74016442afd17382d8067f0ab7061e54cfe64849 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..fd58bcc07f68387011e30d3d5d33482f884c35f2 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..ea53a1c3bdd2af97705c81f112886a696054fffa 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..6908a85b4b38559b31446309641aeffae8ef84d8 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..e7978986beeb7087cd95a76b35e94228af796ebb 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..18da1db54804739bc2647e46a287aa429d016fd9 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..81cdd6ab227558d9cbaf612318ad7ac25e6b0f52 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..a4c78ee86913d37a827a57f80feb4ec8425ed03d 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..b6cc85541fc33dee71fba275ff79e56ee5ab02dd 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..4d48670c4fe5b4cab6e71f24eecb147db896de1d 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..38da9bcaae1c676ec2aa656a2c55177337933507 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..66137edea609db0fad2a0bc3816250ba3baa5a03 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..90114934cf010fc57ae4d6d9188771816be48c97 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..1df3138bde5213fd3ff25030c5f3cb80e5e1473c 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..0bf0b345bbe61e42c64ddc064ae664de529ee74d 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..47cf7902fe2c6318b29e0c4143009fe01b6d9aaa 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..f76f8fdd3a5d0829bd8894de82cda988f1fab934 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..21887f65dba76988443011c925b3de7db63de175 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..fcf023b1720b03add52639b0068e1101d29ffd2b 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..7113e2fd7de5134659dd005128d7e79501cad320 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..1933577e86f511fb54461dc6b3fc21d7b94b0fd5 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..a70bcdaaafb79689872418b573ba3d211bb6b498 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..aa787a068a6a775db6c07a5142b2deb34b2d37a2 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..e1a70845bc0db525288732a4a86501016e0ea187 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..783ab03acd177e64220a39cb635c865dae3e916b 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..f13ea33e522dc8b1c5f7151ebdda545b7012daf2 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..3b9beeb6e4622fc4ed23dfd510687f6a94014e32 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..7c52a1dc9a2c694e27846e26860d6340d26e7d0c 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..bdd19735295b6ba80ca3476acabc290b20f101a4 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..a88880df3ad459933e15397e4e6b2857c6ea49bf 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..13e9a32fa9173cabfe83bdd069992bfa0da00d23 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..616ff08e51151ecd308035242388eddc4f299fe9 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..d68a01fd5fb3defbbb919607c1a84230061d954f 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..8e38539aa7c929cd57dfc181cb50d02afc40f329 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..9c9e9306947cbd31ecbbb8a350a7b9486847660a 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..5bb4f9e4487cc902887882403b7652f05c804ace 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..3cadd8cbc43ef996814e502f71c3b59667929587 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..5ae350769728662e25c9ceab83b73d97aa4022fd 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..6d286e5238cf52312286c4349aa79afd007ca65a 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..4a1c7b2072ff8db2e204fc57d0e1afd7126b7026 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..ddad7b015866ce8c3a4ec7b121a9d47c18293f60 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..fa0b78f9d5f6226ff9fc161b3fcf6cb8936b0a42 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..b38cfcd06377808b7418f7919004c5e8ab0ed600 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..c5e0b2d07086cb003260cd98a58cf596b29f9553 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..ae7143cffd0e6069378f5c8109682109381d9f8a 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..bfca166b4c37849adc0266629b2f9fcffa2b639b 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..92e158ff58a780e40d0561ace6dc32fcc515982e 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..e5309624053bb315f8734c2e3076cb68b5e69e63 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..1e95d2b0951b795cadb11e93722da4ae17aa828d 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..5fd2afbbdf21094467917d1596a95df5b9a3e3e8 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..0b58fba2677d2af0343cdc86e48d9838fc4fa086 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..0fe45ffb12ccd790b0767bb8f38835a0b1e5732b 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..e8f0d6dc1f08956db36f393b85b5356194c51925 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..de07be732625d2a3954d29224e7d27f57b608706 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..f8d5737e961498a6159d5c26f03ddec5834d1558 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..07aed8409cfd5a641e7b3e32cca72cf417964597 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..bef0b41a481ef519d21ef8fe13004647df727d2b 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..0bc5331b71f7315fb5ad7ed85a5d3031def5ba24 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..a7920c00ba243ecb4143695a61af387b83452231 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..ff93a8f93c68bd59468f4f50f83d173a19ed6b1a 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..5c031f396efb066fa228e8d728ca59452566f198 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..e63e60103b8a11eb9ec027c7c05a22d56f3ae817 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..bf8bc9a96724eabcba3cdcfd4182e790c2a1f63f 