diff --git a/.gitattributes b/.gitattributes index 78390a976143d4221c13d42ef9918eca3b2250af..55c649e395713d9e4a6d08ce8a697456e3f027f0 100644 --- a/.gitattributes +++ b/.gitattributes @@ -43,3 +43,6 @@ videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval/rl-video-ep videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text +videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 6f6bc572c8e064e68bce50e01a92fb32cb1f6663..7397ec187b6f278d320fa562d71e6f83f3c53c3b 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ model-index: type: HalfCheetah-v4 metrics: - type: mean_reward - value: 1608.34 +/- 18.25 + value: 1826.84 +/- 26.43 name: mean_reward verified: false --- diff --git a/events.out.tfevents.1705702908.3090-172.2625643.0 b/events.out.tfevents.1705702908.3090-172.2625643.0 deleted file mode 100644 index b8085825f785b440f4c0550c53b4a7df187cdaff..0000000000000000000000000000000000000000 --- a/events.out.tfevents.1705702908.3090-172.2625643.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ac8154f9904f7faab5bf6d0286864ce2711a01cc3eeb5c68efecb612fcd78e66 -size 376394 diff --git a/events.out.tfevents.1705726167.4090-171.2582067.0 b/events.out.tfevents.1705726167.4090-171.2582067.0 new file mode 100644 index 0000000000000000000000000000000000000000..3b46451a0f1ffdef4e525aa9517d5b8a33051ca5 --- /dev/null +++ b/events.out.tfevents.1705726167.4090-171.2582067.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661d0e15c25a3163487036cb96b93f4e05e5612515bc32d4ffe88f79bad167fe +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..a50a03fe692c310a6f2df179c971d3aea85e7cb9 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..12551879ac87560c7d43b7f3acd164431723370f 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..ffffa821e6924cb47eaed8fe8177c03b55cc2d3e 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..f792ec70611e295483c789f7d98b11dd82a80cda 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..d7a329f46fc6945a9472aaae9287a8fc1565efe3 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..7c8bdfb86e882f695e44e40993f19155e04f67dc 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..68b43daedf8757fb315f2eb16e8bb65d435a1780 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..8ea8dbf7676361637b66498aa685a491be8cc589 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..cb06fc0dc64288d4e4f677880cbaede36883be01 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..8f6cad2578e6d9b635491e7c99dcd7d50fd60b59 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..52a4e3915df34f03fb3f16d614dc48c8c584405a 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..fbd35e91faa23698301fe3a2ce169c286bb80ace 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..aac5e6a7254dc97d515bab07a290b9634cbf4312 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..433ab94281919be4d05573fa8c85c79a3ca48967 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..a41b12d2b04d76cabb9ae0829d8095671f93862d 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..7563f2dfa645d5439407449a669b3949f9a93fa7 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..b99d232f53aee6369c80d8e7b18cdcb46f7cddba 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..4eea09925b852cff71329c67984b5993cebb8b38 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..886352c32031fe2a1ded6d89379c74fa4f4a0aa0 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..8432e1dff7051d1dad45989af19c5f57f16064be 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..872713eb42ec3128721bd226130a10a6796edffd 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..408c5369845a08dd1b86a1b649818ef4f34a0b65 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..36f5030b0ba0b96c25bf317c9a113874a66f103e 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..44bcd7d98703582e3e2a2da1ea30ac98a76a5ba1 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..fc70dd5a9d521b4e6b5881cc96b40768abfbd43e 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..7c9a171e89016f18ac86e66ed0d0d0b44fd3ccfb 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..3f7b6d14729f3781b6098aa7b1250c8a5394f9fa 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..292bfcc68a87d0adaf1c8e090f719ae9dd5da742 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..3cc1b6636fc6f5fbb95fde2b69fc4c930d3f46d2 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..0716d32ae76316258da144f3ca07a4785494231c 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..4442f44f275bffc7e79a11381b652e836979e7a2 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..02dbd9f9aedf4c07633e43e7874ad88844335a8e 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..a9a5ce77dcc23268cb3ff0ae92fe9d610f2ab77a 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..e49775c32fb57f96f5b987f64372dfae17eb9bd7 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..d0c29207bcc9a6c8ef3a1615c4e732d40fa17068 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..feea116018ac7fb3e96bbfa7ee0c41db6a7d58d7 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..5b22da7274239e8def63da5dd0008d2cc1e5044a 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..32b8aea07aead1c4eb46a60fed625ea5f1f98a9a 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..f0bb0cd56ce276e86c020204d2c8cd584d2fa31f 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..abfe00d1bea5c7af6e553507439b2fbc7f9850c3 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..c0ca6d19fdcd1fdeac7be0a6a53a9e03af78389e 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..b92aca93ba74f6ad7d3ce4dd6843e294eeb0aa1c 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..509fc304904b1dc8fd837be14f710807f41a147b 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..7a3a8babd286ae982488340a95d3d41cd640da91 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..fb43698011cf37a8e61ee17d1d793ff3bc9d60d9 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..599ea7e1c2b74059797e7c1e3d886394ddcf84d6 