diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb054a79c768e6feb3896f8ac36507e75bfc598f --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce106b5919dacf3e51f8c565bde8557954c13c74e49a85c18f88c06a8437a828 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..67bca4d7fd54d38ade6e3e950667f04d72baee20 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_154936_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640b5dd34b73f69df99649ebf001f577c4056259e484e4a55bbd867d1e4ba7f4 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0329_180836_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_123_0329_180836_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..001d4ec18496c6d3a9210f74b6b6cb846d05155b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288a538520bb8b7a1c344974c61a2eae1a8566c13ce4d9082b1688ffdb073d77 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..72725d3a802a5e7f6b56bf2f61eae915cb5fe522 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0119_040108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2c38057ee1ef372418551721ca9c031d549722dc3de577e7ad6d2aa3dfd6b3 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index db53ca23012fed3cd53d2cb977ca7ec61f052326..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a832dde9814f788a1aeecaab01ddadde592114e2f233fc38b68d1149e863bd0 -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 75fb6800b2843c0e9c85494968d66fde7cff7d57..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_42_0326_105036_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11ea29548529d4b16e6b369f1d32a24611292ce695261f480c5de676896bfa48 -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3f3a5cad4b027bbe6321b022b0a8c7b86aa9b72 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba52161cff4920cb73c07ea8859c1a65661e4ef16e85e3b584f888f50db23b4 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..9743a34fa355c05a00bd398ae7d25fd3dd3eb787 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0120_014533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ec1ca05bb2746453410cfcdc8f0adae06acd1e53d7d1993c49457719e51b06 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index db53ca23012fed3cd53d2cb977ca7ec61f052326..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a832dde9814f788a1aeecaab01ddadde592114e2f233fc38b68d1149e863bd0 -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 342da853fcda553829593aff9cdcf38a0287db47..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/diffusion/seed_456_0323_234108_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f3312f4a3a65a313bf1324e8e893d17adecd4807bd3bb1da913d483a3251467f -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..c19a0652d432f1207da659ff1c233c964f0e1d71 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbb56db0aa2e1869f77debd77ac0916d770631f19d9c2d6b79303176ca66069 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..ccdad80ab6e266c38eec3ce66bf51ab343cce986 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0114_105954_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eafb3b56888e0297fe02e9caa5c11461725b2897d3ad16b4dd928c79a92e58e4 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0329_154353_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_123_0329_154353_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd952ec5e6a460f30f7826748526be8b5c2fddf5 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50429d173096d77b8fe55ee2b82b56ea0fe2795cd0a75fe1dab77657899a020 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..8aec6a2d658ca01da222902facddda2499642969 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0114_001448_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6aa5e49d631fef60ab84ae52b072c6560fafda721a699c54213fce98fd7ba0c +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 9b367891aed1252f821612c49e4c486089942fbb..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31be326ef4bc6968d0ce148a77e6a9a517ba944706cae8e778b43f329549149c -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 1ffe83779853d5e5bbb267350e28ce82d34f4498..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_42_0326_070504_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:091ff01ea761da3567f97d757f4a21bfa1363d9a72cdbe788bdbf5018f12ea80 -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f24b2ff88149a1a08a8a825d2efe2c61e64bd3d --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14a34b7f9ec9c2d9fc6b5c002fc22e23570210a4196a756bbb2b78c4eb3d474 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3021527d700c0994fca03d0be215d7af9480e93 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0114_202349_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12406c05431af17839a5e739086d6f6a9a4a800606d4d9934233561c6dcfbbad +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 70d7071466325b83cefdc895ce714114e27deeec..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a8d14914abee3e52622bf363934f3413ee063165ffaea1450c1440606f83fec -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..b01d4dc9746f61c4d78814b39a37043dac67dc5b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bba8c628765928bb572b6630c8e9a1b2f56b2d1ffc785d75eadc8fb9c3d5c5 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4beb8a42099f979a50bca7ed845c5e7c81f39342 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_151820_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7279a345430cc1e50363ee9a0986f5951cec7fa4e2ee58eb2bb00b842700463 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_223759_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_223759_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..b01d4dc9746f61c4d78814b39a37043dac67dc5b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bba8c628765928bb572b6630c8e9a1b2f56b2d1ffc785d75eadc8fb9c3d5c5 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a7118f116aaf57dfa4c029bd53a92444a091494 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055755_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46894503b0a71d1f672eb432da89741bc2007d9740137695284aa3cbd6849b3c +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 9b367891aed1252f821612c49e4c486089942fbb..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31be326ef4bc6968d0ce148a77e6a9a517ba944706cae8e778b43f329549149c -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index ad7e35e5b2dc93fe65c75a12caf209be14594835..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0326_215120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:05cbb9ceec1f18e95f680242ee8654d3e0a7aca266fd60ac918fd6cb9f52a6c9 -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..b01d4dc9746f61c4d78814b39a37043dac67dc5b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bba8c628765928bb572b6630c8e9a1b2f56b2d1ffc785d75eadc8fb9c3d5c5 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..657b5ce71df1d527161086eb5867a79b65530058 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0122_021238_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d1d533f822ab07ec5d606f8326eb6ca70de02c41ed3ea9e36f5450d420975c +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index d2eaa2d406918f5d5cc0294f501c24f5214a05ff..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:41b3fa52aa573b41e17449fd5928567e5821eb6fc53eb37b5e53935b6235ad43 -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 70d7071466325b83cefdc895ce714114e27deeec..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_015311_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7a8d14914abee3e52622bf363934f3413ee063165ffaea1450c1440606f83fec -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..63ea998918f039c909f50f353bf98e7190ef0d0e --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bf56d4617900f185f396441914429669a1ddf242db61fe12844fce310850dd +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..751d43631b376d08851700f94c1185c5bdc35be0 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0114_124648_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e92a2e987316229187c1eb1a11b812ae4a7d9acbfc76d6fbad6516fb527bad7 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 9b367891aed1252f821612c49e4c486089942fbb..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31be326ef4bc6968d0ce148a77e6a9a517ba944706cae8e778b43f329549149c -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 72919ac10bbe6ebdaf87f7465fbcf79ce5630b6b..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_094430_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f6b9b4b5696b800c3e31eb5bf38400497dc862728ed6e70b0d288b97d02a432c -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..7494f9d56e0c3f53959dedaa7c948251efe3b5e9 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bf41b4a5a6dda401431d15cf539180edd3780f096e25e709232b6dd853455f +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7446b0a2afebd53f4f5b7e79ac4ec77cadb0cd76 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3245935bf3ef641aa85e4126213c402be5c7490c21f1a95758a94ae47218593 +size 1584 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d724bd22863044fbc9b488006d75257820e9b958 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0114_010248_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1ac7cc8ae80d8464f2408ebd2c34f2f275b486aaa512d026b09a45f51d6475 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 9b367891aed1252f821612c49e4c486089942fbb..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:31be326ef4bc6968d0ce148a77e6a9a517ba944706cae8e778b43f329549149c -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index 897f75a671cbe98fe3e7aeb34d2a6316a8c6b070..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_42_0326_053037_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fbafd4125cc2c8e9b4b3fde145c7879f380b18ec43cd802150ccaa77bb3e53f7 -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a6e611b26c9275dbc9b1cb0665860c2bbc962f6 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee21cd1286fac413b3d497d1e8209628132ee08538b55102ed11eb458b74780 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7446b0a2afebd53f4f5b7e79ac4ec77cadb0cd76 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3245935bf3ef641aa85e4126213c402be5c7490c21f1a95758a94ae47218593 +size 1584 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..398fc599f4caa8e04f91dae2066f039339a624f4 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0115_010419_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb22ca857a701f4b001416d7dbda442ccd030d0dbb065f977065abe5c65ea06 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0329_235735_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/realnvp/seed_456_0329_235735_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..731c2b38b2f081998e31db11a034e05e420687aa --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f057395f2228b3dbe43308fa5bad7ea971202fd4a49b3e109f1cb2b634175e +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7446b0a2afebd53f4f5b7e79ac4ec77cadb0cd76 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3245935bf3ef641aa85e4126213c402be5c7490c21f1a95758a94ae47218593 +size 1584 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfa20f9ed484e64310811aff31f5b84dfc7452a2 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0115_090928_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a300c147671786fc72da30fb6de01254f8fd8f962b5aa9c460975ab805659a5 +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 615a1eebcb7172333c8b95a5e70fe6f4d7653c1b..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6adec29bbf0e1ea855a59d0a56a76de873979cac47fb4eca8a2e032d8d503ecd -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index e0f12f4733a34ca35b5d92e5cbf2301293ae55df..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_123_0227_221120_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3127c8395356c31ece86b77abae2c91c90c03cf848adb8aa1298c12bd3614e4b -size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..8176b0ede73bbb65a8bdb2d5de7496250421efb3 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13404256c17f45db213091d6f1a2cbc22d80a387669cb0bdbebd450f50a68942 +size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7446b0a2afebd53f4f5b7e79ac4ec77cadb0cd76 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3245935bf3ef641aa85e4126213c402be5c7490c21f1a95758a94ae47218593 +size 1584 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a3df667005dcd3f8fa73434fb4a540e905855b9 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0114_213159_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061bb2f7e62887d02906e703423195181f380bc89a99054662558dc9f418cddd +size 1473418 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003006_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003006_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth deleted file mode 100644 index a6940b6dcbcf1ecbee4e6bee9eab6423ee08809a..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003006_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0f0ff179d635c8de425cc17aa7a071a34567f2dc50b4a714a01f37c7ac693015 -size 21120 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/kde/seed_456_0302_184319_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt rename to halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7446b0a2afebd53f4f5b7e79ac4ec77cadb0cd76 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3245935bf3ef641aa85e4126213c402be5c7490c21f1a95758a94ae47218593 +size 1584 diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth similarity index 100% rename from halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth rename to halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0222_054148_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/policy_halfcheetah-medium-expert-v2.pth diff --git a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt b/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt deleted file mode 100644 index 615a1eebcb7172333c8b95a5e70fe6f4d7653c1b..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mbpo_based/vae/seed_456_0301_061533_halfcheetah_medium_expert_v2_gormpo_sparse_72.5/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6adec29bbf0e1ea855a59d0a56a76de873979cac47fb4eca8a2e032d8d503ecd -size 3736742 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/checkpoint/policy.pth b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/checkpoint/policy.pth deleted file mode 100644 index 61732c0be480afcbe8e5dd51b8214a26f11f5598..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/checkpoint/policy.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fa5867961cf43e24c6e5f210a4e3627df9a3d27ce056803de8f25155d14283ee -size 1459666 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt deleted file mode 100644 index d7bb266eb17eb872227acdabce10bd788b6acb52..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt +++ /dev/null @@ -1,109 +0,0 @@ -num rollout transitions: 250000, reward mean: 7.9591 ----------------------------------------------------------------------------------- -| alpha | 0.951 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | 2.25 | -| eval/normalized_episode_reward_std | 2.26 | -| loss/actor | -26.7 | -| loss/alpha | -0.501 | -| loss/critic | 2.42 | -| penalty/lcb_mean | 0.239 | -| penalty/lcb_std | 0.183 | -| rollout_info/dynamics_penalty_mean | 0.948 | -| rollout_info/dynamics_penalty_std | 0.154 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 7.96 | -| timestep | 1000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.0816 ----------------------------------------------------------------------------------- -| alpha | 0.861 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | 2.24 | -| eval/normalized_episode_reward_std | 2.26 | -| loss/actor | -56.7 | -| loss/alpha | -1.4 | -| loss/critic | 5.1 | -| penalty/lcb_mean | 0.686 | -| penalty/lcb_std | 0.51 | -| rollout_info/dynamics_penalty_mean | 0.883 | -| rollout_info/dynamics_penalty_std | 0.238 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 8.08 | -| timestep | 2000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.1632 ----------------------------------------------------------------------------------- -| alpha | 0.785 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | 2.26 | -| eval/normalized_episode_reward_std | 2.36 | -| loss/actor | -84.5 | -| loss/alpha | -1.92 | -| loss/critic | 12.1 | -| penalty/lcb_mean | 1.12 | -| penalty/lcb_std | 0.888 | -| rollout_info/dynamics_penalty_mean | 0.798 | -| rollout_info/dynamics_penalty_std | 0.318 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 8.16 | -| timestep | 3000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.2764 ----------------------------------------------------------------------------------- -| alpha | 0.723 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | -1.76 | -| eval/normalized_episode_reward_std | 3.59 | -| loss/actor | -115 | -| loss/alpha | -1.91 | -| loss/critic | 23.1 | -| penalty/lcb_mean | 1.47 | -| penalty/lcb_std | 1.3 | -| rollout_info/dynamics_penalty_mean | 0.622 | -| rollout_info/dynamics_penalty_std | 0.41 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 8.28 | -| timestep | 4000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.3717 ----------------------------------------------------------------------------------- -| alpha | 0.671 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | -0.523 | -| eval/normalized_episode_reward_std | 3.04 | -| loss/actor | -148 | -| loss/alpha | -1.73 | -| loss/critic | 33.1 | -| penalty/lcb_mean | 1.69 | -| penalty/lcb_std | 1.65 | -| rollout_info/dynamics_penalty_mean | 0.513 | -| rollout_info/dynamics_penalty_std | 0.433 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 8.37 | -| timestep | 5000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.4004 ----------------------------------------------------------------------------------- -| alpha | 0.625 | -| eval/episode_length | 1e+03 | -| eval/episode_length_std | 0 | -| eval/normalized_episode_reward | -0.727 | -| eval/normalized_episode_reward_std | 2.97 | -| loss/actor | -184 | -| loss/alpha | -1.55 | -| loss/critic | 40.4 | -| penalty/lcb_mean | 1.62 | -| penalty/lcb_std | 1.72 | -| rollout_info/dynamics_penalty_mean | 0.489 | -| rollout_info/dynamics_penalty_std | 0.438 | -| rollout_info/num_transitions | 2.5e+05 | -| rollout_info/reward_mean | 8.4 | -| timestep | 6000 | ----------------------------------------------------------------------------------- -num rollout transitions: 250000, reward mean: 8.4457 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv deleted file mode 100644 index bfc9cf04f6fffec7fe2d2facaacc1d772e19314a..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv +++ /dev/null @@ -1,7 +0,0 @@ -alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep -0.9510112407207484,1000.0,0.0,2.2480923128261394,2.262089153151541,-26.71767212626339,-0.5005366210330977,2.421098216891298,0.23889984861016272,0.1828052099738271,0.9475828686230767,0.15422547312640653,250000.0,7.959125518874213,1000 -0.8614789130091686,1000.0,0.0,2.243184598253138,2.263307580543581,-56.730259044647205,-1.4012687608003593,5.095535691261273,0.6864486481547346,0.5101754370331767,0.8829295114833671,0.23844507018385008,250000.0,8.081574176361917,2000 -0.7848412469625478,1000.0,0.0,2.2570826636084877,2.356420749107294,-84.52276610565215,-1.916771145820618,12.139820645809177,1.1215785875916489,0.888472099453209,0.7979656769289477,0.31797584038972176,250000.0,8.163160870889284,3000 -0.7225907544493669,1000.0,0.0,-1.7588679730673356,3.5890129589497333,-114.91533139801037,-1.9133579128980656,23.094216865539536,1.470472787141799,1.2992941896319354,0.6217726752409218,0.40963976235318167,250000.0,8.276367412597486,4000 -0.6708657387495042,1000.0,0.0,-0.5232415725018443,3.0396031974787094,-148.4734272079464,-1.7257029182910912,33.137822557449304,1.6914653149843195,1.651797513604163,0.513250201046385,0.432529844480266,250000.0,8.371745433683223,5000 -0.625270288348199,1000.0,0.0,-0.7265880655791849,2.9698222093695716,-184.1360603637696,-1.5519387843608818,40.38626070022576,1.6157407870292673,1.721018972933291,0.48892481898505485,0.4375016123247296,250000.0,8.400391131568952,6000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/tb/events.out.tfevents.1773705363.aysin.2854248.0 b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/tb/events.out.tfevents.1773705363.aysin.2854248.0 deleted file mode 100644 index 87c4d1f63eb7aaf6a6e2e1d374c24ddf706fc184..0000000000000000000000000000000000000000 --- a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/tb/events.out.tfevents.1773705363.aysin.2854248.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fff6f51f8403b45bb466417dbd6e18e887fe4614c67b0ad4f0fe3a4f3e76aa37 -size 6965 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/checkpoint/policy.pth b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/checkpoint/policy.pth new file mode 100644 index 0000000000000000000000000000000000000000..ddbad90afa073788dc252b6db2a93cda2cb078e7 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/checkpoint/policy.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41664e0e8df3a3f7dc3a6001d0d1e89b8e40ecfb61958f3525883106b216456 +size 1459666 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/dynamics.pth b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/dynamics.pth new file mode 100644 index 0000000000000000000000000000000000000000..798fad3fa588a6ce1f76a4b374d3c9a1a1d1fd49 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/dynamics.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d46a99bbd82ae1cf17dffde409f0ede4209656112516a7d45df5d952dfcc45b +size 7435052 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/mu.npy b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/mu.npy new file mode 100644 index 0000000000000000000000000000000000000000..1789da0b1f583577a02cb856ca3186395f8318e4 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/mu.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b784a16d85ec615cb2ef8089891792056ab4714fe7b63f696b370a0e9b990b4 +size 220 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/policy.pth b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/policy.pth new file mode 100644 index 0000000000000000000000000000000000000000..ddbad90afa073788dc252b6db2a93cda2cb078e7 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/policy.