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..e8d0e533866d431041b017af5dd2419b65184afe 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..d2edcd12ea07c43bead4ddd958e2348e60785ef4 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..c9c17c4cbd3474786d6acf7420001ee4691b6cb3 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..a291c1e0f86b145bb3faf5eec0143c5b985618ae 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..68039ae9526482c9b6612270370a231a46d06d32 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..3f843c80a1453dbab22fe4dd59fa909683b1277e 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..57d1f8ae07f7137d76c0a92387010b2f1f4f97c5 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..be50562cbd108bbcba5c037ace49d859b9f9f3a1 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..022e2f72f7df8124d79d3765afd7d4bd2264fc19 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..53d3bc9d9a3666e41116a2eaeaee281a87f6a4b9 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..8fae74d3285ce347ddf4b64b2510cf3770349f7d 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..ca11b4a3e380e5a7dcd43ab9f7378960a404d067 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..333d6dcc532eb101a3fee88cddf974eed9e51565 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..1ffd01b487ccf58598a91cc21780292eec84eaa5 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..dd4e608b4fac4fc3b7a04ed08d5f87a5d5900d88 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..3e44f40e73c0d516c77937b8819d4ae2c4caacb4 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..9464cfe4cd5d764737a31a05a93343fac8dcd8e3 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..15704da669bd3bb2a1863ae57fb8153b6f30e9dc 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..25656e5ea35c57fe12f1056c55ac1dfeb757e913 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..446403abe0074490b4c90445ae0c2d2d834323f7 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..2ba9a666beca8208ec1ee6696057bc61145d2790 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..b6d560abe4ca679f85606e763fca86ec14605811 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..f7b63d0d6ec9f3c4bd2c1ac83b52f5884528ff5d 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..e66afbbd2e891f84474b4e6fbcf1ca96c73c8608 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..43b0f0a7a3b7f4e7e5de5a4ede098f70f3ee6894 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..49c75e231931ab31414bde456e524c9dd7301b30 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..fe487615f38017b847dc95d7217c5c9b00035657 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..29ab7b27dd795c61023b9aad046519870be13716 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..609289f16f50fd2e05293a6a143aa8b86f145d2a 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..030878eb936c718c884da119b39c83968f9f5844 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..6c2f482933d0010eff830595d8769d319cef3d17 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..65ae8f6e6d198c2977a89ec9a50997aa95c4eef7 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..db010f95391874766d331db7c70b60eddf6884eb 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 ddd4f45377f6eed738aae24bc549a3bcf030419e..3bd61752a4ce61b9df9c0715ccfb8f3959cebbd4 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 ed97fe29dcbaced064eb9495714a623d9131bade..f1c2dcc6f92af1e8a574cc97df5b2d155ae17bb7 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c3d729383a2c97a2f571945ce3589c4db7f655894771c4ea7aec2d81eeb04227 -size 1319244 +oid sha256:82c0c376113f2290cb6b6dbdfb4a8cd632dfe638ff99e318c09b9353304e728c +size 1213684 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-0.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-0.mp4 deleted file mode 100644 index 8f694dbc03c4ac4d061886173d0ddc63a3f7bff0..0000000000000000000000000000000000000000 --- a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-0.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b71799d79372e5e8a3b34e5425644800b4a49983f16d9707c60f23ce901c7698 -size 1322864 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-1.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-1.mp4 deleted file mode 100644 index 918bc1f933406d84146143eec11be243ddfdca3c..0000000000000000000000000000000000000000 --- a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-1.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:81012edef0e16b6f26309daa2ff70c9b52ef39ef76e24b8950cf0b21954a83d1 -size 1277332 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-8.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-8.mp4 deleted file mode 100644 index ed97fe29dcbaced064eb9495714a623d9131bade..0000000000000000000000000000000000000000 --- a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705694952-eval/rl-video-episode-8.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c3d729383a2c97a2f571945ce3589c4db7f655894771c4ea7aec2d81eeb04227 -size 1319244 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-0.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..9dbad721d7d03157d73801df0d25128a5b50d257 --- /dev/null +++ b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966f701a814b6449e09b8bea906e4c4e943b7a61a6d2a00208bd9afdce779eab +size 1220197 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-1.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..07bee318c090e7f2a9af4e729b16398377f91b92 --- /dev/null +++ b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e53c6e98f4832095b784c7a76e7c5461ae7c0def2b154b84618e17d167a3393 +size 1235915 diff --git a/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-8.mp4 b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..f1c2dcc6f92af1e8a574cc97df5b2d155ae17bb7 --- /dev/null +++ b/videos/Walker2d-v4__ppo_fix_continuous_action__3__1705732290-eval/rl-video-episode-8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c0c376113f2290cb6b6dbdfb4a8cd632dfe638ff99e318c09b9353304e728c +size 1213684