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..65cb8756397aa553f5dfb4ca6aac1300adc165b0 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..d9791b505b8106899c39b788090d38757f83c703 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..1cf5fb73a57a8ff7342a8bd498d5cc675f3682af 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..a0672016097aea5c24ce02f3330454468eb12c9e 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..212092106e3485e9d9aa17e7131b6080ed8a17c5 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..c0ec3d47445a9d76ad655fd159669044a9af8c3e 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..95c1496f9111128455b94127d624d38919faa1f7 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..6d80d3febea787c3f443ff308740bbf2d1e7923e 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..05c02bc757d42bd43e465b111bc79b3e01cc62c6 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..452f827d7f6b3db4ecbdaa289d1270395b8f325f 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..a26107b37fcb00375a16682b983a2e586604464c 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..fc48e0c5fb5e6686bb0b7aaae1f679246a45d1ac 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..5d397298422fc3ca76185ffba6e7a120df153d45 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..7787da316f60a12fe3e1f07cd0e017cd91213a2f 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..0efd155ec6b3e6c7eef308df659d969a205caa9b 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..64d7bd20891e92a30b0724b0850999f7b3515edb 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..8f43eca618e7ef3d478a0a09d6c5c720fa276bfe 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..a1daab905313baefa02a3c6bde5d7766f9462449 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..13957a1f27fc82f75a4da5f1c3d56822663dd4bf 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..4047c3b9a8a3c49d5f08c55dbc59824cd77de683 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..29d750504f82adba5979c9ddbc2ab3ec2087ec35 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..0623c1886e11da593d5a2354275eebe0a9eeec45 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..f72aaadc1d2826e72ddc874d936cdb02a2faab76 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..fc7cad7b961cc38803def21c793b2f9b1f2cbb3a 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..918caa60e6de3773e3572ebb7bff56c25acf1dfe 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..07429d0773ec2d4d44469a55ed21b5621d26e42a 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..af1c1523602c7ccf365828d23a7d186de19d61a0 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..034a1d8234cb4fafc83ce4b00eb0053ec3c78fdc 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..be01199bab00c945d00ccee93f2989eb8a28e1d8 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..6423ca67c84593a2b9522d7ce76ed4204c08c648 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..85fcb3d57cca9d309cb73238fbba7b8a632b1871 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..bf7ef510c83fc1b17a70e249b4cac97f603c8879 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..bfc6763cb662d29cf5854fb617ef59dd43031f9a 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..41128d905dbdcedc1ff43c29c0df7aef64b92f8e 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..247e8528f222499b41cba4dee3e865eee9ee957e 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..df055a524fc56722cc09884694f59c9d8c850720 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..fa80e6d32a77f27d8684234d6d09fcefec5f9691 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..a14938a65ccb058195c93d6a7b0131475b113f9d 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..88f24d4184fcc3c3bbe1eba4de98d3a400634d6e 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..a0b22e7732da892f73635abfd05ac8fab97247ab 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..bf4a722605ac3095d5afbbe642d187d2ebe3ff29 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..e51c08a70e2e29d47645882e2e7667c3eb6e76c2 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..236f6aa9955b021afdaa53c66e713dd701fe1d82 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..376215ea56839ef843f044930e7b4aceb3ec49d5 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..99ff8525685c3dc97134f5eaf9d16f06aa81e9c7 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..659f8e9c8ee0a3f05cf9f8f5634bec1cc268f1a0 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..6cf311daade14fc74624b255e162f55f85fd7073 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..ee5934093a4fd16ba68f6751af7a80e7ddbce433 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..d6b9fac91ef1041994b418069fd5eb1765190aed 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..7fae96c8fcbe936fd8a338c47c9596f83ffaa0d4 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..ebb3f05d1915e7aa6e3e8990cb1ef192a22caf35 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..99329b9beb61cadb5047067bf47db5ff381185a4 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..d9b2dd31a3afd2035a1f34c8e20df1070d6eccfd 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..6c664a78e66fb2a8db192971a320e688506b7599 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..126a7ab614d232aaed58b4d19f170a46eaa838b3 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..81d1366e076d66ecbbd3cce0b1d0c6f61cccf54a 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..1b8e8860de15b84af9f580fcc89eb19742717de6 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..7eeacb01d21f5e533bd8e845402089413b4c712e 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..b6c366418dbd39d84a4a3fa6db4565a808c55dad 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..8974c20fbdb1a0b7330cbde9b6a85e0c9dbf0c44 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..6970dee0f4afe94bb484da0ee792afc000294286 