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41664e0e8df3a3f7dc3a6001d0d1e89b8e40ecfb61958f3525883106b216456 +size 1459666 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/std.npy b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/std.npy new file mode 100644 index 0000000000000000000000000000000000000000..2fe16055cd735c966efc16ab6498386dbd81c32a --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/model/std.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d357e34aa10eca32dbb67ae51db28fd3510bec82ad42a3f8d32bb5ca7010dd +size 220 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..b2cf1ac345941f4f8373bb16dbbf799e958f9670 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 7.9591 +num rollout transitions: 250000, reward mean: 8.0816 +num rollout transitions: 250000, reward mean: 8.1632 +num rollout transitions: 250000, reward mean: 8.2764 +num rollout transitions: 250000, reward mean: 8.3717 +num rollout transitions: 250000, reward mean: 8.4004 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4778 +num rollout transitions: 250000, reward mean: 8.5289 +num rollout transitions: 250000, reward mean: 8.4947 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.5682 +num rollout transitions: 250000, reward mean: 8.5353 +num rollout transitions: 250000, reward mean: 8.5491 +num rollout transitions: 250000, reward mean: 8.6858 +num rollout transitions: 250000, reward mean: 8.5934 +num rollout transitions: 250000, reward mean: 8.5655 +num rollout transitions: 250000, reward mean: 8.6137 +num rollout transitions: 250000, reward mean: 8.7345 +num rollout transitions: 250000, reward mean: 8.5281 +num rollout transitions: 250000, reward mean: 8.6957 +num rollout transitions: 250000, reward mean: 8.6455 +num rollout transitions: 250000, reward mean: 8.6413 +num rollout transitions: 250000, reward mean: 8.6213 +num rollout transitions: 250000, reward mean: 8.7316 +num rollout transitions: 250000, reward mean: 8.6694 +num rollout transitions: 250000, reward mean: 8.7117 +num rollout transitions: 250000, reward mean: 8.7115 +num rollout transitions: 250000, reward mean: 8.7228 +num rollout transitions: 250000, reward mean: 8.7241 +num rollout transitions: 250000, reward mean: 8.7610 +num rollout transitions: 250000, reward mean: 8.7727 +num rollout transitions: 250000, reward mean: 8.7793 +num rollout transitions: 250000, reward mean: 8.7367 +num rollout transitions: 250000, reward mean: 8.7932 +num rollout transitions: 250000, reward mean: 8.7869 +num rollout transitions: 250000, reward mean: 8.7599 +num rollout transitions: 250000, reward mean: 8.7957 +num rollout transitions: 250000, reward mean: 8.7930 +num rollout transitions: 250000, reward mean: 8.7900 +num rollout transitions: 250000, reward mean: 8.7836 +num rollout transitions: 250000, reward mean: 8.8281 +num rollout transitions: 250000, reward mean: 8.7818 +num rollout transitions: 250000, reward mean: 8.8268 +num rollout transitions: 250000, reward mean: 8.8373 +num rollout transitions: 250000, reward mean: 8.8113 +num rollout transitions: 250000, reward mean: 8.7985 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.7822 +---------------------------------------------------------------------------------- +| alpha | 0.558 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 33.1 | +| eval/normalized_episode_reward_std | 19.6 | +| loss/actor | -377 | +| loss/alpha | -0.298 | +| loss/critic | 306 | +| penalty/lcb_mean | 2.62 | +| penalty/lcb_std | 3.82 | +| rollout_info/dynamics_penalty_mean | 0.258 | +| rollout_info/dynamics_penalty_std | 0.329 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.63 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8175 +num rollout transitions: 250000, reward mean: 8.8147 +num rollout transitions: 250000, reward mean: 8.8231 +num rollout transitions: 250000, reward mean: 8.8204 +num rollout transitions: 250000, reward mean: 8.7668 +num rollout transitions: 250000, reward mean: 8.8218 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8125 +num rollout transitions: 250000, reward mean: 8.8343 +num rollout transitions: 250000, reward mean: 8.8354 +num rollout transitions: 250000, reward mean: 8.8123 +num rollout transitions: 250000, reward mean: 8.8485 +num rollout transitions: 250000, reward mean: 8.8260 +num rollout transitions: 250000, reward mean: 8.8589 +num rollout transitions: 250000, reward mean: 8.8480 +num rollout transitions: 250000, reward mean: 8.8422 +num rollout transitions: 250000, reward mean: 8.8179 +num rollout transitions: 250000, reward mean: 8.8513 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.7986 +num rollout transitions: 250000, reward mean: 8.8475 +num rollout transitions: 250000, reward mean: 8.8567 +num rollout transitions: 250000, reward mean: 8.8492 +num rollout transitions: 250000, reward mean: 8.8472 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8197 +num rollout transitions: 250000, reward mean: 8.8298 +num rollout transitions: 250000, reward mean: 8.8379 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8330 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8297 +num rollout transitions: 250000, reward mean: 8.8296 +num rollout transitions: 250000, reward mean: 8.8214 +num rollout transitions: 250000, reward mean: 8.7755 +num rollout transitions: 250000, reward mean: 8.8387 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8529 +num rollout transitions: 250000, reward mean: 8.8200 +num rollout transitions: 250000, reward mean: 8.7987 +num rollout transitions: 250000, reward mean: 8.8402 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8436 +num rollout transitions: 250000, reward mean: 8.8954 +---------------------------------------------------------------------------------- +| alpha | 0.723 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 67.5 | +| eval/normalized_episode_reward_std | 20.8 | +| loss/actor | -562 | +| loss/alpha | 0.0019 | +| loss/critic | 302 | +| penalty/lcb_mean | 3.14 | +| penalty/lcb_std | 3.94 | +| rollout_info/dynamics_penalty_mean | 0.0696 | +| rollout_info/dynamics_penalty_std | 0.214 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.84 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8280 +num rollout transitions: 250000, reward mean: 8.8456 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.8490 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8117 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8127 +num rollout transitions: 250000, reward mean: 8.8269 +num rollout transitions: 250000, reward mean: 8.8253 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8510 +num rollout transitions: 250000, reward mean: 8.8433 +num rollout transitions: 250000, reward mean: 8.8094 +num rollout transitions: 250000, reward mean: 8.7919 +num rollout transitions: 250000, reward mean: 8.8507 +num rollout transitions: 250000, reward mean: 8.8434 +num rollout transitions: 250000, reward mean: 8.8680 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.8192 +num rollout transitions: 250000, reward mean: 8.8607 +num rollout transitions: 250000, reward mean: 8.8395 +num rollout transitions: 250000, reward mean: 8.8116 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.8586 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8515 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.8482 +num rollout transitions: 250000, reward mean: 8.8383 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8487 +num rollout transitions: 250000, reward mean: 8.8620 +num rollout transitions: 250000, reward mean: 8.8455 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8201 +num rollout transitions: 250000, reward mean: 8.8231 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.8482 +num rollout transitions: 250000, reward mean: 8.8203 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.8612 +num rollout transitions: 250000, reward mean: 8.8335 +num rollout transitions: 250000, reward mean: 8.8440 +num rollout transitions: 250000, reward mean: 8.7993 +---------------------------------------------------------------------------------- +| alpha | 0.719 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 77.7 | +| eval/normalized_episode_reward_std | 22.5 | +| loss/actor | -698 | +| loss/alpha | -0.00138 | +| loss/critic | 262 | +| penalty/lcb_mean | 3 | +| penalty/lcb_std | 4 | +| rollout_info/dynamics_penalty_mean | 0.0605 | +| rollout_info/dynamics_penalty_std | 0.2 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.85 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8665 +num rollout transitions: 250000, reward mean: 8.8404 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8427 +num rollout transitions: 250000, reward mean: 8.8433 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8223 +num rollout transitions: 250000, reward mean: 8.8284 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.8595 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8474 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8496 +num rollout transitions: 250000, reward mean: 8.8241 +num rollout transitions: 250000, reward mean: 8.8584 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.8620 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.8482 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8332 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8189 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8346 +num rollout transitions: 250000, reward mean: 8.8590 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8540 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8432 +num rollout transitions: 250000, reward mean: 8.8664 +num rollout transitions: 250000, reward mean: 8.8446 +num rollout transitions: 250000, reward mean: 8.8721 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8332 +num rollout transitions: 250000, reward mean: 8.8673 +---------------------------------------------------------------------------------- +| alpha | 0.65 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 82 | +| eval/normalized_episode_reward_std | 23.3 | +| loss/actor | -799 | +| loss/alpha | -0.00329 | +| loss/critic | 191 | +| penalty/lcb_mean | 2.59 | +| penalty/lcb_std | 3.57 | +| rollout_info/dynamics_penalty_mean | 0.0555 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.86 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8451 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8310 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8581 +num rollout transitions: 250000, reward mean: 8.8356 +num rollout transitions: 250000, reward mean: 8.8549 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8342 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.8074 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8538 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8498 +num rollout transitions: 250000, reward mean: 8.8414 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.8483 +num rollout transitions: 250000, reward mean: 8.8464 +num rollout transitions: 250000, reward mean: 8.8410 +num rollout transitions: 250000, reward mean: 8.8471 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8313 +num rollout transitions: 250000, reward mean: 8.8418 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.8697 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8373 +num rollout transitions: 250000, reward mean: 8.8395 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.8522 +---------------------------------------------------------------------------------- +| alpha | 0.578 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.2 | +| eval/normalized_episode_reward_std | 7.78 | +| loss/actor | -853 | +| loss/alpha | -0.00293 | +| loss/critic | 155 | +| penalty/lcb_mean | 2.32 | +| penalty/lcb_std | 3.32 | +| rollout_info/dynamics_penalty_mean | 0.0549 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.8428 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8679 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8500 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8441 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8636 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8316 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8366 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8612 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8461 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8558 +num rollout transitions: 250000, reward mean: 8.8549 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8914 +---------------------------------------------------------------------------------- +| alpha | 0.526 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.4 | +| eval/normalized_episode_reward_std | 14 | +| loss/actor | -895 | +| loss/alpha | -0.00294 | +| loss/critic | 130 | +| penalty/lcb_mean | 2.13 | +| penalty/lcb_std | 3.12 | +| rollout_info/dynamics_penalty_mean | 0.0545 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8542 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8490 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8439 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8519 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8227 +num rollout transitions: 250000, reward mean: 8.8655 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.8675 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8631 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8588 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8562 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8461 +---------------------------------------------------------------------------------- +| alpha | 0.489 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 11.9 | +| loss/actor | -916 | +| loss/alpha | -0.00191 | +| loss/critic | 118 | +| penalty/lcb_mean | 2.02 | +| penalty/lcb_std | 3.03 | +| rollout_info/dynamics_penalty_mean | 0.0551 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.8552 +num rollout transitions: 250000, reward mean: 8.8356 +num rollout transitions: 250000, reward mean: 8.8579 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.8584 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8564 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8276 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8478 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8549 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8526 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8362 +num rollout transitions: 250000, reward mean: 8.8538 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8399 +num rollout transitions: 250000, reward mean: 8.8566 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8432 +---------------------------------------------------------------------------------- +| alpha | 0.459 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.7 | +| eval/normalized_episode_reward_std | 15.3 | +| loss/actor | -924 | +| loss/alpha | -0.003 | +| loss/critic | 111 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0.0545 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8490 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8680 +num rollout transitions: 250000, reward mean: 8.8606 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.8336 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8290 +num rollout transitions: 250000, reward mean: 8.8448 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8663 +num rollout transitions: 250000, reward mean: 8.8579 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.8464 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8591 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8507 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.8363 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8495 +num rollout transitions: 250000, reward mean: 8.8431 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8936 +----------------------------------------------------------------------------------- +| alpha | 0.439 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -933 | +| loss/alpha | -0.000907 | +| loss/critic | 100 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.0547 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8205 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.8596 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8597 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8603 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.8509 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8521 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8607 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8598 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8564 +num rollout transitions: 250000, reward mean: 8.8446 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8599 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8580 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8934 +----------------------------------------------------------------------------------- +| alpha | 0.43 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 8.51 | +| loss/actor | -940 | +| loss/alpha | -0.000996 | +| loss/critic | 98 | +| penalty/lcb_mean | 1.84 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0.0545 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8427 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8591 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8592 +num rollout transitions: 250000, reward mean: 8.8757 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8471 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9144 +---------------------------------------------------------------------------------- +| alpha | 0.418 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.8 | +| eval/normalized_episode_reward_std | 5.07 | +| loss/actor | -948 | +| loss/alpha | -0.00179 | +| loss/critic | 94.8 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0.0538 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8532 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8549 +num rollout transitions: 250000, reward mean: 8.8757 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8575 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8538 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8516 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8585 +num rollout transitions: 250000, reward mean: 8.8760 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8429 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8462 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.8494 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.8524 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8382 +num rollout transitions: 250000, reward mean: 8.8586 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.8914 +---------------------------------------------------------------------------------- +| alpha | 0.41 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -949 | +| loss/alpha | -0.00191 | +| loss/critic | 95.3 | +| penalty/lcb_mean | 1.81 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.0544 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8499 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8483 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8517 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8363 +num rollout transitions: 250000, reward mean: 8.8665 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.8555 +---------------------------------------------------------------------------------- +| alpha | 0.395 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 10.5 | +| loss/actor | -950 | +| loss/alpha | -0.00139 | +| loss/critic | 92 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.8511 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8359 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8604 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8598 +num rollout transitions: 250000, reward mean: 8.8626 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8659 +----------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 5.25 | +| loss/actor | -956 | +| loss/alpha | -0.000781 | +| loss/critic | 85.5 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8517 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8562 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8700 +num rollout transitions: 250000, reward mean: 8.8721 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8800 +---------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.8 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -962 | +| loss/alpha | 0.00141 | +| loss/critic | 87.2 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0533 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8500 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8448 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.8556 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8700 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8599 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.8633 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8483 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8730 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8541 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 3.35 | +| loss/actor | -962 | +| loss/alpha | -0.00141 | +| loss/critic | 96.8 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.95 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8582 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.8479 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8478 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8459 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8651 +---------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 13.8 | +| loss/actor | -965 | +| loss/alpha | 0.00027 | +| loss/critic | 81.8 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8505 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8634 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.8539 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.8682 +num rollout transitions: 250000, reward mean: 8.8689 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8351 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8714 +----------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.3 | +| eval/normalized_episode_reward_std | 3.28 | +| loss/actor | -966 | +| loss/alpha | -0.000495 | +| loss/critic | 85.