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..1b523420294eab49a46b94e0ff2dd7c0f2bb0d37 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..e9f85040394a3a25612a5e8ec79afe7da10a0c17 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..09d7293bc03576454c6d6f2b0eb6257321b4fd6d 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..9974cb42c6e0598efd4eccfa83bd3a569a6ff013 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..552ad06c667017fc76398277a7daa53643d4086f 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..59f0e028e81e97fa3bc4217d14651930a0f90df4 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..619f1471c0ed04e7ce99b90e4acb7197b3a11eb4 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..9d70c8bc3cf2e23a033990e3b796760c6a27ab34 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..8c7dd9fdabd834b85a83d40a0e9125221f32dfde 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..af9e7d27f686422393830fdac2ba96193bd52648 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..4341dbae34ebb48d344dab68e22a271eafc6c439 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..1d5c249252efac8b17ffc210e0538c03b4a9eb73 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..76f7a5575666a201aa2d9e3588dc32f57a7822fa 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..cfce442ee062e5c5ff01c6763fc1fc9a54989c03 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..633daacdd098d01d9155d20bf095f5356396ae0c 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..92137dd5007d1552c63e18d85ff4eb5ba12b9842 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..c75d7729c0505ba73e8fa38a063bc8b2eea15b68 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..46bcc71980a6db7c7694047bb226c3eb4248b52b 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..c540b64da127e1dca64eb0f5f243f886c55e9e42 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..f755fbfe96389f0175ea9cf450e37c059a9180ad 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..9aaf5cc719b34aded3bc36273c4af142e77586ee 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..f0bd6ee01ba3a08e4c90bf57a44a0601a9e7fac2 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..f77c7b47d25249ac77609eb96f7877c8ead830be 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..0ac9902bd25c8752f68b8ca887d9ccccb2d423c2 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..09692f8ef370d57309aad1e256b8a85ab929e9bc 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..fa7b3cedf05fb3ad656711f5699a2f1de826ac44 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..49a720c9d48d901b7bbffe6ad5432a414b128e50 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..f838d872de1bb4d96648349a933368d2e504f6da 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..eb64d9dc4bc7575dd7094d8de188ca7c817e222c 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..1b50e05781f6bef1f59e75c1795b543d71db7388 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..a6bea126a38a8f8a6aae68a77f0d236d0ba667aa 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..27040876f4b01d99fdf512304befc848b6e687c8 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..260ca1e78b07994221172035f09c253fe12f2f95 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..f6dc263fdcefdc94308e087664d3850f521b1895 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..9888614259f75de9068a2a3dbae6c641831e83c5 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..cb2073b1942dcc170c7bac5f77bfead41b83afc3 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..683a11d09349ad6fb0deb66df231e3891e70e9b4 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..cb40ddcc6fe3506ca323603b6d71db089afa0546 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..98d64872f45ae4107856a8ccfa5140f371c06183 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..051b58ea98a7b302c6d906fc3b19974178c97149 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..7dd5fcdea3946fe047347acb579eefd3365b969b 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..45dbecae3e1f278cce4e18c8f604ddd7008023bd 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..2a2be07d02f97cd0295d43dbdc45a34b0a5845af 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..fe03338655d18a58e8b904d5f6681cd6452b7a0c 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..d7f1e3ee88c877d22cf10ac0738226dd23a50b98 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..c944b50f8288398f4b76125c585a1db2a8c04318 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..232f6c8e1bfca24b9fcb4838e1b9612ffd122f2b 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..f6540cf0649b926420b8a29d4103a4b97556174f 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..65bb790a74c843d1008c947ef57beb23b638d902 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..8e71fd47a5e10b56bbcbd29dd1b780c0bb453092 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..4e231b52e357d71658e3374b1c442c5422dce36e 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..ae200b099d761ab12f17ffe1ec871a32621266fb 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..f70de523ca120e462f46402b8f7245b6514c874d 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..8a703af4555aae58cf77e6b8379e801245ad0c5f 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..4ed67172225fa57ae17769e916d74a01ef136a6c 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..8fc852de6a7d33e84508c56f64d7ee5da1715a8c 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..6012410fbc0bd8f23c01f25b17daca6a0b3fc207 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..f2392900fbb9da357b1e30bdf0aeff4e55fe0af4 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..53c9b0589381365ce472055035f7fdeb5f0f06d4 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..6cbcadce9266834b28f5a2ba365c1e63b794595c 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..97b158c20be5177cc2fec128274b2c2033919c2e 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..6f26faa85922d411c4ab28b76b2191abd903b9e9 