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0539 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8582 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8577 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8599 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8464 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8043 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9009 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.5 | +| eval/normalized_episode_reward_std | 10.3 | +| loss/actor | -969 | +| loss/alpha | 0.000805 | +| loss/critic | 78.5 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0.0532 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8702 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8525 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8700 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8442 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8898 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.8 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -971 | +| loss/alpha | -0.0019 | +| loss/critic | 80.1 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0.0531 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8406 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8218 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8880 +----------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.5 | +| eval/normalized_episode_reward_std | 17.4 | +| loss/actor | -973 | +| loss/alpha | -0.000384 | +| loss/critic | 75.1 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.8448 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8474 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8563 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.8960 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 5.93 | +| loss/actor | -979 | +| loss/alpha | 0.000389 | +| loss/critic | 70.8 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8517 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8358 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.8538 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8627 +num rollout transitions: 250000, reward mean: 8.8882 +----------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.29 | +| loss/actor | -980 | +| loss/alpha | -0.000816 | +| loss/critic | 79.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8589 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.8421 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8606 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8569 +---------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -977 | +| loss/alpha | 0.0021 | +| loss/critic | 83.2 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0539 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.8343 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8489 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9002 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 13.1 | +| loss/actor | -975 | +| loss/alpha | -0.0035 | +| loss/critic | 81.6 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0531 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8697 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.8387 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8895 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.44 | +| loss/actor | -981 | +| loss/alpha | 0.000377 | +| loss/critic | 71.2 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.0526 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.9248 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 4.03 | +| loss/actor | -987 | +| loss/alpha | 0.000472 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.0521 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8569 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8880 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.36 | +| loss/actor | -987 | +| loss/alpha | -0.00183 | +| loss/critic | 70.6 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0.0522 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8976 +---------------------------------------------------------------------------------- +| alpha | 0.341 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.2 | +| loss/actor | -989 | +| loss/alpha | 0.00147 | +| loss/critic | 68.7 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.0517 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8730 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8503 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9020 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.3 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -990 | +| loss/alpha | 0.00183 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8657 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8702 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8659 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.8760 +num rollout transitions: 250000, reward mean: 8.8575 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9266 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 10.3 | +| loss/actor | -987 | +| loss/alpha | -0.00384 | +| loss/critic | 68.7 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0.0514 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8617 +num rollout transitions: 250000, reward mean: 8.8378 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8938 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 7.02 | +| loss/actor | -989 | +| loss/alpha | 0.00135 | +| loss/critic | 80.6 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0.052 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8935 +----------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.9 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -990 | +| loss/alpha | -0.000831 | +| loss/critic | 70.6 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.0515 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9055 +---------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.9 | +| eval/normalized_episode_reward_std | 2.99 | +| loss/actor | -992 | +| loss/alpha | 0.00082 | +| loss/critic | 68.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8730 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9117 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.5 | +| eval/normalized_episode_reward_std | 19 | +| loss/actor | -989 | +| loss/alpha | 0.000923 | +| loss/critic | 75.2 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0.0523 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9055 +---------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.2 | +| eval/normalized_episode_reward_std | 3.23 | +| loss/actor | -994 | +| loss/alpha | 0.00144 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0527 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8545 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8902 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -997 | +| loss/alpha | -0.00243 | +| loss/critic | 70.9 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 0.0526 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9034 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.11 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00134 | +| loss/critic | 65 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0.0525 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8663 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9082 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 9.31 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00107 | +| loss/critic | 66.9 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8571 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.9236 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 5.73 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00124 | +| loss/critic | 66 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0.0525 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.8728 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9031 +---------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 11.5 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000105 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0521 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8689 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9004 +----------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 5.46 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00134 | +| loss/critic | 65 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0516 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9148 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 9.46 | +| loss/actor | -1.01e+03 | +| loss/alpha | 5.36e-05 | +| loss/critic | 64.2 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0.0519 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.9264 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 11.2 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000156 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9162 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 13.6 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000362 | +| loss/critic | 68.4 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0517 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9012 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 13.5 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000311 | +| loss/critic | 66.2 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.8632 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8879 +----------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 4.19 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00111 | +| loss/critic | 66.3 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.0515 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8900 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 9.78 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00142 | +| loss/critic | 66.2 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.0523 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8635 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9086 +----------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.41 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000253 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0515 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9206 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 7.96 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000655 | +| loss/critic | 64.8 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.0515 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.8868 +----------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 8.45 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000115 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.0517 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9118 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.28 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000116 | +| loss/critic | 64.7 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9160 +----------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.4 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000115 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.0518 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8994 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 8.89 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000323 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9013 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00116 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0.0519 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9202 +----------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 4.36 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.0022 | +| loss/critic | 66.9 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.0521 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9334 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.35 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000558 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.0519 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.8973 +----------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 5.88 | +| loss/actor | -1.02e+03 | +| loss/alpha | -5.75e-05 | +| loss/critic | 68.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0.0519 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8948 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.7 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00135 | +| loss/critic | 68.3 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 0.052 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8987 +----------------------------------------------------------------------------------- +| alpha | 0.319 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 5.32 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00794 | +| loss/critic | 66.5 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0518 | +| rollout_info/dynamics_penalty_std | 0.182 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 131250.14s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/dynamics_training_progress.csv similarity index 100% rename from halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv rename to halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/dynamics_training_progress.csv diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/hyper_param.json similarity index 100% rename from halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json rename to halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/hyper_param.json diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..36661a852ccad78a3fdc9781c338126b7d6f6774 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.558202357538935,1000.0,0.0,33.09174882038358,19.633582588158422,-376.80879587942985,-0.2976486299037638,305.58441256493234,2.6220606534653523,3.8182852174868347,0.2583227094758406,0.32945698936495954,250000.0,8.627866863282541,50000 +0.7225340663468832,1000.0,0.0,67.46581079121552,20.798210355491175,-561.6100779846175,0.0019025545473209896,301.56983764480503,3.139301105051058,3.9422041336917935,0.06960831402320163,0.21442741238241278,250000.0,8.842182556123717,100000 +0.7192269480073396,1000.0,0.0,77.661475922361,22.471729979501795,-698.0118207983322,-0.0013799417471047366,262.4181564268499,3.000696541850593,3.9972728082561595,0.06049606797213285,0.19993918088260926,250000.0,8.851055347034086,150000 +0.6503626118493111,1000.0,0.0,81.95168060819948,23.33424332397863,-799.1987567956522,-0.003288093293327877,191.1994055336765,2.5897516148138493,3.5697758391642282,0.055481336024787525,0.1912367430225348,250000.0,8.863725836810346,200000 +0.5777504582881787,1000.0,0.0,96.20408278950406,7.783011747286796,-852.6085134448142,-0.002928372376645046,154.7990771024325,2.3245618863010495,3.3169270945954477,0.05492667462599414,0.18945970513785768,250000.0,8.86563495241084,250000 +0.5259682415658267,1000.0,0.0,95.41188188165778,13.987932166663095,-895.0613358593755,-0.0029375921585131468,129.87553267128078,2.1275168201875876,3.1154212565576893,0.05446953918466294,0.18842761243392256,250000.0,8.876474022456273,300000 +0.4885947595918195,1000.0,0.0,96.07706685527553,11.919601638842702,-916.2477918884248,-0.0019059864881541496,117.89962167266845,2.018444877345558,3.030581214990623,0.05507711333951829,0.18929180961020983,250000.0,8.87530520115916,350000 +0.45876509886682093,1000.0,0.0,90.71813897559376,15.302818713790838,-924.4174444067418,-0.0030023681308329313,110.78239033023901,1.9345785341334194,2.980706056816573,0.05446185230072354,0.1881091509138171,250000.0,8.878570204904715,400000 +0.43850096068739736,1000.0,0.0,90.95162017407746,3.161684150317879,-932.7483862585594,-0.0009072355664335126,100.45042740817998,1.8629192825984888,2.825846829078187,0.05466737052993361,0.18822349633093863,250000.0,8.881504386679582,450000 +0.4299981966245161,1000.0,0.0,96.58429647221121,8.511504095708547,-940.1105707299834,-0.000996427781190729,97.98854170353108,1.8411381872201018,2.843498807719957,0.05451411689673649,0.18766397884874222,250000.0,8.87883014154497,500000 +0.4176873780787007,1000.0,0.0,93.75826638291488,5.074099948082515,-947.7809702319306,-0.0017893515914864811,94.8134948164747,1.8155836318659517,2.822334202680601,0.053791950574984475,0.1866037286647732,250000.0,8.885181742237014,550000 +0.4095125883328846,1000.0,0.0,96.91834499349758,2.999724935729052,-949.1172260766733,-0.0019065311894751876,95.28734710682097,1.8076911541414258,2.8315239376354597,0.054351170832060154,0.18734074461329908,250000.0,8.882507020864203,600000 +0.39499008392751306,1000.0,0.0,95.94173094543872,10.48404898145739,-950.4707934216332,-0.0013891961077042018,92.03911774616233,1.757503546388148,2.814485135537426,0.053523049442693024,0.18586874336561743,250000.0,8.885636426460641,650000 +0.3859471244186186,1000.0,0.0,98.03773209986433,5.248299449185337,-955.7073417736823,-0.0007811897781770723,85.48001494731876,1.7139521070242076,2.7098423757195484,0.05351546822671931,0.18571222677611726,250000.0,8.883372776654918,700000 +0.3816968973171712,1000.0,0.0,95.81730539567859,3.2530215645292215,-962.3237457507354,0.0014145766405761313,87.24108788341601,1.7226424784254903,2.756252290133253,0.05333001855624218,0.1853478330739744,250000.0,8.890596077024833,750000 +0.3810921112972488,1000.0,0.0,98.35933083053968,3.3466421507814674,-961.8291533129877,-0.0014070487907715263,96.81023458644947,1.749059802680006,2.9507812499355937,0.05345116771707717,0.18549174997883278,250000.0,8.885528232855629,800000 +0.369045627262593,1000.0,0.0,96.87451019185653,13.805242400768606,-965.3410311962842,0.00026979548310859005,81.82700082511884,1.676916619312766,2.7028180990124286,0.05351255054455397,0.18546841419441074,250000.0,8.891809183640046,850000 +0.3688241823172559,1000.0,0.0,98.26282348682238,3.27813659392847,-965.9093775586033,-0.0004949885127507016,85.36361946415023,1.6884904373574119,2.7616089791738987,0.05389776476810108,0.18603687612427644,250000.0,8.888326524591491,900000 +0.3634171213477807,1000.0,0.0,97.51158997009043,10.268016479543085,-969.1020967114289,0.0008050999284535522,78.53097356090524,1.6476992118716272,2.6457760433411432,0.05315419599710863,0.18499325288996465,250000.0,8.888919760281752,950000 +0.36504844777524215,1000.0,0.0,91.84247832347859,3.033395759755012,-970.8310087988374,-0.0018990224724263368,80.12379351715111,1.6599925288534096,2.7064678996014533,0.053102774405488266,0.1850647002786198,250000.0,8.895818265778326,1000000 +0.3548628160774699,1000.0,0.0,94.45308453573719,17.35461119875757,-973.249207910153,-0.00038355542588978757,75.08151531791715,1.6112576790070627,2.598451002837404,0.05281516677289651,0.18429875236080215,250000.0,8.891712634157109,1050000 +0.35204198340058596,1000.0,0.0,98.59004088359107,5.926362243623709,-979.0609685607894,0.00038858600668609136,70.7632115384285,1.588189687947022,2.5099235924839873,0.052407504353462926,0.18354908394821373,250000.0,8.895661007292082,1100000 +0.35548689414680157,1000.0,0.0,100.85214020542874,8.293878477118156,-979.879592216796,-0.000815881279427562,79.38533831691812,1.6234633713472038,2.6906742540871935,0.052785029012176646,0.1843878571820432,250000.0,8.893340669619919,1150000 +0.34976627045273756,1000.0,0.0,97.3637649979985,3.0869525124792223,-976.9974578161598,0.0021045217679627514,83.2004534508117,1.6348848333728474,2.76760304910538,0.05387565938289593,0.18627717344853,250000.0,8.892489705103555,1200000 +0.3480986086422231,1000.0,0.0,96.79916289839834,13.05122871761119,-975.2243233178676,-0.003503183922860777,81.62888437885384,1.6174016685092463,2.758322238395195,0.05305474572354033,0.18486389003861475,250000.0,8.893301088329583,1250000 +0.34330419757306846,1000.0,0.0,101.22814028071487,3.4432071144224428,-981.149769544682,0.00037690474268047865,71.24968313941874,1.5558724735367384,2.5411389843941223,0.05263156772346964,0.18413777526682118,250000.0,8.899043729007357,1300000 +0.3466523774665615,1000.0,0.0,100.40411275205979,4.029693350179024,-986.5177561767482,0.00047231966057792,70.07089362346593,1.5688684260261059,2.5272907917416263,0.0520711305826865,0.1830496955167479,250000.0,8.89843702490613,1350000 +0.3424640662926441,1000.0,0.0,102.32319829419968,3.3604067028082594,-986.906374313953,-0.0018254332514107286,70.5900156674202,1.555210947036739,2.5601527567267004,0.05220917135249838,0.1833076053120054,250000.0,8.897805775169468,1400000 +0.3410965490859766,1000.0,0.0,101.16291133903049,3.1952091107882006,-988.8717027526862,0.0014663914921134804,68.6532110225293,1.5398551490581116,2.5265169462585675,0.05168999887884659,0.18248282698575513,250000.0,8.900931853993203,1450000 +0.339427957535981,1000.0,0.0,92.27717619950896,3.127830074489061,-989.5634880468751,0.0018302430824003889,70.13771976154217,1.540636792510757,2.5613346981334284,0.05236778944061718,0.18340826398653082,250000.0,8.900599105717362,1500000 +0.3378143701988447,1000.0,0.0,99.80374224913953,10.32757654858501,-987.3879544860828,-0.0038353560685553223,68.65133872264838,1.5250889930581948,2.5034313097930063,0.05140816463647579,0.18213574311000524,250000.0,8.895057220431756,1550000 +0.342008907217385,1000.0,0.0,100.19237721110188,7.022539748727576,-989.0893630993688,0.0013510333325155448,80.60041506339974,1.5678581703853611,2.7169121806526375,0.05197416481964898,0.18297533865696705,250000.0,8.896307990000214,1600000 +0.3359742564624565,1000.0,0.0,98.93932597416473,10.384658522572824,-990.1386378527887,-0.0008310665324516461,70.61605323287937,1.5223441072404256,2.57326372326377,0.05148517413993521,0.1821432687221153,250000.0,8.89881169109111,1650000 +0.33424538396775694,1000.0,0.0,88.8775356183224,2.9861756179740264,-991.823763369135,0.0008204182712547778,68.10215477161258,1.5216780936765983,2.5332577229690467,0.05275159491901023,0.1842904939652096,250000.0,8.899114912197373,1700000 +0.33842839222848875,1000.0,0.0,94.51785769707138,18.998664491174686,-989.1536248571831,0.0009234580167569144,75.24617199371197,1.55479686657072,2.6605867370700724,0.05231688376069089,0.18343055217418422,250000.0,8.899369421485329,1750000 +0.33452897676169724,1000.0,0.0,96.23642851530607,3.2280424363328257,-994.1245372229091,0.0014449944325536303,68.82950478545955,1.5254106690537907,2.553897522190806,0.052745914506598074,0.1839964431633838,250000.0,8.903376428988299,1800000 +0.3374262922012839,1000.0,0.0,103.06437674991528,3.1351215640824446,-997.4706511499146,-0.002427832889612764,70.86566636714966,1.5390968687224396,2.6091317826843397,0.052556441578152424,0.18365339325820737,250000.0,8.901842312639145,1850000 +0.33632548919200783,1000.0,0.0,102.74145179430731,8.1143781725574,-1000.065435878921,0.0013373385042324685,64.95989793609614,1.511554402834193,2.457296020861857,0.05245231913643874,0.18360816312502973,250000.0,8.903161986167067,1900000 +0.3390178009551746,1000.0,0.0,103.32973714999692,9.307943085419113,-1004.1400500378406,-0.0010719379910454103,66.9412500143065,1.547883771576875,2.5191410122216062,0.05351057885047084,0.18509054601916416,250000.0,8.901682116087985,1950000 +0.3369889227235286,1000.0,0.0,98.41840100259361,5.725701139427933,-1003.5043179663124,0.0012383006845973596,65.98729007003656,1.5193395683157596,2.4726221461153344,0.052545526938755326,0.1836901699911639,250000.0,8.902235615714803,2000000 +0.33374582090914495,1000.0,0.0,101.34734565609773,11.538549183084733,-1002.4435811499037,0.00010501759370786479,66.42991750900346,1.5041601662075716,2.490177802585363,0.05210755004382859,0.18290897983876905,250000.0,8.904120916043203,2050000 +0.3381646905022877,1000.0,0.0,102.14830318921693,5.462231288058775,-1005.6855334960944,-0.0013426316942647017,65.03019911960489,1.5145570675563778,2.4910841659069396,0.05161643439072419,0.18202059485476796,250000.0,8.901596822855943,2100000 +0.3325890554016792,1000.0,0.0,100.16072953966342,9.460721069684658,-1006.0201594531135,5.3608267158258954e-05,64.15405705661885,1.4954307179749018,2.445207863737349,0.05192091242176023,0.18253422916171,250000.0,8.902387936118659,2150000 +0.33404120991408537,1000.0,0.0,99.68463471484591,11.239433257851761,-1008.3429596191377,0.00015640077892688906,67.51428488227981,1.512307195191367,2.547859018137455,0.05279177105422867,0.18405203629854927,250000.0,8.906705565191785,2200000 +0.33423989020645595,1000.0,0.0,100.25023460731246,13.61273563059499,-1008.0621245104894,0.000361862855479101,68.36444583591592,1.5191607201755017,2.5487211718107194,0.051670823111960126,0.1820256863943543,250000.0,8.907195766596127,2250000 +0.3327638653761154,1000.0,0.0,102.398464912467,13.457247636753452,-1007.58839702881,-0.00031104716179892165,66.15409262012653,1.517144539048649,2.5424129980575945,0.05239845869858848,0.18334454705240052,250000.0,8.907560485292453,2300000 +0.33181950992286297,1000.0,0.0,104.5788528178865,4.187931524561107,-1009.2571055053622,0.0011133222936093859,66.26575295635281,1.5030415648233946,2.5133509673285315,0.05152294480882899,0.18171555570695389,250000.0,8.900603050445612,2350000 +0.33493839451849516,1000.0,0.0,102.68137338776772,9.784358047283117,-1010.5012814892584,-0.001421563265975563,66.18729753360655,1.51668216697933,2.532389552760155,0.052337250008302014,0.18321257487093573,250000.0,8.907399242965365,2400000 +0.3319277310466735,1000.0,0.0,103.21965361103803,3.4075104760794424,-1009.7034756689544,0.00025284112086514603,68.04271456844366,1.5139116758954312,2.5548111374998244,0.05149367043237836,0.1818037962021553,250000.0,8.903300484555713,2450000 +0.33130287418841536,1000.0,0.0,103.9442930233551,7.955741854169937,-1010.2993777648906,0.0006549505542591518,64.79804389816158,1.5074260022652162,2.4770129748654144,0.0514552606571338,0.18152399389977675,250000.0,8.91276372415074,2500000 +0.33590659453154287,1000.0,0.0,104.23608968102907,8.445244940171955,-1013.5216585632343,0.00011460502285509864,66.40191829177952,1.520133489555153,2.535728294032818,0.05165976641411419,0.18193958748106437,250000.0,8.909476885204603,2550000 +0.3338498123425178,1000.0,0.0,106.07906277754233,3.276068349882139,-1015.2656848498599,0.00011646651811897224,64.72874057567601,1.5134040598237206,2.4867076241040453,0.052449662924507014,0.18302997419757486,250000.0,8.909877962614388,2600000 +0.32977877919018217,1000.0,0.0,105.88812236261651,3.3951260780679906,-1014.54095157226,0.00011497344864532299,66.445928492812,1.5152549255108811,2.5245485156619463,0.051756517745301246,0.1819328187671266,250000.0,8.90871971824673,2650000 +0.3349707734805346,1000.0,0.0,104.52306941604952,8.890171275824358,-1015.5859690185673,-0.0003231106904521589,66.36770251476214,1.5351594991970028,2.5549596935152676,0.05241625498896369,0.18307183058705453,250000.0,8.908254191593677,2700000 +0.3340231299370574,1000.0,0.0,106.17867448195857,3.235338470911042,-1016.6310770446825,-0.001160513943303368,69.1024010899727,1.5443591296780006,2.615519740383612,0.05191357272194745,0.182217447444887,250000.0,8.90976909790378,2750000 +0.3358682731091989,1000.0,0.0,104.82416302113029,4.355076554993931,-1016.9625367785591,0.0021954394645430507,66.90112910522353,1.5449634176349458,2.538448782497626,0.05207301395209928,0.1825013110563076,250000.0,8.90838527546806,2800000 +0.33541598524451477,1000.0,0.0,105.69875068499283,3.3505732343914127,-1017.9502348083587,-0.0005576423654891733,66.82281878975034,1.5501152191412548,2.5709245627009825,0.05188294195153205,0.18218449803111428,250000.0,8.908146754982132,2850000 +0.336099375733727,1000.0,0.0,105.6728789825798,5.884763558449427,-1018.3840957202124,-5.754411689934823e-05,68.60974424922944,1.5539053872942996,2.5775791523134366,0.05190927774334571,0.18214642203499187,250000.0,8.915385551983952,2900000 +0.33288346129834623,1000.0,0.0,105.54847513007708,3.7032953866140907,-1017.1320915759309,0.0013525766239129054,68.33215829578437,1.549705433433047,2.6082213208687786,0.0519518637200071,0.18232050544052403,250000.0,8.912644512952452,2950000 +0.31891921836971926,1000.0,0.0,105.5342336528535,5.319969972023396,-1016.0174644177276,-0.007944895742051197,66.50081700801978,1.5438534758877647,2.5492667937780107,0.051772038202776406,0.182074058124756,250000.0,8.909888668133508,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/tb/events.out.tfevents.1773706566.aysin.2860517.0 b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/tb/events.out.tfevents.1773706566.aysin.2860517.0 new file mode 100644 index 0000000000000000000000000000000000000000..bbd318e19b7a7fb57d474e42947564fad3ecc45b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0317-001604/record/tb/events.out.tfevents.1773706566.aysin.2860517.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ff3dbe28e67a96601d6f15f3aabbbb570e890aa69632c3b354af4a8b2f9ed0 +size 53323 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..61c439b5b4fc4e9396d45e2dd95b2bc8d92fa4bd --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2604f3d36474c2e8409601c138592ea6ce4ff8ce795ff5d66ef1a3faa4ccae6 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..61dcaf66101553f5429c8f21cc7b2d77cfd4ffba --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0119_105550_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c68637cf8a82ddbd980e0f27262ba7aaf5d3fc8d20f928e6ba499dbe949fa5 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index f2893abfde7931a5c623493cd901292133e623e6..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9454bd029ddbecb10571f8badab5431bece4bd3a3fb902b1177d08eda7f52e6f -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 67df837930f669330a001545c3d16cc182d32944..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_191301_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:82ee0881c3ce819bdefa93a3bb464c12e171a96429adb06ea9dc6f26187eb3ba -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..51b32d70c16fdd27671f4514b53743aa4d95f9b6 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2236ad17039cf09473bc1a6b754116ebc6aa75f7839dd8fe8f57af08b507f5a6 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f2d43e6fa1c42328c59b4c5f7fff1badf1d877b --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_1_0117_155031_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5216ccd816761add8be5f24671cdf9ad736af080d52ef06be96fbe723c767aaf +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index f2893abfde7931a5c623493cd901292133e623e6..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9454bd029ddbecb10571f8badab5431bece4bd3a3fb902b1177d08eda7f52e6f -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 534f6796bb52e62fb3411067000656e1e1e9e88f..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_42_0330_093526_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:30caf1301f9c53d47ee92e8fdfb1d843ccf6543da70f9a98d2da41b1c8dcdb6f -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8184d6decad0ee59c8694c6e13a65011ac296c3 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94dd644a7b5bb6d558bb6e3712e0449983b46d155d44c9f1891358e97b51647 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e361490fcf54a26cfaa8e07c0d6cf3634766ae64 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0119_183434_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3df0c0c51d93aab510e2f13144ae206ac6d95734640a61ea0fdabd8eb79731f3 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index de5c688af835a26924691ee16228d915f123c7bb..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8da2307aa2b521f76dccf41c7113b998e63322095ec3145fdbaa2feee33c6fe4 -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 1812a3418829e2531115baff2ec3eaf9a50beea9..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/diffusion/seed_456_0303_112704_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4a92162a5a14d412f705b1c0411bdce373030ec31577c51669f51f6f45798dc1 -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt rename to hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..db1118e19c034d3fd567316a3442e568c4f0f8f3 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0128_113342_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b607fb0d0650a5eb1bf8c271067f7499d40d6848cffe300ffe28bb028cb87c0 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index f2893abfde7931a5c623493cd901292133e623e6..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9454bd029ddbecb10571f8badab5431bece4bd3a3fb902b1177d08eda7f52e6f -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index a40065ef255b3eaef5303aba47956c2e19c90cd0..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/kde/seed_123_0329_044659_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5640913742f055674c1cbb1ea8af8c1d01f5dd13eba5f926c3a32069e27e04cd -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..97aa82f9e1a164ceccbd91f3ec916be5846c1409 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e946dd3c7f221d1493cbfac8a8db2ae5f61677eb6c9289410543a7a2fa6555 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..47488374cd86b5c5673d3073c7321d832b936a5e --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0128_071619_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79771282229d88c67ec9158dd7a1116b8a9393b620f69b773c2c0960508e336e +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0329_235228_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_42_0329_235228_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..97aa82f9e1a164ceccbd91f3ec916be5846c1409 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e946dd3c7f221d1493cbfac8a8db2ae5f61677eb6c9289410543a7a2fa6555 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..78d9032a5406a0d82d348308a904ac503c2cc177 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0128_155028_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5697ecff7b9e6acacc8a7cb679597e87833ace1ddc23a453744c411bd200b71a +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index de5c688af835a26924691ee16228d915f123c7bb..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8da2307aa2b521f76dccf41c7113b998e63322095ec3145fdbaa2feee33c6fe4 -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 1032655e5080513c6f91edf6058393cf47170b01..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/kde/seed_456_0303_111431_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c6f33114cff70b9ddf55c2c826c145f4f2e39d88a00caa86aae548037a751c0e -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9bc372403b92cb0b58725d1db4919e043001ac1 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4007fdec9fa1dc7515bde64cfd5a951aa871b15b9d3d64ee6fbbcaf77ad8544b +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..e70413d40b69227e94fd7303173065bad255ad38 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_121951_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a31a32912af786795d0e562795a7a4ddf93675353fb9129d83962de7bef3654 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_154924_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0329_154924_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9bc372403b92cb0b58725d1db4919e043001ac1 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4007fdec9fa1dc7515bde64cfd5a951aa871b15b9d3d64ee6fbbcaf77ad8544b +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..66fa8726a90c4c0272e95d6b45ece920f27665b2 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_055909_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5386601293a945bb761ecba8b8c0a47b489594784a78e42e01c6cb74be7c2f59 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index 28f48724d6cae9ca8b7426b4f1a0743a70d65933..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:985fce4adb142d9336a7bfe9897213a2d804919818d6a4055bad9f0aab0eb61c -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index bde38973334e1f3f1ac6f040a236fed0211ed7aa..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0328_182718_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:22e39282c878dc06593c156a6ac476bb3ab29672cd9dc75db6da03b46dfb0cad -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9bc372403b92cb0b58725d1db4919e043001ac1 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4007fdec9fa1dc7515bde64cfd5a951aa871b15b9d3d64ee6fbbcaf77ad8544b +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..90260a196268a01af3df2055a7687be2c4b96ae4 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_185544_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a4a7225358246a2c1ef48dacf6224a84443b2cc95a2d04d2a466f03be051ca +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 84fba2fe2e3f81d452318d8317598f812d87b36f..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:37744295a70e196196065d24fda28c6d07174621a7049158be6a858a755b6ff7 -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_125153_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_123_0329_125153_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4dddc525c1b7017554632b8ee393609f56aa6a9 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c64707a8ee914c5d3f3dd7649eaa5a9bd55b461548a4a264917d608bc939d9 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4071c1b9d5a6d0267d7456fe5670e61756469779 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_182410_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae70eb0d4d1512c4713a3b6b813fbb1c59ca43844227b2cb9c89d2694f50e1d6 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4dddc525c1b7017554632b8ee393609f56aa6a9 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c64707a8ee914c5d3f3dd7649eaa5a9bd55b461548a4a264917d608bc939d9 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt rename to hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..51721fd20c4cb10bda3848d1ef115c22c6b3875a --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_1_0111_215949_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89cb01937eb3b5516a58f3c09c90223ca27606e6d32df60c3b5b38c86c99e9dd +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index 58daca1874a8474936cfaaed6d04c2fcf9f19529..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ce15ac8d1f14e79b4b6d1cc49b2c70f34305a9e091ac9f6057b51229d6ee6b71 -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 589854308b280b4bad853b6980d6bea37d24d2fa..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_42_0328_161817_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cc32d5a4114b58aea83e99f66ebee42b69c426aa39bf14e63bf11bd5a9c21af6 -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d289705e18de02c2c2731ac59dfa6b7c05289e44 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107091839beec2fda8f2d6f5beb73a32ac1d42f7f89e21fb619ccf79011673e5 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7704c3e283a5a5be9a13cc517ab77a2fd468d476 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ffc1a24c2ffe2487b537cffbe99232badf73e1212758f1f084b9f440c37f38 +size 1456 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ac8d1c75bcf3efd051b42587f4cb913dd31a4ba --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0114_204914_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10d77d9ba5446806c485af563ceb19d11025512adb79f35de42afd074bc49db9 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 9bb32db24cc8051c64da31d43d78fd984da82925..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/realnvp/seed_456_0303_183132_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e1771c36277d3069fd5bfdeb1e48173d26829e9a69acb142d1ca880fb86d2613 -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4dddc525c1b7017554632b8ee393609f56aa6a9 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c64707a8ee914c5d3f3dd7649eaa5a9bd55b461548a4a264917d608bc939d9 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7704c3e283a5a5be9a13cc517ab77a2fd468d476 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ffc1a24c2ffe2487b537cffbe99232badf73e1212758f1f084b9f440c37f38 +size 1456 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ef8bf38acff6a55f03cf2ea563069d320f8a7ba --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0129_012441_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5749042e2dba14431a635c817cd2281790013a292a76cb4ac71d2ca60e4810a +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0329_091138_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0329_091138_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index 3354504ee20862421f26814f3336e14ffa5b6294..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/vae/seed_123_0329_091138_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8683094bdefc0eae94168974ea0e2f2cda005170701aefa3ae9932e379b6262 -size 14976 diff --git a/hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt similarity index 100% rename from hopper_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_104310_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt rename to hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7704c3e283a5a5be9a13cc517ab77a2fd468d476 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ffc1a24c2ffe2487b537cffbe99232badf73e1212758f1f084b9f440c37f38 +size 1456 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab55328e895c28da0363ceae8f79e31fb86c4fac --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0129_012506_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c150b416f88c1e44a07a54dbfe2b0aa62ce02c5df1e06782f27cd2de04b0d2c0 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index 58daca1874a8474936cfaaed6d04c2fcf9f19529..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ce15ac8d1f14e79b4b6d1cc49b2c70f34305a9e091ac9f6057b51229d6ee6b71 -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index d50871b8e4eb406c76a3b835a4ac83bfce5e9977..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/vae/seed_42_0328_144032_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a8f8ee093001549a4292820d103181f2fbc88cf33745fde34f20d84889aa265f -size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4dddc525c1b7017554632b8ee393609f56aa6a9 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c64707a8ee914c5d3f3dd7649eaa5a9bd55b461548a4a264917d608bc939d9 +size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..7704c3e283a5a5be9a13cc517ab77a2fd468d476 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ffc1a24c2ffe2487b537cffbe99232badf73e1212758f1f084b9f440c37f38 +size 1456 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d2b3ccfbc54ffff4b390d4fb8b48d2fdcf9dc72 --- /dev/null +++ b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0129_012415_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0906400b5f590aa1ad4be3e6addc6791605e50f1e3f8c72914d6f693bf346202 +size 1417922 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt deleted file mode 100644 index f25af3b3940699fb5d38c863c89f4df2daaa52ee..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b3fa0a822bc84e6e8031345df833587617e1c58d389a836f6cc19489a12c2e6a -size 3618342 diff --git a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth b/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth deleted file mode 100644 index e42e3710183684de0a349601f7fb179028f8365c..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mbpo_based/vae/seed_456_0304_014818_hopper_medium_expert_v2_gormpo_sparse_78/policy_hopper-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e43141d15c4f3a9c69c8aec7cef4c73b99b32167ad0567ef59392b9f443e00f1 -size 1417922 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/consoleout_backup.txt b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/consoleout_backup.txt deleted file mode 100644 index 3c064505e95269473a6f1c59cf71fdd4548df8f9..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/consoleout_backup.txt +++ /dev/null @@ -1,39 +0,0 @@ -num rollout transitions: 246321, reward mean: 3.2922 -num rollout transitions: 249046, reward mean: 3.4104 -num rollout transitions: 249385, reward mean: 3.4258 -num rollout transitions: 249305, reward mean: 3.4649 -num rollout transitions: 249334, reward mean: 3.4735 -num rollout transitions: 249347, reward mean: 3.4937 -num rollout transitions: 249254, reward mean: 3.4778 -num rollout transitions: 249383, reward mean: 3.4763 -num rollout transitions: 249332, reward mean: 3.4586 -num rollout transitions: 249285, reward mean: 3.5015 -num rollout transitions: 249332, reward mean: 3.4704 -num rollout transitions: 249333, reward mean: 3.4828 -num rollout transitions: 249391, reward mean: 3.4500 -num rollout transitions: 249359, reward mean: 3.5146 -num rollout transitions: 249390, reward mean: 3.5303 -num rollout transitions: 249370, reward mean: 3.5017 -num rollout transitions: 249378, reward mean: 3.5136 -num rollout transitions: 249283, reward mean: 3.4779 -num rollout transitions: 249381, reward mean: 3.5343 -num rollout transitions: 249311, reward mean: 3.5321 -num rollout transitions: 249318, reward mean: 3.5174 -num rollout transitions: 249380, reward mean: 3.5197 -num rollout transitions: 249383, reward mean: 3.4979 -num rollout transitions: 249246, reward mean: 3.4760 -num rollout transitions: 249381, reward mean: 3.5215 -num rollout transitions: 249391, reward mean: 3.5078 -num rollout transitions: 249364, reward mean: 3.5369 -num rollout transitions: 249334, reward mean: 3.5104 -num rollout transitions: 249370, reward mean: 3.5451 -num rollout transitions: 249341, reward mean: 3.5344 -num rollout transitions: 249301, reward mean: 3.5348 -num rollout transitions: 249430, reward mean: 3.5254 -num rollout transitions: 249338, reward mean: 3.5222 -num rollout transitions: 249368, reward mean: 3.5070 -num rollout transitions: 249294, reward mean: 3.5251 -num rollout transitions: 249394, reward mean: 3.5305 -num rollout transitions: 249437, reward mean: 3.5110 -num rollout transitions: 249268, reward mean: 3.5206 -num rollout transitions: 249342, reward mean: 3.4984 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/policy_training_progress.csv deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/tb/events.out.tfevents.1778011898.aysin.1174952.0 b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/tb/events.out.tfevents.1778011898.aysin.1174952.0 deleted file mode 100644 index 95a977b874469246dd46ce9ebd29fada5b3653c4..0000000000000000000000000000000000000000 --- a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/tb/events.out.tfevents.1778011898.aysin.1174952.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:33f65d396bfa56e6f9ed70a4dfb1a59fc17415d533cf7c916bb6551e548659eb -size 1850 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/checkpoint/policy.pth b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/checkpoint/policy.pth new file mode 100644 index 0000000000000000000000000000000000000000..17baa8928a76a490c0b1ccb6406a86cc0b7e0cbd --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/checkpoint/policy.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4aeee9d525bc2805a676796e25126e47717bc098daa74a909820b31b80bfd3 +size 1410514 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/dynamics.pth b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/dynamics.pth new file mode 100644 index 0000000000000000000000000000000000000000..20ad74251b65e1b4ed054441db379f03b2c67c31 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/dynamics.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a72cc6ae5ee81654e43d5560b504b7710ed0a247ae251b07902db8d3fdb0e2 +size 7199148 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/mu.npy b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/mu.npy new file mode 100644 index 0000000000000000000000000000000000000000..b41f8b92999aee91990eea70c9fb798b10d1de88 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/mu.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771e41115c416b5fea8018b492291e7b91a3130084e95a851dae4861ee5fc19a +size 184 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/policy.pth b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/policy.pth new file mode 100644 index 0000000000000000000000000000000000000000..17baa8928a76a490c0b1ccb6406a86cc0b7e0cbd --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/policy.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4aeee9d525bc2805a676796e25126e47717bc098daa74a909820b31b80bfd3 +size 1410514 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/std.npy b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/std.npy new file mode 100644 index 0000000000000000000000000000000000000000..8682faf7a528c5abd00701303775802fb333f14d --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/model/std.npy @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72dd959d361057b555115fcdf65216ab9a531a3f6497aa7d38ad94eb7281c80c +size 184 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/consoleout_backup.txt b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..7e52649ba37941b6816988a51d2aa84a6461cf56 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 246321, reward mean: 3.2922 +num rollout transitions: 249046, reward mean: 3.4104 +num rollout transitions: 249385, reward mean: 3.4258 +num rollout transitions: 249305, reward mean: 3.4649 +num rollout transitions: 249334, reward mean: 3.4735 +num rollout transitions: 249347, reward mean: 3.4937 +num rollout transitions: 249254, reward mean: 3.4778 +num rollout transitions: 249383, reward mean: 3.4763 +num rollout transitions: 249332, reward mean: 3.4586 +num rollout transitions: 249285, reward mean: 3.5015 +num rollout transitions: 249332, reward mean: 3.4704 +num rollout transitions: 249333, reward mean: 3.4828 +num rollout transitions: 249391, reward mean: 3.4500 +num rollout transitions: 249359, reward mean: 3.5146 +num rollout transitions: 249390, reward mean: 3.5303 +num rollout transitions: 249370, reward mean: 3.5017 +num rollout transitions: 249378, reward mean: 3.5136 +num rollout transitions: 249283, reward mean: 3.4779 +num rollout transitions: 249381, reward mean: 3.5343 +num rollout transitions: 249311, reward mean: 3.5321 +num rollout transitions: 249318, reward mean: 3.5174 +num rollout transitions: 249380, reward mean: 3.5197 +num rollout transitions: 249383, reward mean: 3.4979 +num rollout transitions: 249246, reward mean: 3.4760 +num rollout transitions: 249381, reward mean: 3.5215 +num rollout transitions: 249391, reward mean: 3.5078 +num rollout transitions: 249364, reward mean: 3.5369 +num rollout transitions: 249334, reward mean: 3.5104 +num rollout transitions: 249370, reward mean: 3.5451 +num rollout transitions: 249341, reward mean: 3.5344 +num rollout transitions: 249301, reward mean: 3.5348 +num rollout transitions: 249430, reward mean: 3.5254 +num rollout transitions: 249338, reward mean: 3.5222 +num rollout transitions: 249368, reward mean: 3.5070 +num rollout transitions: 249294, reward mean: 3.5251 +num rollout transitions: 249394, reward mean: 3.5305 +num rollout transitions: 249437, reward mean: 3.5110 +num rollout transitions: 249268, reward mean: 3.5206 +num rollout transitions: 249342, reward mean: 3.4984 +num rollout transitions: 249357, reward mean: 3.4951 +num rollout transitions: 249370, reward mean: 3.5161 +num rollout transitions: 249367, reward mean: 3.5124 +num rollout transitions: 249337, reward mean: 3.4819 +num rollout transitions: 249317, reward mean: 3.4967 +num rollout transitions: 249272, reward mean: 3.4712 +num rollout transitions: 249355, reward mean: 3.5162 +num rollout transitions: 249405, reward mean: 3.5065 +num rollout transitions: 249333, reward mean: 3.4942 +num rollout transitions: 249335, reward mean: 3.4917 +num rollout transitions: 249310, reward mean: 3.5153 +---------------------------------------------------------------------------------- +| alpha | 0.267 | +| eval/episode_length | 30.1 | +| eval/episode_length_std | 0.544 | +| eval/normalized_episode_reward | 2.14 | +| eval/normalized_episode_reward_std | 0.656 | +| loss/actor | -370 | +| loss/alpha | -0.792 | +| loss/critic | 17.5 | +| penalty/lcb_mean | 0.487 | +| penalty/lcb_std | 0.668 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.5 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249265, reward mean: 3.4962 +num rollout transitions: 249379, reward mean: 3.4836 +num rollout transitions: 249297, reward mean: 3.4948 +num rollout transitions: 249201, reward mean: 3.4944 +num rollout transitions: 249332, reward mean: 3.4670 +num rollout transitions: 249331, reward mean: 3.5053 +num rollout transitions: 249257, reward mean: 3.5004 +num rollout transitions: 249284, reward mean: 3.5059 +num rollout transitions: 249350, reward mean: 3.4900 +num rollout transitions: 249440, reward mean: 3.5011 +num rollout transitions: 249296, reward mean: 3.4961 +num rollout transitions: 249327, reward mean: 3.4834 +num rollout transitions: 249356, reward mean: 3.4936 +num rollout transitions: 249292, reward mean: 3.4542 +num rollout transitions: 249236, reward mean: 3.4892 +num rollout transitions: 249290, reward mean: 3.4696 +num rollout transitions: 249242, reward mean: 3.4525 +num rollout transitions: 249361, reward mean: 3.4695 +num rollout transitions: 249330, reward mean: 3.5038 +num rollout transitions: 249306, reward mean: 3.4564 +num rollout transitions: 249286, reward mean: 3.4721 +num rollout transitions: 249335, reward mean: 3.4737 +num rollout transitions: 249324, reward mean: 3.4478 +num rollout transitions: 249277, reward mean: 3.4677 +num rollout transitions: 249283, reward mean: 3.4636 +num rollout transitions: 249327, reward mean: 3.4367 +num rollout transitions: 249338, reward mean: 3.4519 +num rollout transitions: 249325, reward mean: 3.4355 +num rollout transitions: 249350, reward mean: 3.4597 +num rollout transitions: 249310, reward mean: 3.4378 +num rollout transitions: 249252, reward mean: 3.4741 +num rollout transitions: 249364, reward mean: 3.4641 +num rollout transitions: 249346, reward mean: 3.4395 +num rollout transitions: 249467, reward mean: 3.4478 +num rollout transitions: 249343, reward mean: 3.4395 +num rollout transitions: 249308, reward mean: 3.4440 +num rollout transitions: 249250, reward mean: 3.4354 +num rollout transitions: 249212, reward mean: 3.4358 +num rollout transitions: 249378, reward mean: 3.4616 +num rollout transitions: 249328, reward mean: 3.4579 +num rollout transitions: 249317, reward mean: 3.4261 +num rollout transitions: 249339, reward mean: 3.4270 +num rollout transitions: 249312, reward mean: 3.4927 +num rollout transitions: 249330, reward mean: 3.4495 +num rollout transitions: 249372, reward mean: 3.4402 +num rollout transitions: 249360, reward mean: 3.4411 +num rollout transitions: 249289, reward mean: 3.4763 +num rollout transitions: 249288, reward mean: 3.4665 +num rollout transitions: 249307, reward mean: 3.4462 +num rollout transitions: 249355, reward mean: 3.4529 +---------------------------------------------------------------------------------- +| alpha | 0.0925 | +| eval/episode_length | 57.5 | +| eval/episode_length_std | 1.05 | +| eval/normalized_episode_reward | 3.93 | +| eval/normalized_episode_reward_std | 0.688 | +| loss/actor | -454 | +| loss/alpha | -0.0409 | +| loss/critic | 16.5 | +| penalty/lcb_mean | 0.381 | +| penalty/lcb_std | 0.675 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.47 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249253, reward mean: 3.4409 +num rollout transitions: 249326, reward mean: 3.4456 +num rollout transitions: 249300, reward mean: 3.4720 +num rollout transitions: 249322, reward mean: 3.4348 +num rollout transitions: 249335, reward mean: 3.4347 +num rollout transitions: 249248, reward mean: 3.4442 +num rollout transitions: 249324, reward mean: 3.4282 +num rollout transitions: 249295, reward mean: 3.4458 +num rollout transitions: 249382, reward mean: 3.4332 +num rollout transitions: 249290, reward mean: 3.4553 +num rollout transitions: 249332, reward mean: 3.4347 +num rollout transitions: 249379, reward mean: 3.4486 +num rollout transitions: 249300, reward mean: 3.4299 +num rollout transitions: 249198, reward mean: 3.4305 +num rollout transitions: 249272, reward mean: 3.4293 +num rollout transitions: 249253, reward mean: 3.4298 +num rollout transitions: 249276, reward mean: 3.4380 +num rollout transitions: 249287, reward mean: 3.4535 +num rollout transitions: 249390, reward mean: 3.4431 +num rollout transitions: 249316, reward mean: 3.4594 +num rollout transitions: 249306, reward mean: 3.4457 +num rollout transitions: 249374, reward mean: 3.4431 +num rollout transitions: 249290, reward mean: 3.4289 +num rollout transitions: 249302, reward mean: 3.4407 +num rollout transitions: 249292, reward mean: 3.4161 +num rollout transitions: 249268, reward mean: 3.4537 +num rollout transitions: 249289, reward mean: 3.4149 +num rollout transitions: 249222, reward mean: 3.4432 +num rollout transitions: 249255, reward mean: 3.4430 +num rollout transitions: 249380, reward mean: 3.4397 +num rollout transitions: 249308, reward mean: 3.4363 +num rollout transitions: 249333, reward mean: 3.4535 +num rollout transitions: 249297, reward mean: 3.4105 +num rollout transitions: 249308, reward mean: 3.4304 +num rollout transitions: 249340, reward mean: 3.4058 +num rollout transitions: 249340, reward mean: 3.4202 +num rollout transitions: 249337, reward mean: 3.4446 +num rollout transitions: 249328, reward mean: 3.4100 +num rollout transitions: 249294, reward mean: 3.4145 +num rollout transitions: 249383, reward mean: 3.4237 +num rollout transitions: 249303, reward mean: 3.4273 +num rollout transitions: 249312, reward mean: 3.4004 +num rollout transitions: 249244, reward mean: 3.4052 +num rollout transitions: 249247, reward mean: 3.3995 +num rollout transitions: 249306, reward mean: 3.3780 +num rollout transitions: 249313, reward mean: 3.3694 +num rollout transitions: 249114, reward mean: 3.3508 +num rollout transitions: 249203, reward mean: 3.3756 +num rollout transitions: 249336, reward mean: 3.3598 +num rollout transitions: 249284, reward mean: 3.3866 +---------------------------------------------------------------------------------- +| alpha | 0.084 | +| eval/episode_length | 41.9 | +| eval/episode_length_std | 1.18 | +| eval/normalized_episode_reward | 2.8 | +| eval/normalized_episode_reward_std | 0.688 | +| loss/actor | -370 | +| loss/alpha | -0.0115 | +| loss/critic | 12.6 | +| penalty/lcb_mean | 0.34 | +| penalty/lcb_std | 0.532 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.43 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249247, reward mean: 3.3911 +num rollout transitions: 249256, reward mean: 3.3713 +num rollout transitions: 249231, reward mean: 3.3543 +num rollout transitions: 249346, reward mean: 3.3771 +num rollout transitions: 249281, reward mean: 3.3842 +num rollout transitions: 249345, reward mean: 3.3656 +num rollout transitions: 249334, reward mean: 3.3788 +num rollout transitions: 249377, reward mean: 3.3743 +num rollout transitions: 249241, reward mean: 3.3689 +num rollout transitions: 249312, reward mean: 3.4003 +num rollout transitions: 249311, reward mean: 3.4027 +num rollout transitions: 249326, reward mean: 3.3858 +num rollout transitions: 249371, reward mean: 3.4097 +num rollout transitions: 249254, reward mean: 3.3705 +num rollout transitions: 249336, reward mean: 3.3643 +num rollout transitions: 249368, reward mean: 3.4076 +num rollout transitions: 249282, reward mean: 3.3798 +num rollout transitions: 249340, reward mean: 3.3962 +num rollout transitions: 249315, reward mean: 3.3952 +num rollout transitions: 249312, reward mean: 3.3917 +num rollout transitions: 249256, reward mean: 3.3790 +num rollout transitions: 249382, reward mean: 3.4007 +num rollout transitions: 249362, reward mean: 3.3821 +num rollout transitions: 249288, reward mean: 3.3745 +num rollout transitions: 249293, reward mean: 3.3941 +num rollout transitions: 249244, reward mean: 3.3709 +num rollout transitions: 249254, reward mean: 3.3904 +num rollout transitions: 249292, reward mean: 3.3858 +num rollout transitions: 249359, reward mean: 3.3786 +num rollout transitions: 249373, reward mean: 3.3834 +num rollout transitions: 249341, reward mean: 3.4001 +num rollout transitions: 249276, reward mean: 3.3908 +num rollout transitions: 249261, reward mean: 3.3916 +num rollout transitions: 249327, reward mean: 3.4016 +num rollout transitions: 249306, reward mean: 3.3775 +num rollout transitions: 249245, reward mean: 3.3870 +num rollout transitions: 249348, reward mean: 3.3640 +num rollout transitions: 249279, reward mean: 3.3856 +num rollout transitions: 249380, reward mean: 3.3860 +num rollout transitions: 249358, reward mean: 3.3991 +num rollout transitions: 249280, reward mean: 3.3792 +num rollout transitions: 249322, reward mean: 3.3966 +num rollout transitions: 249253, reward mean: 3.4134 +num rollout transitions: 249310, reward mean: 3.3718 +num rollout transitions: 249290, reward mean: 3.3482 +num rollout transitions: 249284, reward mean: 3.4020 +num rollout transitions: 249300, reward mean: 3.4159 +num rollout transitions: 249304, reward mean: 3.4016 +num rollout transitions: 249347, reward mean: 3.4010 +num rollout transitions: 249359, reward mean: 3.3929 +---------------------------------------------------------------------------------- +| alpha | 0.0692 | +| eval/episode_length | 32 | +| eval/episode_length_std | 0.582 | +| eval/normalized_episode_reward | 2.24 | +| eval/normalized_episode_reward_std | 0.654 | +| loss/actor | -333 | +| loss/alpha | -0.0262 | +| loss/critic | 8.71 | +| penalty/lcb_mean | 0.294 | +| penalty/lcb_std | 0.481 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.39 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249351, reward mean: 3.3764 +num rollout transitions: 249316, reward mean: 3.3972 +num rollout transitions: 249262, reward mean: 3.4031 +num rollout transitions: 249352, reward mean: 3.3886 +num rollout transitions: 249356, reward mean: 3.3884 +num rollout transitions: 249279, reward mean: 3.3912 +num rollout transitions: 249310, reward mean: 3.3867 +num rollout transitions: 249234, reward mean: 3.3987 +num rollout transitions: 249243, reward mean: 3.3795 +num rollout transitions: 249249, reward mean: 3.4185 +num rollout transitions: 249311, reward mean: 3.3951 +num rollout transitions: 249274, reward mean: 3.4033 +num rollout transitions: 249418, reward mean: 3.3756 +num rollout transitions: 249341, reward mean: 3.3885 +num rollout transitions: 249259, reward mean: 3.3947 +num rollout transitions: 249340, reward mean: 3.3943 +num rollout transitions: 249342, reward mean: 3.3833 +num rollout transitions: 249240, reward mean: 3.3659 +num rollout transitions: 249228, reward mean: 3.3917 +num rollout transitions: 249335, reward mean: 3.4003 +num rollout transitions: 249333, reward mean: 3.4078 +num rollout transitions: 249342, reward mean: 3.3983 +num rollout transitions: 249417, reward mean: 3.3890 +num rollout transitions: 249245, reward mean: 3.3906 +num rollout transitions: 249347, reward mean: 3.4008 +num rollout transitions: 249359, reward mean: 3.3833 +num rollout transitions: 249251, reward mean: 3.4012 +num rollout transitions: 249274, reward mean: 3.3903 +num rollout transitions: 249340, reward mean: 3.3914 +num rollout transitions: 249307, reward mean: 3.3830 +num rollout transitions: 249364, reward mean: 3.3780 +num rollout transitions: 249358, reward mean: 3.4192 +num rollout transitions: 249340, reward mean: 3.3934 +num rollout transitions: 249336, reward mean: 3.3666 +num rollout transitions: 249315, reward mean: 3.4104 +num rollout transitions: 249262, reward mean: 3.4000 +num rollout transitions: 249193, reward mean: 3.4039 +num rollout transitions: 249344, reward mean: 3.3876 +num rollout transitions: 249363, reward mean: 3.4076 +num rollout transitions: 249298, reward mean: 3.3939 +num rollout transitions: 249231, reward mean: 3.3909 +num rollout transitions: 249336, reward mean: 3.3817 +num rollout transitions: 249286, reward mean: 3.3921 +num rollout transitions: 249275, reward mean: 3.3625 +num rollout transitions: 249376, reward mean: 3.3717 +num rollout transitions: 249324, reward mean: 3.3910 +num rollout transitions: 249275, reward mean: 3.3998 +num rollout transitions: 249295, reward mean: 3.3642 +num rollout transitions: 249357, reward mean: 3.3764 +num rollout transitions: 249185, reward mean: 3.3359 +---------------------------------------------------------------------------------- +| alpha | 0.0512 | +| eval/episode_length | 34.7 | +| eval/episode_length_std | 1.67 | +| eval/normalized_episode_reward | 2.41 | +| eval/normalized_episode_reward_std | 0.71 | +| loss/actor | -317 | +| loss/alpha | -0.0348 | +| loss/critic | 6.23 | +| penalty/lcb_mean | 0.243 | +| penalty/lcb_std | 0.426 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.39 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249299, reward mean: 3.4365 +num rollout transitions: 249354, reward mean: 3.3978 +num rollout transitions: 249317, reward mean: 3.4174 +num rollout transitions: 249282, reward mean: 3.3961 +num rollout transitions: 249304, reward mean: 3.4079 +num rollout transitions: 249340, reward mean: 3.3947 +num rollout transitions: 249274, reward mean: 3.3765 +num rollout transitions: 249358, reward mean: 3.4129 +num rollout transitions: 249318, reward mean: 3.3934 +num rollout transitions: 249293, reward mean: 3.3948 +num rollout transitions: 249249, reward mean: 3.3781 +num rollout transitions: 249298, reward mean: 3.3775 +num rollout transitions: 249263, reward mean: 3.3902 +num rollout transitions: 249343, reward mean: 3.3901 +num rollout transitions: 249262, reward mean: 3.3739 +num rollout transitions: 249379, reward mean: 3.3813 +num rollout transitions: 249352, reward mean: 3.3764 +num rollout transitions: 249294, reward mean: 3.3875 +num rollout transitions: 249380, reward mean: 3.3629 +num rollout transitions: 249350, reward mean: 3.3554 +num rollout transitions: 249313, reward mean: 3.3615 +num rollout transitions: 249327, reward mean: 3.3712 +num rollout transitions: 249382, reward mean: 3.3571 +num rollout transitions: 249335, reward mean: 3.3775 +num rollout transitions: 249362, reward mean: 3.3925 +num rollout transitions: 249363, reward mean: 3.3843 +num rollout transitions: 249363, reward mean: 3.3698 +num rollout transitions: 249352, reward mean: 3.3833 +num rollout transitions: 249332, reward mean: 3.3836 +num rollout transitions: 249300, reward mean: 3.3759 +num rollout transitions: 249310, reward mean: 3.3829 +num rollout transitions: 249292, reward mean: 3.3958 +num rollout transitions: 249391, reward mean: 3.3637 +num rollout transitions: 249365, reward mean: 3.3807 +num rollout transitions: 249337, reward mean: 3.3961 +num rollout transitions: 249347, reward mean: 3.3540 +num rollout transitions: 249256, reward mean: 3.3440 +num rollout transitions: 249326, reward mean: 3.3862 +num rollout transitions: 249386, reward mean: 3.3919 +num rollout transitions: 249371, reward mean: 3.3768 +num rollout transitions: 249327, reward mean: 3.3790 +num rollout transitions: 249292, reward mean: 3.4203 +num rollout transitions: 249361, reward mean: 3.3745 +num rollout transitions: 249347, reward mean: 3.3730 +num rollout transitions: 249290, reward mean: 3.3617 +num rollout transitions: 249349, reward mean: 3.3568 +num rollout transitions: 249327, reward mean: 3.3469 +num rollout transitions: 249270, reward mean: 3.3629 +num rollout transitions: 249249, reward mean: 3.3684 +num rollout transitions: 249311, reward mean: 3.3596 +---------------------------------------------------------------------------------- +| alpha | 0.0429 | +| eval/episode_length | 45.8 | +| eval/episode_length_std | 2.28 | +| eval/normalized_episode_reward | 3.04 | +| eval/normalized_episode_reward_std | 0.77 | +| loss/actor | -309 | +| loss/alpha | -0.0112 | +| loss/critic | 6.83 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.413 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.38 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3461 +num rollout transitions: 249335, reward