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..6afa460455ddaba77ab3fa1abccb608c7d22984f 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..a5a3e0615370ea956ccb4ed5f9fa53a7c10aa1c6 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..237c0d1a72fdca8e848e44525528e3752599deb5 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..3c4af7329ca03e084a67321a69fea112afba07a4 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..8bf6f24b3ade13b86b0f93709d572a2aaadb3c6e 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..9faf190b1fbb0777c9a5e6fff71b4189b649a4f6 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..8bcabff9d4ffb9f810ea0d8c3c699e7abde46f98 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..8daed6e4009a352ab4658a5bf22351dc029f712b 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..4ee18f1a46e446d3b7b8242c5beed87442ed326f 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..774f35f9cc927c78084047e9907380672da4764f 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..273971a910dfcc3639746384f707d2cadbbcd354 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..39739bec3337ba15754644da56c352565fb027b1 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..b9785dc7437f43881648e21589cb548f6f517ade 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..234fc3fa8ac32a39e54e416513cbfa2aa42ef776 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..77d51a32da41909115da3e189f910f8589e78add 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..f818a5129d276b5e0a19bb308203e9902ce72771 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..6b70d59deeec4c951d8c1f7afc49443a4483525d 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..f2a8f3780bdc60779d60f636502adb048bd52baf 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..1fd306ec45da6808252e568e37f5b6d93f64897b 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..410a2df7df611ffc9905e07eb57b5963394f3d52 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..09a62afade8df59593cdcb061a4dd9b755fefa7e 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..3fbc767577f94a51e32b7f1eba8ee05a0bfeb127 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..b597f42052bc756d4e6031bdd68f7b06a2f866e3 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..2fff1c77a2efdf94711001626078023786b721f3 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..a7bfed8ca4adc2a77f7aac8ecabc9519951f7a87 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..a454f3c75a2e02cced841cd6c173eaf8b90822c0 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..218fec896d915ac97840140e8053b27e775cb48b 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..cc4af75dd80cfad993ca54cb720abcb83c35d699 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..5b9b1daed5dd47d9b3539b469bb13db29a0f5735 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..06192d0ab7c1089133157b2e6ada6d9fe300bff5 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 f270ac1edaa02495fec840d7b6565ce4fab3da21..019673e81ed818309e71b8e53e072e03c31a1995 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 eb57e0dca31b06ae5261a0ca9663bfdd22fff483..5f3797f8fc09e223c9eaf150474f59d71f46d7c2 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4072ae9c1b8ffff37108e3ad3f2b447111d55e2358efaa4670eb5458d782892d -size 2047150 +oid sha256:418019b4c5300241fa33c8bd50cf52884f2837bce9bae53ddf852c4f80df21b4 +size 2172355 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-0.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-0.mp4 deleted file mode 100644 index b8ec249fef6c41a5edc402db24566d13f3af55b9..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-0.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3aa3e3aaaf1477ad2c0ec447abc0f5ea43e26089e8ebdcfa2f1df307aa040ec2 -size 2003448 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-1.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-1.mp4 deleted file mode 100644 index abb485db638f3334598a012eae954b3560ee9351..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-1.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:10ce836ea72981ac1232d987301a4108c440ace76b184cbca79bf19ae79321cc -size 2029003 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-8.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-8.mp4 deleted file mode 100644 index eb57e0dca31b06ae5261a0ca9663bfdd22fff483..0000000000000000000000000000000000000000 --- a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705702894-eval/rl-video-episode-8.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4072ae9c1b8ffff37108e3ad3f2b447111d55e2358efaa4670eb5458d782892d -size 2047150 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-0.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-0.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..d9c8cf70527b6d3fbf8dc96efe6e5b542d92714f --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-0.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1aaea2fff2b450bc293211f941ccd59073a696f9ae9c0b5fd610f80c08e5e7 +size 2170396 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-1.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-1.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..432bef868862884e6441bc0b190aea73b54a1327 --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-1.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56c88e421ba054831582e3e42aeb3d47f1b9b3a488dea337c0b8fac3e951ae2 +size 2156502 diff --git a/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-8.mp4 b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-8.mp4 new file mode 100644 index 0000000000000000000000000000000000000000..5f3797f8fc09e223c9eaf150474f59d71f46d7c2 --- /dev/null +++ b/videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1705726141-eval/rl-video-episode-8.mp4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418019b4c5300241fa33c8bd50cf52884f2837bce9bae53ddf852c4f80df21b4 +size 2172355