mean: 3.3443 +num rollout transitions: 249287, reward mean: 3.3809 +num rollout transitions: 249386, reward mean: 3.3586 +num rollout transitions: 249287, reward mean: 3.3814 +num rollout transitions: 249384, reward mean: 3.3629 +num rollout transitions: 249270, reward mean: 3.3656 +num rollout transitions: 249299, reward mean: 3.3649 +num rollout transitions: 249368, reward mean: 3.3515 +num rollout transitions: 249260, reward mean: 3.3490 +num rollout transitions: 249298, reward mean: 3.3585 +num rollout transitions: 249348, reward mean: 3.3651 +num rollout transitions: 249351, reward mean: 3.3678 +num rollout transitions: 249338, reward mean: 3.3723 +num rollout transitions: 249341, reward mean: 3.3890 +num rollout transitions: 249333, reward mean: 3.3702 +num rollout transitions: 249385, reward mean: 3.3637 +num rollout transitions: 249281, reward mean: 3.3659 +num rollout transitions: 249298, reward mean: 3.3406 +num rollout transitions: 249405, reward mean: 3.3701 +num rollout transitions: 249300, reward mean: 3.3654 +num rollout transitions: 249376, reward mean: 3.3801 +num rollout transitions: 249280, reward mean: 3.3462 +num rollout transitions: 249303, reward mean: 3.3559 +num rollout transitions: 249225, reward mean: 3.3752 +num rollout transitions: 249326, reward mean: 3.3952 +num rollout transitions: 249323, reward mean: 3.3604 +num rollout transitions: 249292, reward mean: 3.3529 +num rollout transitions: 249320, reward mean: 3.3409 +num rollout transitions: 249373, reward mean: 3.3540 +num rollout transitions: 249321, reward mean: 3.3427 +num rollout transitions: 249267, reward mean: 3.3339 +num rollout transitions: 249337, reward mean: 3.3567 +num rollout transitions: 249214, reward mean: 3.3264 +num rollout transitions: 249285, reward mean: 3.3467 +num rollout transitions: 249279, reward mean: 3.3613 +num rollout transitions: 249317, reward mean: 3.3481 +num rollout transitions: 249318, reward mean: 3.3480 +num rollout transitions: 249297, reward mean: 3.3653 +num rollout transitions: 249253, reward mean: 3.3407 +num rollout transitions: 249310, reward mean: 3.3463 +num rollout transitions: 249333, reward mean: 3.3473 +num rollout transitions: 249251, reward mean: 3.3622 +num rollout transitions: 249364, reward mean: 3.3843 +num rollout transitions: 249289, reward mean: 3.3633 +num rollout transitions: 249341, reward mean: 3.3664 +num rollout transitions: 249254, reward mean: 3.3600 +num rollout transitions: 249326, reward mean: 3.3329 +num rollout transitions: 249255, reward mean: 3.3589 +num rollout transitions: 249323, reward mean: 3.3375 +---------------------------------------------------------------------------------- +| alpha | 0.0378 | +| eval/episode_length | 81.8 | +| eval/episode_length_std | 101 | +| eval/normalized_episode_reward | 6.62 | +| eval/normalized_episode_reward_std | 11.4 | +| loss/actor | -304 | +| loss/alpha | -0.0125 | +| loss/critic | 5.53 | +| penalty/lcb_mean | 0.224 | +| penalty/lcb_std | 0.412 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249268, reward mean: 3.3161 +num rollout transitions: 249352, reward mean: 3.3907 +num rollout transitions: 249313, reward mean: 3.4194 +num rollout transitions: 249347, reward mean: 3.3611 +num rollout transitions: 249342, reward mean: 3.3325 +num rollout transitions: 249326, reward mean: 3.3257 +num rollout transitions: 249317, reward mean: 3.3609 +num rollout transitions: 249317, reward mean: 3.3564 +num rollout transitions: 249323, reward mean: 3.3474 +num rollout transitions: 249374, reward mean: 3.3836 +num rollout transitions: 249320, reward mean: 3.3676 +num rollout transitions: 249296, reward mean: 3.3489 +num rollout transitions: 249296, reward mean: 3.3617 +num rollout transitions: 249251, reward mean: 3.3608 +num rollout transitions: 249301, reward mean: 3.3234 +num rollout transitions: 249290, reward mean: 3.3199 +num rollout transitions: 249289, reward mean: 3.3547 +num rollout transitions: 249291, reward mean: 3.3386 +num rollout transitions: 249217, reward mean: 3.3531 +num rollout transitions: 249402, reward mean: 3.3393 +num rollout transitions: 249272, reward mean: 3.3550 +num rollout transitions: 249415, reward mean: 3.3678 +num rollout transitions: 249340, reward mean: 3.3505 +num rollout transitions: 249300, reward mean: 3.3542 +num rollout transitions: 249365, reward mean: 3.3442 +num rollout transitions: 249312, reward mean: 3.3373 +num rollout transitions: 249309, reward mean: 3.3417 +num rollout transitions: 249312, reward mean: 3.3119 +num rollout transitions: 249238, reward mean: 3.3392 +num rollout transitions: 249343, reward mean: 3.3339 +num rollout transitions: 249311, reward mean: 3.3191 +num rollout transitions: 249341, reward mean: 3.3522 +num rollout transitions: 249323, reward mean: 3.3563 +num rollout transitions: 249345, reward mean: 3.3319 +num rollout transitions: 249322, reward mean: 3.3232 +num rollout transitions: 249234, reward mean: 3.3406 +num rollout transitions: 249375, reward mean: 3.3215 +num rollout transitions: 249305, reward mean: 3.3196 +num rollout transitions: 249328, reward mean: 3.3416 +num rollout transitions: 249342, reward mean: 3.3338 +num rollout transitions: 249339, reward mean: 3.3586 +num rollout transitions: 249342, reward mean: 3.3365 +num rollout transitions: 249307, reward mean: 3.3634 +num rollout transitions: 249424, reward mean: 3.3516 +num rollout transitions: 249411, reward mean: 3.3408 +num rollout transitions: 249286, reward mean: 3.3414 +num rollout transitions: 249374, reward mean: 3.3183 +num rollout transitions: 249300, reward mean: 3.3329 +num rollout transitions: 249372, reward mean: 3.3194 +num rollout transitions: 249311, reward mean: 3.3542 +---------------------------------------------------------------------------------- +| alpha | 0.0362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 0.839 | +| loss/actor | -302 | +| loss/alpha | -0.00826 | +| loss/critic | 7.21 | +| penalty/lcb_mean | 0.228 | +| penalty/lcb_std | 0.429 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249286, reward mean: 3.3544 +num rollout transitions: 249300, reward mean: 3.3175 +num rollout transitions: 249278, reward mean: 3.3498 +num rollout transitions: 249326, reward mean: 3.3377 +num rollout transitions: 249268, reward mean: 3.3515 +num rollout transitions: 249262, reward mean: 3.3563 +num rollout transitions: 249319, reward mean: 3.3858 +num rollout transitions: 249337, reward mean: 3.3769 +num rollout transitions: 249279, reward mean: 3.3520 +num rollout transitions: 249309, reward mean: 3.3667 +num rollout transitions: 249306, reward mean: 3.3500 +num rollout transitions: 249298, reward mean: 3.3610 +num rollout transitions: 249306, reward mean: 3.3187 +num rollout transitions: 249276, reward mean: 3.3318 +num rollout transitions: 249185, reward mean: 3.3344 +num rollout transitions: 249374, reward mean: 3.3543 +num rollout transitions: 249303, reward mean: 3.3720 +num rollout transitions: 249326, reward mean: 3.3374 +num rollout transitions: 249330, reward mean: 3.3439 +num rollout transitions: 249276, reward mean: 3.3344 +num rollout transitions: 249381, reward mean: 3.3305 +num rollout transitions: 249262, reward mean: 3.3398 +num rollout transitions: 249285, reward mean: 3.3739 +num rollout transitions: 249298, reward mean: 3.3139 +num rollout transitions: 249286, reward mean: 3.3458 +num rollout transitions: 249302, reward mean: 3.3352 +num rollout transitions: 249388, reward mean: 3.3484 +num rollout transitions: 249372, reward mean: 3.3390 +num rollout transitions: 249277, reward mean: 3.3446 +num rollout transitions: 249333, reward mean: 3.3215 +num rollout transitions: 249230, reward mean: 3.3389 +num rollout transitions: 249306, reward mean: 3.3614 +num rollout transitions: 249217, reward mean: 3.3228 +num rollout transitions: 249248, reward mean: 3.3545 +num rollout transitions: 249298, reward mean: 3.3073 +num rollout transitions: 249263, reward mean: 3.3922 +num rollout transitions: 249351, reward mean: 3.3776 +num rollout transitions: 249394, reward mean: 3.3633 +num rollout transitions: 249286, reward mean: 3.3675 +num rollout transitions: 249304, reward mean: 3.3439 +num rollout transitions: 249284, reward mean: 3.3573 +num rollout transitions: 249345, reward mean: 3.3263 +num rollout transitions: 249327, reward mean: 3.3310 +num rollout transitions: 249280, reward mean: 3.3738 +num rollout transitions: 249277, reward mean: 3.3447 +num rollout transitions: 249236, reward mean: 3.3204 +num rollout transitions: 249417, reward mean: 3.3335 +num rollout transitions: 249382, reward mean: 3.3234 +num rollout transitions: 249378, reward mean: 3.3403 +num rollout transitions: 249314, reward mean: 3.3235 +---------------------------------------------------------------------------------- +| alpha | 0.0337 | +| eval/episode_length | 421 | +| eval/episode_length_std | 256 | +| eval/normalized_episode_reward | 44 | +| eval/normalized_episode_reward_std | 28.9 | +| loss/actor | -303 | +| loss/alpha | -0.00111 | +| loss/critic | 6.99 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.426 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249384, reward mean: 3.3363 +num rollout transitions: 249283, reward mean: 3.3237 +num rollout transitions: 249287, reward mean: 3.3255 +num rollout transitions: 249406, reward mean: 3.3485 +num rollout transitions: 249339, reward mean: 3.3192 +num rollout transitions: 249336, reward mean: 3.3627 +num rollout transitions: 249222, reward mean: 3.3418 +num rollout transitions: 249375, reward mean: 3.3505 +num rollout transitions: 249357, reward mean: 3.3496 +num rollout transitions: 249288, reward mean: 3.3627 +num rollout transitions: 249314, reward mean: 3.3538 +num rollout transitions: 249312, reward mean: 3.3316 +num rollout transitions: 249340, reward mean: 3.3441 +num rollout transitions: 249328, reward mean: 3.3465 +num rollout transitions: 249305, reward mean: 3.3331 +num rollout transitions: 249222, reward mean: 3.3633 +num rollout transitions: 249341, reward mean: 3.3557 +num rollout transitions: 249359, reward mean: 3.3466 +num rollout transitions: 249345, reward mean: 3.3417 +num rollout transitions: 249332, reward mean: 3.3373 +num rollout transitions: 249309, reward mean: 3.3278 +num rollout transitions: 249309, reward mean: 3.3435 +num rollout transitions: 249296, reward mean: 3.3572 +num rollout transitions: 249384, reward mean: 3.3403 +num rollout transitions: 249340, reward mean: 3.3394 +num rollout transitions: 249285, reward mean: 3.3195 +num rollout transitions: 249257, reward mean: 3.3327 +num rollout transitions: 249273, reward mean: 3.3133 +num rollout transitions: 249320, reward mean: 3.3491 +num rollout transitions: 249359, reward mean: 3.3513 +num rollout transitions: 249391, reward mean: 3.3272 +num rollout transitions: 249333, reward mean: 3.3505 +num rollout transitions: 249360, reward mean: 3.3989 +num rollout transitions: 249408, reward mean: 3.3385 +num rollout transitions: 249280, reward mean: 3.3344 +num rollout transitions: 249345, reward mean: 3.3407 +num rollout transitions: 249359, reward mean: 3.3428 +num rollout transitions: 249282, reward mean: 3.3232 +num rollout transitions: 249230, reward mean: 3.3097 +num rollout transitions: 249375, reward mean: 3.3208 +num rollout transitions: 249292, reward mean: 3.3238 +num rollout transitions: 249266, reward mean: 3.3220 +num rollout transitions: 249340, reward mean: 3.3420 +num rollout transitions: 249361, reward mean: 3.3152 +num rollout transitions: 249300, reward mean: 3.3279 +num rollout transitions: 249306, reward mean: 3.3583 +num rollout transitions: 249131, reward mean: 3.3417 +num rollout transitions: 249303, reward mean: 3.3322 +num rollout transitions: 249323, reward mean: 3.3240 +num rollout transitions: 249209, reward mean: 3.3445 +---------------------------------------------------------------------------------- +| alpha | 0.0333 | +| eval/episode_length | 31 | +| eval/episode_length_std | 0.173 | +| eval/normalized_episode_reward | 1.9 | +| eval/normalized_episode_reward_std | 0.633 | +| loss/actor | -302 | +| loss/alpha | 0.0208 | +| loss/critic | 6.44 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.415 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249356, reward mean: 3.3452 +num rollout transitions: 249307, reward mean: 3.2998 +num rollout transitions: 249339, reward mean: 3.3116 +num rollout transitions: 249289, reward mean: 3.3326 +num rollout transitions: 249381, reward mean: 3.3287 +num rollout transitions: 249321, reward mean: 3.3086 +num rollout transitions: 249333, reward mean: 3.3469 +num rollout transitions: 249294, reward mean: 3.3495 +num rollout transitions: 249304, reward mean: 3.3202 +num rollout transitions: 249377, reward mean: 3.3186 +num rollout transitions: 249353, reward mean: 3.3143 +num rollout transitions: 249365, reward mean: 3.3343 +num rollout transitions: 249324, reward mean: 3.3335 +num rollout transitions: 249372, reward mean: 3.3266 +num rollout transitions: 249415, reward mean: 3.3215 +num rollout transitions: 249314, reward mean: 3.3419 +num rollout transitions: 249300, reward mean: 3.3387 +num rollout transitions: 249213, reward mean: 3.3233 +num rollout transitions: 249263, reward mean: 3.3099 +num rollout transitions: 249319, reward mean: 3.3308 +num rollout transitions: 249385, reward mean: 3.3247 +num rollout transitions: 249260, reward mean: 3.3213 +num rollout transitions: 249339, reward mean: 3.3434 +num rollout transitions: 249340, reward mean: 3.3054 +num rollout transitions: 249359, reward mean: 3.3167 +num rollout transitions: 249292, reward mean: 3.3182 +num rollout transitions: 249314, reward mean: 3.3381 +num rollout transitions: 249262, reward mean: 3.3237 +num rollout transitions: 249295, reward mean: 3.3199 +num rollout transitions: 249268, reward mean: 3.3219 +num rollout transitions: 249323, reward mean: 3.3175 +num rollout transitions: 249317, reward mean: 3.3132 +num rollout transitions: 249293, reward mean: 3.3221 +num rollout transitions: 249381, reward mean: 3.3295 +num rollout transitions: 249335, reward mean: 3.3261 +num rollout transitions: 249296, reward mean: 3.3421 +num rollout transitions: 249307, reward mean: 3.3248 +num rollout transitions: 249348, reward mean: 3.3282 +num rollout transitions: 249377, reward mean: 3.3139 +num rollout transitions: 249314, reward mean: 3.3514 +num rollout transitions: 249281, reward mean: 3.3414 +num rollout transitions: 249338, reward mean: 3.3312 +num rollout transitions: 249408, reward mean: 3.3259 +num rollout transitions: 249305, reward mean: 3.3235 +num rollout transitions: 249197, reward mean: 3.3307 +num rollout transitions: 249309, reward mean: 3.3231 +num rollout transitions: 249319, reward mean: 3.3079 +num rollout transitions: 249273, reward mean: 3.3119 +num rollout transitions: 249287, reward mean: 3.3340 +num rollout transitions: 249303, reward mean: 3.3369 +---------------------------------------------------------------------------------- +| alpha | 0.0339 | +| eval/episode_length | 33 | +| eval/episode_length_std | 0.218 | +| eval/normalized_episode_reward | 1.98 | +| eval/normalized_episode_reward_std | 0.635 | +| loss/actor | -301 | +| loss/alpha | -0.00979 | +| loss/critic | 5.32 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.418 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249304, reward mean: 3.3131 +num rollout transitions: 249290, reward mean: 3.3254 +num rollout transitions: 249261, reward mean: 3.3266 +num rollout transitions: 249310, reward mean: 3.3212 +num rollout transitions: 249411, reward mean: 3.3439 +num rollout transitions: 249277, reward mean: 3.3284 +num rollout transitions: 249369, reward mean: 3.3346 +num rollout transitions: 249304, reward mean: 3.3030 +num rollout transitions: 249270, reward mean: 3.3492 +num rollout transitions: 249369, reward mean: 3.3086 +num rollout transitions: 249274, reward mean: 3.3198 +num rollout transitions: 249263, reward mean: 3.3512 +num rollout transitions: 249342, reward mean: 3.3480 +num rollout transitions: 249333, reward mean: 3.3322 +num rollout transitions: 249308, reward mean: 3.3305 +num rollout transitions: 249207, reward mean: 3.3144 +num rollout transitions: 249321, reward mean: 3.3313 +num rollout transitions: 249333, reward mean: 3.3299 +num rollout transitions: 249375, reward mean: 3.3114 +num rollout transitions: 249265, reward mean: 3.3410 +num rollout transitions: 249288, reward mean: 3.3456 +num rollout transitions: 249397, reward mean: 3.3340 +num rollout transitions: 249389, reward mean: 3.3364 +num rollout transitions: 249322, reward mean: 3.3208 +num rollout transitions: 249299, reward mean: 3.3291 +num rollout transitions: 249243, reward mean: 3.3263 +num rollout transitions: 249351, reward mean: 3.3166 +num rollout transitions: 249288, reward mean: 3.3087 +num rollout transitions: 249324, reward mean: 3.3195 +num rollout transitions: 249250, reward mean: 3.3485 +num rollout transitions: 249384, reward mean: 3.3261 +num rollout transitions: 249283, reward mean: 3.2924 +num rollout transitions: 249229, reward mean: 3.3254 +num rollout transitions: 249318, reward mean: 3.3598 +num rollout transitions: 249287, reward mean: 3.3242 +num rollout transitions: 249223, reward mean: 3.3264 +num rollout transitions: 249271, reward mean: 3.3374 +num rollout transitions: 249398, reward mean: 3.3347 +num rollout transitions: 249324, reward mean: 3.3062 +num rollout transitions: 249294, reward mean: 3.3289 +num rollout transitions: 249296, reward mean: 3.3268 +num rollout transitions: 249292, reward mean: 3.3289 +num rollout transitions: 249298, reward mean: 3.3290 +num rollout transitions: 249262, reward mean: 3.2959 +num rollout transitions: 249354, reward mean: 3.3221 +num rollout transitions: 249365, reward mean: 3.3117 +num rollout transitions: 249331, reward mean: 3.3301 +num rollout transitions: 249319, reward mean: 3.3159 +num rollout transitions: 249275, reward mean: 3.3443 +num rollout transitions: 249259, reward mean: 3.3103 +---------------------------------------------------------------------------------- +| alpha | 0.0336 | +| eval/episode_length | 41 | +| eval/episode_length_std | 0.538 | +| eval/normalized_episode_reward | 2.47 | +| eval/normalized_episode_reward_std | 0.657 | +| loss/actor | -302 | +| loss/alpha | 0.00828 | +| loss/critic | 5.74 | +| penalty/lcb_mean | 0.217 | +| penalty/lcb_std | 0.431 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249371, reward mean: 3.3300 +num rollout transitions: 249326, reward mean: 3.3120 +num rollout transitions: 249410, reward mean: 3.3288 +num rollout transitions: 249326, reward mean: 3.3296 +num rollout transitions: 249301, reward mean: 3.3202 +num rollout transitions: 249296, reward mean: 3.3308 +num rollout transitions: 249302, reward mean: 3.3342 +num rollout transitions: 249355, reward mean: 3.3165 +num rollout transitions: 249373, reward mean: 3.3477 +num rollout transitions: 249328, reward mean: 3.3222 +num rollout transitions: 249357, reward mean: 3.3357 +num rollout transitions: 249208, reward mean: 3.3238 +num rollout transitions: 249390, reward mean: 3.3346 +num rollout transitions: 249275, reward mean: 3.3307 +num rollout transitions: 249355, reward mean: 3.3381 +num rollout transitions: 249286, reward mean: 3.3258 +num rollout transitions: 249249, reward mean: 3.3234 +num rollout transitions: 249360, reward mean: 3.3470 +num rollout transitions: 249374, reward mean: 3.3149 +num rollout transitions: 249317, reward mean: 3.3183 +num rollout transitions: 249374, reward mean: 3.3320 +num rollout transitions: 249372, reward mean: 3.3220 +num rollout transitions: 249323, reward mean: 3.3312 +num rollout transitions: 249365, reward mean: 3.3331 +num rollout transitions: 249304, reward mean: 3.3326 +num rollout transitions: 249306, reward mean: 3.3170 +num rollout transitions: 249405, reward mean: 3.3183 +num rollout transitions: 249368, reward mean: 3.3459 +num rollout transitions: 249300, reward mean: 3.3407 +num rollout transitions: 249260, reward mean: 3.3409 +num rollout transitions: 249334, reward mean: 3.3469 +num rollout transitions: 249350, reward mean: 3.3298 +num rollout transitions: 249283, reward mean: 3.3528 +num rollout transitions: 249236, reward mean: 3.3469 +num rollout transitions: 249396, reward mean: 3.3551 +num rollout transitions: 249351, reward mean: 3.3410 +num rollout transitions: 249292, reward mean: 3.3158 +num rollout transitions: 249296, reward mean: 3.3343 +num rollout transitions: 249385, reward mean: 3.3415 +num rollout transitions: 249358, reward mean: 3.3172 +num rollout transitions: 249410, reward mean: 3.3329 +num rollout transitions: 249411, reward mean: 3.3421 +num rollout transitions: 249292, reward mean: 3.3436 +num rollout transitions: 249348, reward mean: 3.3289 +num rollout transitions: 249306, reward mean: 3.3326 +num rollout transitions: 249255, reward mean: 3.3465 +num rollout transitions: 249339, reward mean: 3.3400 +num rollout transitions: 249271, reward mean: 3.3422 +num rollout transitions: 249309, reward mean: 3.3446 +num rollout transitions: 249313, reward mean: 3.3274 +---------------------------------------------------------------------------------- +| alpha | 0.0349 | +| eval/episode_length | 113 | +| eval/episode_length_std | 0.913 | +| eval/normalized_episode_reward | 8.78 | +| eval/normalized_episode_reward_std | 0.7 | +| loss/actor | -300 | +| loss/alpha | -0.00829 | +| loss/critic | 4.74 | +| penalty/lcb_mean | 0.23 | +| penalty/lcb_std | 0.449 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249320, reward mean: 3.3353 +num rollout transitions: 249350, reward mean: 3.3348 +num rollout transitions: 249275, reward mean: 3.3367 +num rollout transitions: 249338, reward mean: 3.3675 +num rollout transitions: 249372, reward mean: 3.3368 +num rollout transitions: 249295, reward mean: 3.3427 +num rollout transitions: 249332, reward mean: 3.3403 +num rollout transitions: 249289, reward mean: 3.3334 +num rollout transitions: 249289, reward mean: 3.3362 +num rollout transitions: 249275, reward mean: 3.3599 +num rollout transitions: 249397, reward mean: 3.3459 +num rollout transitions: 249280, reward mean: 3.3484 +num rollout transitions: 249245, reward mean: 3.3384 +num rollout transitions: 249388, reward mean: 3.3545 +num rollout transitions: 249295, reward mean: 3.3438 +num rollout transitions: 249322, reward mean: 3.3477 +num rollout transitions: 249316, reward mean: 3.3261 +num rollout transitions: 249304, reward mean: 3.3435 +num rollout transitions: 249291, reward mean: 3.3558 +num rollout transitions: 249250, reward mean: 3.3492 +num rollout transitions: 249243, reward mean: 3.3547 +num rollout transitions: 249242, reward mean: 3.3437 +num rollout transitions: 249368, reward mean: 3.3455 +num rollout transitions: 249314, reward mean: 3.3971 +num rollout transitions: 249317, reward mean: 3.3394 +num rollout transitions: 249311, reward mean: 3.3359 +num rollout transitions: 249270, reward mean: 3.3422 +num rollout transitions: 249364, reward mean: 3.3722 +num rollout transitions: 249307, reward mean: 3.3519 +num rollout transitions: 249289, reward mean: 3.3320 +num rollout transitions: 249328, reward mean: 3.3698 +num rollout transitions: 249309, reward mean: 3.3537 +num rollout transitions: 249256, reward mean: 3.3283 +num rollout transitions: 249343, reward mean: 3.3385 +num rollout transitions: 249352, reward mean: 3.3395 +num rollout transitions: 249357, reward mean: 3.3453 +num rollout transitions: 249219, reward mean: 3.3457 +num rollout transitions: 249304, reward mean: 3.3330 +num rollout transitions: 249363, reward mean: 3.3832 +num rollout transitions: 249312, reward mean: 3.3532 +num rollout transitions: 249272, reward mean: 3.3544 +num rollout transitions: 249344, reward mean: 3.3684 +num rollout transitions: 249343, reward mean: 3.3502 +num rollout transitions: 249353, reward mean: 3.3561 +num rollout transitions: 249365, reward mean: 3.3580 +num rollout transitions: 249281, reward mean: 3.3636 +num rollout transitions: 249363, reward mean: 3.3566 +num rollout transitions: 249401, reward mean: 3.3619 +num rollout transitions: 249366, reward mean: 3.3436 +num rollout transitions: 249303, reward mean: 3.3444 +---------------------------------------------------------------------------------- +| alpha | 0.0326 | +| eval/episode_length | 47.1 | +| eval/episode_length_std | 0.882 | +| eval/normalized_episode_reward | 3.05 | +| eval/normalized_episode_reward_std | 0.678 | +| loss/actor | -301 | +| loss/alpha | -0.00115 | +| loss/critic | 4.25 | +| penalty/lcb_mean | 0.225 | +| penalty/lcb_std | 0.447 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249350, reward mean: 3.3321 +num rollout transitions: 249288, reward mean: 3.3527 +num rollout transitions: 249296, reward mean: 3.3405 +num rollout transitions: 249311, reward mean: 3.3517 +num rollout transitions: 249388, reward mean: 3.3416 +num rollout transitions: 249310, reward mean: 3.3482 +num rollout transitions: 249327, reward mean: 3.3591 +num rollout transitions: 249315, reward mean: 3.3447 +num rollout transitions: 249344, reward mean: 3.3585 +num rollout transitions: 249438, reward mean: 3.3243 +num rollout transitions: 249389, reward mean: 3.3527 +num rollout transitions: 249367, reward mean: 3.3506 +num rollout transitions: 249314, reward mean: 3.3468 +num rollout transitions: 249321, reward mean: 3.3551 +num rollout transitions: 249317, reward mean: 3.3534 +num rollout transitions: 249336, reward mean: 3.3412 +num rollout transitions: 249298, reward mean: 3.3457 +num rollout transitions: 249344, reward mean: 3.3338 +num rollout transitions: 249313, reward mean: 3.3559 +num rollout transitions: 249327, reward mean: 3.3412 +num rollout transitions: 249382, reward mean: 3.3362 +num rollout transitions: 249312, reward mean: 3.3413 +num rollout transitions: 249335, reward mean: 3.3527 +num rollout transitions: 249335, reward mean: 3.3546 +num rollout transitions: 249306, reward mean: 3.3524 +num rollout transitions: 249376, reward mean: 3.3782 +num rollout transitions: 249348, reward mean: 3.3423 +num rollout transitions: 249255, reward mean: 3.3516 +num rollout transitions: 249378, reward mean: 3.3460 +num rollout transitions: 249333, reward mean: 3.3576 +num rollout transitions: 249280, reward mean: 3.3482 +num rollout transitions: 249324, reward mean: 3.3483 +num rollout transitions: 249300, reward mean: 3.3457 +num rollout transitions: 249299, reward mean: 3.3564 +num rollout transitions: 249377, reward mean: 3.3407 +num rollout transitions: 249394, reward mean: 3.3499 +num rollout transitions: 249330, reward mean: 3.3621 +num rollout transitions: 249307, reward mean: 3.3330 +num rollout transitions: 249335, reward mean: 3.3574 +num rollout transitions: 249342, reward mean: 3.3501 +num rollout transitions: 249276, reward mean: 3.3403 +num rollout transitions: 249263, reward mean: 3.3478 +num rollout transitions: 249396, reward mean: 3.3548 +num rollout transitions: 249325, reward mean: 3.3652 +num rollout transitions: 249404, reward mean: 3.3517 +num rollout transitions: 249338, reward mean: 3.3488 +num rollout transitions: 249365, reward mean: 3.3718 +num rollout transitions: 249380, reward mean: 3.3473 +num rollout transitions: 249368, reward mean: 3.3727 +num rollout transitions: 249366, reward mean: 3.3663 +---------------------------------------------------------------------------------- +| alpha | 0.0304 | +| eval/episode_length | 40.8 | +| eval/episode_length_std | 0.776 | +| eval/normalized_episode_reward | 2.67 | +| eval/normalized_episode_reward_std | 0.665 | +| loss/actor | -302 | +| loss/alpha | -0.00697 | +| loss/critic | 4.49 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.459 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249349, reward mean: 3.3719 +num rollout transitions: 249308, reward mean: 3.3410 +num rollout transitions: 249289, reward mean: 3.3675 +num rollout transitions: 249436, reward mean: 3.3476 +num rollout transitions: 249252, reward mean: 3.3603 +num rollout transitions: 249370, reward mean: 3.3536 +num rollout transitions: 249299, reward mean: 3.3351 +num rollout transitions: 249264, reward mean: 3.3522 +num rollout transitions: 249346, reward mean: 3.3569 +num rollout transitions: 249408, reward mean: 3.3299 +num rollout transitions: 249387, reward mean: 3.3367 +num rollout transitions: 249248, reward mean: 3.3413 +num rollout transitions: 249243, reward mean: 3.3494 +num rollout transitions: 249381, reward mean: 3.3385 +num rollout transitions: 249364, reward mean: 3.3317 +num rollout transitions: 249345, reward mean: 3.3497 +num rollout transitions: 249293, reward mean: 3.3618 +num rollout transitions: 249354, reward mean: 3.3573 +num rollout transitions: 249352, reward mean: 3.3426 +num rollout transitions: 249261, reward mean: 3.3579 +num rollout transitions: 249338, reward mean: 3.3517 +num rollout transitions: 249290, reward mean: 3.3068 +num rollout transitions: 249238, reward mean: 3.3592 +num rollout transitions: 249375, reward mean: 3.3709 +num rollout transitions: 249300, reward mean: 3.3459 +num rollout transitions: 249343, reward mean: 3.3756 +num rollout transitions: 249359, reward mean: 3.3612 +num rollout transitions: 249330, reward mean: 3.3355 +num rollout transitions: 249245, reward mean: 3.3641 +num rollout transitions: 249270, reward mean: 3.3428 +num rollout transitions: 249376, reward mean: 3.3660 +num rollout transitions: 249240, reward mean: 3.3526 +num rollout transitions: 249338, reward mean: 3.3365 +num rollout transitions: 249242, reward mean: 3.3390 +num rollout transitions: 249329, reward mean: 3.3694 +num rollout transitions: 249292, reward mean: 3.3534 +num rollout transitions: 249220, reward mean: 3.3690 +num rollout transitions: 249369, reward mean: 3.3421 +num rollout transitions: 249272, reward mean: 3.3678 +num rollout transitions: 249409, reward mean: 3.3552 +num rollout transitions: 249374, reward mean: 3.3465 +num rollout transitions: 249305, reward mean: 3.3399 +num rollout transitions: 249362, reward mean: 3.3326 +num rollout transitions: 249341, reward mean: 3.3629 +num rollout transitions: 249298, reward mean: 3.3417 +num rollout transitions: 249310, reward mean: 3.3586 +num rollout transitions: 249332, reward mean: 3.3637 +num rollout transitions: 249351, reward mean: 3.3533 +num rollout transitions: 249397, reward mean: 3.3511 +num rollout transitions: 249368, reward mean: 3.3577 +---------------------------------------------------------------------------------- +| alpha | 0.0307 | +| eval/episode_length | 655 | +| eval/episode_length_std | 255 | +| eval/normalized_episode_reward | 71.5 | +| eval/normalized_episode_reward_std | 30.2 | +| loss/actor | -302 | +| loss/alpha | -0.011 | +| loss/critic | 4.76 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.467 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249338, reward mean: 3.3385 +num rollout transitions: 249380, reward mean: 3.3433 +num rollout transitions: 249329, reward mean: 3.3379 +num rollout transitions: 249247, reward mean: 3.3352 +num rollout transitions: 249362, reward mean: 3.3286 +num rollout transitions: 249333, reward mean: 3.3202 +num rollout transitions: 249377, reward mean: 3.3546 +num rollout transitions: 249384, reward mean: 3.3109 +num rollout transitions: 249266, reward mean: 3.3553 +num rollout transitions: 249408, reward mean: 3.3540 +num rollout transitions: 249320, reward mean: 3.3627 +num rollout transitions: 249226, reward mean: 3.3742 +num rollout transitions: 249347, reward mean: 3.3771 +num rollout transitions: 249365, reward mean: 3.3553 +num rollout transitions: 249399, reward mean: 3.3491 +num rollout transitions: 249421, reward mean: 3.3492 +num rollout transitions: 249278, reward mean: 3.3486 +num rollout transitions: 249336, reward mean: 3.3558 +num rollout transitions: 249332, reward mean: 3.3127 +num rollout transitions: 249354, reward mean: 3.3674 +num rollout transitions: 249260, reward mean: 3.3662 +num rollout transitions: 249282, reward mean: 3.3518 +num rollout transitions: 249340, reward mean: 3.3521 +num rollout transitions: 249296, reward mean: 3.3598 +num rollout transitions: 249293, reward mean: 3.3622 +num rollout transitions: 249314, reward mean: 3.3311 +num rollout transitions: 249350, reward mean: 3.3659 +num rollout transitions: 249350, reward mean: 3.3572 +num rollout transitions: 249296, reward mean: 3.3435 +num rollout transitions: 249253, reward mean: 3.3382 +num rollout transitions: 249310, reward mean: 3.3506 +num rollout transitions: 249326, reward mean: 3.3215 +num rollout transitions: 249313, reward mean: 3.3458 +num rollout transitions: 249315, reward mean: 3.3394 +num rollout transitions: 249326, reward mean: 3.3609 +num rollout transitions: 249379, reward mean: 3.3501 +num rollout transitions: 249355, reward mean: 3.3476 +num rollout transitions: 249311, reward mean: 3.3609 +num rollout transitions: 249260, reward mean: 3.3420 +num rollout transitions: 249361, reward mean: 3.3710 +num rollout transitions: 249310, reward mean: 3.3501 +num rollout transitions: 249244, reward mean: 3.3638 +num rollout transitions: 249288, reward mean: 3.3548 +num rollout transitions: 249271, reward mean: 3.3613 +num rollout transitions: 249279, reward mean: 3.3399 +num rollout transitions: 249298, reward mean: 3.3385 +num rollout transitions: 249327, reward mean: 3.3410 +num rollout transitions: 249249, reward mean: 3.3609 +num rollout transitions: 249277, reward mean: 3.3233 +num rollout transitions: 249331, reward mean: 3.3572 +---------------------------------------------------------------------------------- +| alpha | 0.0296 | +| eval/episode_length | 591 | +| eval/episode_length_std | 250 | +| eval/normalized_episode_reward | 64 | +| eval/normalized_episode_reward_std | 29.3 | +| loss/actor | -302 | +| loss/alpha | 0.0108 | +| loss/critic | 4.74 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.474 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249306, reward mean: 3.3426 +num rollout transitions: 249293, reward mean: 3.3339 +num rollout transitions: 249306, reward mean: 3.3231 +num rollout transitions: 249392, reward mean: 3.3409 +num rollout transitions: 249308, reward mean: 3.3430 +num rollout transitions: 249371, reward mean: 3.3507 +num rollout transitions: 249304, reward mean: 3.3455 +num rollout transitions: 249312, reward mean: 3.3376 +num rollout transitions: 249332, reward mean: 3.3459 +num rollout transitions: 249376, reward mean: 3.3419 +num rollout transitions: 249353, reward mean: 3.3380 +num rollout transitions: 249361, reward mean: 3.3288 +num rollout transitions: 249362, reward mean: 3.3597 +num rollout transitions: 249309, reward mean: 3.3300 +num rollout transitions: 249355, reward mean: 3.3312 +num rollout transitions: 249256, reward mean: 3.3213 +num rollout transitions: 249282, reward mean: 3.3402 +num rollout transitions: 249306, reward mean: 3.3219 +num rollout transitions: 249359, reward mean: 3.3265 +num rollout transitions: 249287, reward mean: 3.3428 +num rollout transitions: 249257, reward mean: 3.3585 +num rollout transitions: 249337, reward mean: 3.3418 +num rollout transitions: 249291, reward mean: 3.3384 +num rollout transitions: 249239, reward mean: 3.3387 +num rollout transitions: 249343, reward mean: 3.3185 +num rollout transitions: 249257, reward mean: 3.3008 +num rollout transitions: 249319, reward mean: 3.3506 +num rollout transitions: 249284, reward mean: 3.3239 +num rollout transitions: 249278, reward mean: 3.3528 +num rollout transitions: 249338, reward mean: 3.3531 +num rollout transitions: 249245, reward mean: 3.3432 +num rollout transitions: 249328, reward mean: 3.3322 +num rollout transitions: 249329, reward mean: 3.3422 +num rollout transitions: 249341, reward mean: 3.3364 +num rollout transitions: 249309, reward mean: 3.3386 +num rollout transitions: 249226, reward mean: 3.3382 +num rollout transitions: 249324, reward mean: 3.3638 +num rollout transitions: 249361, reward mean: 3.3561 +num rollout transitions: 249366, reward mean: 3.3740 +num rollout transitions: 249308, reward mean: 3.3273 +num rollout transitions: 249324, reward mean: 3.3686 +num rollout transitions: 249338, reward mean: 3.3380 +num rollout transitions: 249305, reward mean: 3.3396 +num rollout transitions: 249347, reward mean: 3.3352 +num rollout transitions: 249418, reward mean: 3.3513 +num rollout transitions: 249325, reward mean: 3.3285 +num rollout transitions: 249324, reward mean: 3.3208 +num rollout transitions: 249291, reward mean: 3.3345 +num rollout transitions: 249389, reward mean: 3.3545 +num rollout transitions: 249300, reward mean: 3.3445 +---------------------------------------------------------------------------------- +| alpha | 0.0307 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.837 | +| loss/actor | -301 | +| loss/alpha | 0.0154 | +| loss/critic | 4.94 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.494 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249343, reward mean: 3.3486 +num rollout transitions: 249259, reward mean: 3.3461 +num rollout transitions: 249313, reward mean: 3.3442 +num rollout transitions: 249299, reward mean: 3.3441 +num rollout transitions: 249256, reward mean: 3.3475 +num rollout transitions: 249408, reward mean: 3.3283 +num rollout transitions: 249340, reward mean: 3.3110 +num rollout transitions: 249346, reward mean: 3.3439 +num rollout transitions: 249328, reward mean: 3.3627 +num rollout transitions: 249393, reward mean: 3.3588 +num rollout transitions: 249269, reward mean: 3.3452 +num rollout transitions: 249373, reward mean: 3.3510 +num rollout transitions: 249343, reward mean: 3.3554 +num rollout transitions: 249296, reward mean: 3.3503 +num rollout transitions: 249405, reward mean: 3.3494 +num rollout transitions: 249221, reward mean: 3.3694 +num rollout transitions: 249314, reward mean: 3.3334 +num rollout transitions: 249384, reward mean: 3.3398 +num rollout transitions: 249306, reward mean: 3.3420 +num rollout transitions: 249291, reward mean: 3.3541 +num rollout transitions: 249306, reward mean: 3.3469 +num rollout transitions: 249326, reward mean: 3.3135 +num rollout transitions: 249344, reward mean: 3.3463 +num rollout transitions: 249316, reward mean: 3.3395 +num rollout transitions: 249324, reward mean: 3.3392 +num rollout transitions: 249281, reward mean: 3.3459 +num rollout transitions: 249339, reward mean: 3.3542 +num rollout transitions: 249356, reward mean: 3.3368 +num rollout transitions: 249309, reward mean: 3.3169 +num rollout transitions: 249347, reward mean: 3.3457 +num rollout transitions: 249321, reward mean: 3.3514 +num rollout transitions: 249326, reward mean: 3.3349 +num rollout transitions: 249394, reward mean: 3.3486 +num rollout transitions: 249377, reward mean: 3.3661 +num rollout transitions: 249359, reward mean: 3.3374 +num rollout transitions: 249359, reward mean: 3.3109 +num rollout transitions: 249253, reward mean: 3.3315 +num rollout transitions: 249327, reward mean: 3.3496 +num rollout transitions: 249394, reward mean: 3.3284 +num rollout transitions: 249328, reward mean: 3.3567 +num rollout transitions: 249308, reward mean: 3.3428 +num rollout transitions: 249287, reward mean: 3.3371 +num rollout transitions: 249347, reward mean: 3.3474 +num rollout transitions: 249281, reward mean: 3.3278 +num rollout transitions: 249359, reward mean: 3.3074 +num rollout transitions: 249348, reward mean: 3.3458 +num rollout transitions: 249332, reward mean: 3.3671 +num rollout transitions: 249376, reward mean: 3.3243 +num rollout transitions: 249352, reward mean: 3.3483 +num rollout transitions: 249383, reward mean: 3.3292 +---------------------------------------------------------------------------------- +| alpha | 0.0313 | +| eval/episode_length | 202 | +| eval/episode_length_std | 1.43 | +| eval/normalized_episode_reward | 19.9 | +| eval/normalized_episode_reward_std | 0.767 | +| loss/actor | -299 | +| loss/alpha | 0.0127 | +| loss/critic | 4.88 | +| penalty/lcb_mean | 0.243 | +| penalty/lcb_std | 0.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249341, reward mean: 3.3349 +num rollout transitions: 249273, reward mean: 3.3320 +num rollout transitions: 249312, reward mean: 3.3166 +num rollout transitions: 249352, reward mean: 3.3620 +num rollout transitions: 249331, reward mean: 3.3441 +num rollout transitions: 249279, reward mean: 3.3272 +num rollout transitions: 249259, reward mean: 3.3151 +num rollout transitions: 249278, reward mean: 3.3419 +num rollout transitions: 249313, reward mean: 3.3445 +num rollout transitions: 249354, reward mean: 3.3393 +num rollout transitions: 249354, reward mean: 3.3258 +num rollout transitions: 249278, reward mean: 3.3249 +num rollout transitions: 249316, reward mean: 3.3392 +num rollout transitions: 249283, reward mean: 3.3428 +num rollout transitions: 249263, reward mean: 3.3305 +num rollout transitions: 249349, reward mean: 3.3638 +num rollout transitions: 249306, reward mean: 3.3522 +num rollout transitions: 249312, reward mean: 3.3351 +num rollout transitions: 249402, reward mean: 3.3421 +num rollout transitions: 249344, reward mean: 3.3356 +num rollout transitions: 249275, reward mean: 3.3502 +num rollout transitions: 249360, reward mean: 3.3669 +num rollout transitions: 249266, reward mean: 3.3304 +num rollout transitions: 249328, reward mean: 3.3536 +num rollout transitions: 249311, reward mean: 3.3521 +num rollout transitions: 249273, reward mean: 3.3663 +num rollout transitions: 249358, reward mean: 3.3423 +num rollout transitions: 249338, reward mean: 3.3600 +num rollout transitions: 249215, reward mean: 3.3235 +num rollout transitions: 249304, reward mean: 3.3505 +num rollout transitions: 249382, reward mean: 3.3637 +num rollout transitions: 249290, reward mean: 3.3554 +num rollout transitions: 249304, reward mean: 3.3530 +num rollout transitions: 249350, reward mean: 3.3490 +num rollout transitions: 249355, reward mean: 3.3840 +num rollout transitions: 249352, reward mean: 3.3430 +num rollout transitions: 249312, reward mean: 3.3502 +num rollout transitions: 249345, reward mean: 3.3760 +num rollout transitions: 249373, reward mean: 3.3457 +num rollout transitions: 249358, reward mean: 3.3567 +num rollout transitions: 249204, reward mean: 3.3267 +num rollout transitions: 249334, reward mean: 3.3547 +num rollout transitions: 249390, reward mean: 3.3418 +num rollout transitions: 249274, reward mean: 3.3583 +num rollout transitions: 249285, reward mean: 3.3595 +num rollout transitions: 249331, reward mean: 3.3478 +num rollout transitions: 249322, reward mean: 3.3609 +num rollout transitions: 249326, reward mean: 3.3449 +num rollout transitions: 249328, reward mean: 3.3458 +num rollout transitions: 249290, reward mean: 3.3497 +---------------------------------------------------------------------------------- +| alpha | 0.0316 | +| eval/episode_length | 985 | +| eval/episode_length_std | 68.6 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 8.54 | +| loss/actor | -299 | +| loss/alpha | -0.0219 | +| loss/critic | 5.39 | +| penalty/lcb_mean | 0.245 | +| penalty/lcb_std | 0.515 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249275, reward mean: 3.3564 +num rollout transitions: 249285, reward mean: 3.3466 +num rollout transitions: 249251, reward mean: 3.3292 +num rollout transitions: 249295, reward mean: 3.3329 +num rollout transitions: 249299, reward mean: 3.3430 +num rollout transitions: 249323, reward mean: 3.3247 +num rollout transitions: 249373, reward mean: 3.3550 +num rollout transitions: 249278, reward mean: 3.3379 +num rollout transitions: 249350, reward mean: 3.3650 +num rollout transitions: 249309, reward mean: 3.3547 +num rollout transitions: 249293, reward mean: 3.3501 +num rollout transitions: 249295, reward mean: 3.3703 +num rollout transitions: 249208, reward mean: 3.3340 +num rollout transitions: 249283, reward mean: 3.3473 +num rollout transitions: 249314, reward mean: 3.3429 +num rollout transitions: 249355, reward mean: 3.3384 +num rollout transitions: 249341, reward mean: 3.3572 +num rollout transitions: 249317, reward mean: 3.3398 +num rollout transitions: 249350, reward mean: 3.3306 +num rollout transitions: 249264, reward mean: 3.3302 +num rollout transitions: 249324, reward mean: 3.3143 +num rollout transitions: 249359, reward mean: 3.3291 +num rollout transitions: 249342, reward mean: 3.3427 +num rollout transitions: 249397, reward mean: 3.3217 +num rollout transitions: 249335, reward mean: 3.3390 +num rollout transitions: 249300, reward mean: 3.3334 +num rollout transitions: 249321, reward mean: 3.3264 +num rollout transitions: 249360, reward mean: 3.3353 +num rollout transitions: 249331, reward mean: 3.3621 +num rollout transitions: 249261, reward mean: 3.3340 +num rollout transitions: 249291, reward mean: 3.3297 +num rollout transitions: 249351, reward mean: 3.3451 +num rollout transitions: 249358, reward mean: 3.3299 +num rollout transitions: 249294, reward mean: 3.3369 +num rollout transitions: 249398, reward mean: 3.3391 +num rollout transitions: 249275, reward mean: 3.3371 +num rollout transitions: 249253, reward mean: 3.3501 +num rollout transitions: 249261, reward mean: 3.3519 +num rollout transitions: 249372, reward mean: 3.3408 +num rollout transitions: 249278, reward mean: 3.3472 +num rollout transitions: 249330, reward mean: 3.3346 +num rollout transitions: 249257, reward mean: 3.3521 +num rollout transitions: 249308, reward mean: 3.3406 +num rollout transitions: 249291, reward mean: 3.3282 +num rollout transitions: 249377, reward mean: 3.3288 +num rollout transitions: 249342, reward mean: 3.3530 +num rollout transitions: 249368, reward mean: 3.3359 +num rollout transitions: 249272, reward mean: 3.3403 +num rollout transitions: 249243, reward mean: 3.3559 +num rollout transitions: 249407, reward mean: 3.3462 +---------------------------------------------------------------------------------- +| alpha | 0.0304 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.785 | +| loss/actor | -301 | +| loss/alpha | 0.00748 | +| loss/critic | 4.94 | +| penalty/lcb_mean | 0.239 | +| penalty/lcb_std | 0.506 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249314, reward mean: 3.3363 +num rollout transitions: 249264, reward mean: 3.3216 +num rollout transitions: 249278, reward mean: 3.3435 +num rollout transitions: 249355, reward mean: 3.3390 +num rollout transitions: 249277, reward mean: 3.3247 +num rollout transitions: 249251, reward mean: 3.3530 +num rollout transitions: 249315, reward mean: 3.3386 +num rollout transitions: 249305, reward mean: 3.3528 +num rollout transitions: 249317, reward mean: 3.3176 +num rollout transitions: 249329, reward mean: 3.3601 +num rollout transitions: 249365, reward mean: 3.3351 +num rollout transitions: 249324, reward mean: 3.3440 +num rollout transitions: 249288, reward mean: 3.3026 +num rollout transitions: 249344, reward mean: 3.3363 +num rollout transitions: 249349, reward mean: 3.3451 +num rollout transitions: 249398, reward mean: 3.3637 +num rollout transitions: 249337, reward mean: 3.3453 +num rollout transitions: 249321, reward mean: 3.3606 +num rollout transitions: 249269, reward mean: 3.3390 +num rollout transitions: 249278, reward mean: 3.3398 +num rollout transitions: 249287, reward mean: 3.3374 +num rollout transitions: 249280, reward mean: 3.3483 +num rollout transitions: 249371, reward mean: 3.3710 +num rollout transitions: 249255, reward mean: 3.3440 +num rollout transitions: 249407, reward mean: 3.3496 +num rollout transitions: 249291, reward mean: 3.3316 +num rollout transitions: 249243, reward mean: 3.3471 +num rollout transitions: 249325, reward mean: 3.3452 +num rollout transitions: 249329, reward mean: 3.3453 +num rollout transitions: 249216, reward mean: 3.3270 +num rollout transitions: 249307, reward mean: 3.3387 +num rollout transitions: 249323, reward mean: 3.3406 +num rollout transitions: 249281, reward mean: 3.3543 +num rollout transitions: 249351, reward mean: 3.3524 +num rollout transitions: 249308, reward mean: 3.3599 +num rollout transitions: 249356, reward mean: 3.3211 +num rollout transitions: 249417, reward mean: 3.3529 +num rollout transitions: 249369, reward mean: 3.3388 +num rollout transitions: 249311, reward mean: 3.3371 +num rollout transitions: 249320, reward mean: 3.3288 +num rollout transitions: 249321, reward mean: 3.3360 +num rollout transitions: 249304, reward mean: 3.3341 +num rollout transitions: 249307, reward mean: 3.3459 +num rollout transitions: 249305, reward mean: 3.3522 +num rollout transitions: 249263, reward mean: 3.3489 +num rollout transitions: 249422, reward mean: 3.3193 +num rollout transitions: 249274, reward mean: 3.3444 +num rollout transitions: 249257, reward mean: 3.3517 +num rollout transitions: 249341, reward mean: 3.3259 +num rollout transitions: 249326, reward mean: 3.3414 +---------------------------------------------------------------------------------- +| alpha | 0.0296 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.93 | +| loss/actor | -301 | +| loss/alpha | -0.00606 | +| loss/critic | 5.98 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.503 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249352, reward mean: 3.3347 +num rollout transitions: 249271, reward mean: 3.3604 +num rollout transitions: 249344, reward mean: 3.3302 +num rollout transitions: 249359, reward mean: 3.3344 +num rollout transitions: 249263, reward mean: 3.3565 +num rollout transitions: 249236, reward mean: 3.3742 +num rollout transitions: 249270, reward mean: 3.3315 +num rollout transitions: 249351, reward mean: 3.3356 +num rollout transitions: 249383, reward mean: 3.3270 +num rollout transitions: 249230, reward mean: 3.3641 +num rollout transitions: 249369, reward mean: 3.3339 +num rollout transitions: 249312, reward mean: 3.3438 +num rollout transitions: 249223, reward mean: 3.3326 +num rollout transitions: 249285, reward mean: 3.3467 +num rollout transitions: 249293, reward mean: 3.3443 +num rollout transitions: 249367, reward mean: 3.3377 +num rollout transitions: 249356, reward mean: 3.3463 +num rollout transitions: 249246, reward mean: 3.3462 +num rollout transitions: 249282, reward mean: 3.3647 +num rollout transitions: 249335, reward mean: 3.3369 +num rollout transitions: 249418, reward mean: 3.3290 +num rollout transitions: 249318, reward mean: 3.3624 +num rollout transitions: 249396, reward mean: 3.3520 +num rollout transitions: 249426, reward mean: 3.3357 +num rollout transitions: 249296, reward mean: 3.3553 +num rollout transitions: 249305, reward mean: 3.3296 +num rollout transitions: 249314, reward mean: 3.3557 +num rollout transitions: 249332, reward mean: 3.3408 +num rollout transitions: 249353, reward mean: 3.3392 +num rollout transitions: 249303, reward mean: 3.3378 +num rollout transitions: 249368, reward mean: 3.3380 +num rollout transitions: 249224, reward mean: 3.3286 +num rollout transitions: 249330, reward mean: 3.3394 +num rollout transitions: 249234, reward mean: 3.3357 +num rollout transitions: 249327, reward mean: 3.3361 +num rollout transitions: 249294, reward mean: 3.3425 +num rollout transitions: 249316, reward mean: 3.3401 +num rollout transitions: 249377, reward mean: 3.3358 +num rollout transitions: 249240, reward mean: 3.3446 +num rollout transitions: 249316, reward mean: 3.3380 +num rollout transitions: 249328, reward mean: 3.3399 +num rollout transitions: 249317, reward mean: 3.3620 +num rollout transitions: 249349, reward mean: 3.3374 +num rollout transitions: 249284, reward mean: 3.3317 +num rollout transitions: 249359, reward mean: 3.3376 +num rollout transitions: 249278, reward mean: 3.3439 +num rollout transitions: 249326, reward mean: 3.3375 +num rollout transitions: 249298, reward mean: 3.3380 +num rollout transitions: 249337, reward mean: 3.3413 +num rollout transitions: 249164, reward mean: 3.3392 +---------------------------------------------------------------------------------- +| alpha | 0.0281 | +| eval/episode_length | 583 | +| eval/episode_length_std | 151 | +| eval/normalized_episode_reward | 64.5 | +| eval/normalized_episode_reward_std | 17.7 | +| loss/actor | -302 | +| loss/alpha | 0.0187 | +| loss/critic | 4.36 | +| penalty/lcb_mean | 0.238 | +| penalty/lcb_std | 0.514 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249248, reward mean: 3.3623 +num rollout transitions: 249334, reward mean: 3.3491 +num rollout transitions: 249274, reward mean: 3.3746 +num rollout transitions: 249389, reward mean: 3.3300 +num rollout transitions: 249353, reward mean: 3.3922 +num rollout transitions: 249304, reward mean: 3.3388 +num rollout transitions: 249407, reward mean: 3.3450 +num rollout transitions: 249341, reward mean: 3.3391 +num rollout transitions: 249322, reward mean: 3.3485 +num rollout transitions: 249271, reward mean: 3.3297 +num rollout transitions: 249409, reward mean: 3.3627 +num rollout transitions: 249341, reward mean: 3.3376 +num rollout transitions: 249326, reward mean: 3.3425 +num rollout transitions: 249349, reward mean: 3.3359 +num rollout transitions: 249287, reward mean: 3.3274 +num rollout transitions: 249315, reward mean: 3.3404 +num rollout transitions: 249280, reward mean: 3.3413 +num rollout transitions: 249281, reward mean: 3.3289 +num rollout transitions: 249313, reward mean: 3.3395 +num rollout transitions: 249340, reward mean: 3.3492 +num rollout transitions: 249390, reward mean: 3.3418 +num rollout transitions: 249335, reward mean: 3.3448 +num rollout transitions: 249234, reward mean: 3.3206 +num rollout transitions: 249275, reward mean: 3.3515 +num rollout transitions: 249311, reward mean: 3.3559 +num rollout transitions: 249191, reward mean: 3.3643 +num rollout transitions: 249294, reward mean: 3.3547 +num rollout transitions: 249297, reward mean: 3.3327 +num rollout transitions: 249315, reward mean: 3.3406 +num rollout transitions: 249398, reward mean: 3.3620 +num rollout transitions: 249345, reward mean: 3.3402 +num rollout transitions: 249271, reward mean: 3.3513 +num rollout transitions: 249369, reward mean: 3.3441 +num rollout transitions: 249413, reward mean: 3.3170 +num rollout transitions: 249289, reward mean: 3.3389 +num rollout transitions: 249349, reward mean: 3.3509 +num rollout transitions: 249342, reward mean: 3.3414 +num rollout transitions: 249316, reward mean: 3.3329 +num rollout transitions: 249408, reward mean: 3.3507 +num rollout transitions: 249384, reward mean: 3.3267 +num rollout transitions: 249316, reward mean: 3.3311 +num rollout transitions: 249341, reward mean: 3.3381 +num rollout transitions: 249241, reward mean: 3.3450 +num rollout transitions: 249318, reward mean: 3.3349 +num rollout transitions: 249258, reward mean: 3.3240 +num rollout transitions: 249287, reward mean: 3.3392 +num rollout transitions: 249277, reward mean: 3.3413 +num rollout transitions: 249310, reward mean: 3.3594 +num rollout transitions: 249345, reward mean: 3.3453 +num rollout transitions: 249289, reward mean: 3.3447 +---------------------------------------------------------------------------------- +| alpha | 0.0291 | +| eval/episode_length | 738 | +| eval/episode_length_std | 350 | +| eval/normalized_episode_reward | 82 | +| eval/normalized_episode_reward_std | 41.4 | +| loss/actor | -302 | +| loss/alpha | -0.0172 | +| loss/critic | 4.87 | +| penalty/lcb_mean | 0.239 | +| penalty/lcb_std | 0.514 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249368, reward mean: 3.3340 +num rollout transitions: 249305, reward mean: 3.3708 +num rollout transitions: 249426, reward mean: 3.3296 +num rollout transitions: 249311, reward mean: 3.3524 +num rollout transitions: 249339, reward mean: 3.3442 +num rollout transitions: 249308, reward mean: 3.3442 +num rollout transitions: 249342, reward mean: 3.3536 +num rollout transitions: 249334, reward mean: 3.3411 +num rollout transitions: 249233, reward mean: 3.3276 +num rollout transitions: 249316, reward mean: 3.3294 +num rollout transitions: 249354, reward mean: 3.3360 +num rollout transitions: 249285, reward mean: 3.3253 +num rollout transitions: 249360, reward mean: 3.3548 +num rollout transitions: 249325, reward mean: 3.3447 +num rollout transitions: 249267, reward mean: 3.3518 +num rollout transitions: 249368, reward mean: 3.3352 +num rollout transitions: 249341, reward mean: 3.3504 +num rollout transitions: 249349, reward mean: 3.3157 +num rollout transitions: 249415, reward mean: 3.3325 +num rollout transitions: 249303, reward mean: 3.3672 +num rollout transitions: 249336, reward mean: 3.3482 +num rollout transitions: 249252, reward mean: 3.3601 +num rollout transitions: 249347, reward mean: 3.3625 +num rollout transitions: 249310, reward mean: 3.3545 +num rollout transitions: 249261, reward mean: 3.3272 +num rollout transitions: 249330, reward mean: 3.3178 +num rollout transitions: 249326, reward mean: 3.3630 +num rollout transitions: 249272, reward mean: 3.3643 +num rollout transitions: 249288, reward mean: 3.3278 +num rollout transitions: 249384, reward mean: 3.3902 +num rollout transitions: 249247, reward mean: 3.3616 +num rollout transitions: 249348, reward mean: 3.3412 +num rollout transitions: 249299, reward mean: 3.3491 +num rollout transitions: 249263, reward mean: 3.3323 +num rollout transitions: 249304, reward mean: 3.3327 +num rollout transitions: 249295, reward mean: 3.3775 +num rollout transitions: 249292, reward mean: 3.3430 +num rollout transitions: 249367, reward mean: 3.3767 +num rollout transitions: 249360, reward mean: 3.3467 +num rollout transitions: 249281, reward mean: 3.3543 +num rollout transitions: 249255, reward mean: 3.3439 +num rollout transitions: 249281, reward mean: 3.3603 +num rollout transitions: 249400, reward mean: 3.3476 +num rollout transitions: 249443, reward mean: 3.3640 +num rollout transitions: 249321, reward mean: 3.3495 +num rollout transitions: 249341, reward mean: 3.3610 +num rollout transitions: 249404, reward mean: 3.3508 +num rollout transitions: 249225, reward mean: 3.3475 +num rollout transitions: 249367, reward mean: 3.3433 +num rollout transitions: 249207, reward mean: 3.3551 +---------------------------------------------------------------------------------- +| alpha | 0.0288 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.927 | +| loss/actor | -303 | +| loss/alpha | 0.0056 | +| loss/critic | 5.19 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.516 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249317, reward mean: 3.3403 +num rollout transitions: 249317, reward mean: 3.3528 +num rollout transitions: 249293, reward mean: 3.3680 +num rollout transitions: 249270, reward mean: 3.3465 +num rollout transitions: 249306, reward mean: 3.3378 +num rollout transitions: 249318, reward mean: 3.3538 +num rollout transitions: 249359, reward mean: 3.3369 +num rollout transitions: 249258, reward mean: 3.3481 +num rollout transitions: 249356, reward mean: 3.3328 +num rollout transitions: 249314, reward mean: 3.3585 +num rollout transitions: 249357, reward mean: 3.3478 +num rollout transitions: 249340, reward mean: 3.3642 +num rollout transitions: 249321, reward mean: 3.3538 +num rollout transitions: 249394, reward mean: 3.3554 +num rollout transitions: 249308, reward mean: 3.3577 +num rollout transitions: 249297, reward mean: 3.3585 +num rollout transitions: 249368, reward mean: 3.3639 +num rollout transitions: 249352, reward mean: 3.3600 +num rollout transitions: 249361, reward mean: 3.3465 +num rollout transitions: 249259, reward mean: 3.3528 +num rollout transitions: 249301, reward mean: 3.3423 +num rollout transitions: 249255, reward mean: 3.3311 +num rollout transitions: 249236, reward mean: 3.3328 +num rollout transitions: 249376, reward mean: 3.3467 +num rollout transitions: 249266, reward mean: 3.3390 +num rollout transitions: 249441, reward mean: 3.3529 +num rollout transitions: 249404, reward mean: 3.3630 +num rollout transitions: 249278, reward mean: 3.3463 +num rollout transitions: 249295, reward mean: 3.3326 +num rollout transitions: 249269, reward mean: 3.3346 +num rollout transitions: 249297, reward mean: 3.3287 +num rollout transitions: 249344, reward mean: 3.3608 +num rollout transitions: 249355, reward mean: 3.3485 +num rollout transitions: 249306, reward mean: 3.3600 +num rollout transitions: 249371, reward mean: 3.3242 +num rollout transitions: 249294, reward mean: 3.3602 +num rollout transitions: 249326, reward mean: 3.3422 +num rollout transitions: 249326, reward mean: 3.3424 +num rollout transitions: 249298, reward mean: 3.3393 +num rollout transitions: 249348, reward mean: 3.3322 +num rollout transitions: 249293, reward mean: 3.3370 +num rollout transitions: 249247, reward mean: 3.3352 +num rollout transitions: 249254, reward mean: 3.3432 +num rollout transitions: 249298, reward mean: 3.3532 +num rollout transitions: 249368, reward mean: 3.3546 +num rollout transitions: 249434, reward mean: 3.3252 +num rollout transitions: 249294, reward mean: 3.3472 +num rollout transitions: 249320, reward mean: 3.3565 +num rollout transitions: 249378, reward mean: 3.3559 +num rollout transitions: 249374, reward mean: 3.3515 +----------------------------------------------------------------------------------- +| alpha | 0.0289 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.951 | +| loss/actor | -302 | +| loss/alpha | -0.000216 | +| loss/critic | 5.38 | +| penalty/lcb_mean | 0.239 | +| penalty/lcb_std | 0.516 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 249359, reward mean: 3.3557 +num rollout transitions: 249328, reward mean: 3.3322 +num rollout transitions: 249252, reward mean: 3.3539 +num rollout transitions: 249305, reward mean: 3.3391 +num rollout transitions: 249327, reward mean: 3.3358 +num rollout transitions: 249272, reward mean: 3.3422 +num rollout transitions: 249279, reward mean: 3.3332 +num rollout transitions: 249342, reward mean: 3.3299 +num rollout transitions: 249290, reward mean: 3.3591 +num rollout transitions: 249264, reward mean: 3.3406 +num rollout transitions: 249320, reward mean: 3.3328 +num rollout transitions: 249348, reward mean: 3.3586 +num rollout transitions: 249298, reward mean: 3.3495 +num rollout transitions: 249351, reward mean: 3.3340 +num rollout transitions: 249294, reward mean: 3.3317 +num rollout transitions: 249266, reward mean: 3.3393 +num rollout transitions: 249322, reward mean: 3.3513 +num rollout transitions: 249358, reward mean: 3.3431 +num rollout transitions: 249291, reward mean: 3.3721 +num rollout transitions: 249441, reward mean: 3.3464 +num rollout transitions: 249297, reward mean: 3.3500 +num rollout transitions: 249295, reward mean: 3.3493 +num rollout transitions: 249268, reward mean: 3.3614 +num rollout transitions: 249234, reward mean: 3.3300 +num rollout transitions: 249335, reward mean: 3.3412 +num rollout transitions: 249362, reward mean: 3.3436 +num rollout transitions: 249299, reward mean: 3.3291 +num rollout transitions: 249355, reward mean: 3.3360 +num rollout transitions: 249251, reward mean: 3.3502 +num rollout transitions: 249333, reward mean: 3.3513 +num rollout transitions: 249293, reward mean: 3.3394 +num rollout transitions: 249285, reward mean: 3.3532 +num rollout transitions: 249331, reward mean: 3.3543 +num rollout transitions: 249341, reward mean: 3.3625 +num rollout transitions: 249282, reward mean: 3.3516 +num rollout transitions: 249389, reward mean: 3.3506 +num rollout transitions: 249347, reward mean: 3.3391 +num rollout transitions: 249246, reward mean: 3.3467 +num rollout transitions: 249353, reward mean: 3.3526 +num rollout transitions: 249271, reward mean: 3.3411 +num rollout transitions: 249343, reward mean: 3.3404 +num rollout transitions: 249337, reward mean: 3.3227 +num rollout transitions: 249322, reward mean: 3.3381 +num rollout transitions: 249332, reward mean: 3.3332 +num rollout transitions: 249361, reward mean: 3.3191 +num rollout transitions: 249296, reward mean: 3.3102 +num rollout transitions: 249377, reward mean: 3.3453 +num rollout transitions: 249304, reward mean: 3.3588 +num rollout transitions: 249367, reward mean: 3.3421 +num rollout transitions: 249386, reward mean: 3.3233 +---------------------------------------------------------------------------------- +| alpha | 0.0288 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 1.14 | +| loss/actor | -302 | +| loss/alpha | -0.00264 | +| loss/critic | 5.63 | +| penalty/lcb_mean | 0.24 | +| penalty/lcb_std | 0.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249394, reward mean: 3.3378 +num rollout transitions: 249282, reward mean: 3.3328 +num rollout transitions: 249305, reward mean: 3.3327 +num rollout transitions: 249337, reward mean: 3.3426 +num rollout transitions: 249389, reward mean: 3.3393 +num rollout transitions: 249314, reward mean: 3.3299 +num rollout transitions: 249309, reward mean: 3.3187 +num rollout transitions: 249315, reward mean: 3.3429 +num rollout transitions: 249367, reward mean: 3.3427 +num rollout transitions: 249320, reward mean: 3.3499 +num rollout transitions: 249331, reward mean: 3.3529 +num rollout transitions: 249341, reward mean: 3.3484 +num rollout transitions: 249382, reward mean: 3.3351 +num rollout transitions: 249298, reward mean: 3.3324 +num rollout transitions: 249285, reward mean: 3.3323 +num rollout transitions: 249348, reward mean: 3.3279 +num rollout transitions: 249347, reward mean: 3.3410 +num rollout transitions: 249266, reward mean: 3.3449 +num rollout transitions: 249320, reward mean: 3.3121 +num rollout transitions: 249386, reward mean: 3.3411 +num rollout transitions: 249376, reward mean: 3.3295 +num rollout transitions: 249310, reward mean: 3.3419 +num rollout transitions: 249263, reward mean: 3.3550 +num rollout transitions: 249208, reward mean: 3.3370 +num rollout transitions: 249272, reward mean: 3.3172 +num rollout transitions: 249272, reward mean: 3.3543 +num rollout transitions: 249368, reward mean: 3.3494 +num rollout transitions: 249291, reward mean: 3.3457 +num rollout transitions: 249330, reward mean: 3.3344 +num rollout transitions: 249318, reward mean: 3.3448 +num rollout transitions: 249385, reward mean: 3.3547 +num rollout transitions: 249359, reward mean: 3.3416 +num rollout transitions: 249346, reward mean: 3.3170 +num rollout transitions: 249427, reward mean: 3.3183 +num rollout transitions: 249240, reward mean: 3.3374 +num rollout transitions: 249333, reward mean: 3.3385 +num rollout transitions: 249338, reward mean: 3.3515 +num rollout transitions: 249286, reward mean: 3.3606 +num rollout transitions: 249329, reward mean: 3.3466 +num rollout transitions: 249372, reward mean: 3.3308 +num rollout transitions: 249310, reward mean: 3.3334 +num rollout transitions: 249382, reward mean: 3.3425 +num rollout transitions: 249366, reward mean: 3.3483 +num rollout transitions: 249223, reward mean: 3.3444 +num rollout transitions: 249358, reward mean: 3.3722 +num rollout transitions: 249317, reward mean: 3.3411 +num rollout transitions: 249410, reward mean: 3.3521 +num rollout transitions: 249380, reward mean: 3.3207 +num rollout transitions: 249292, reward mean: 3.3290 +num rollout transitions: 249431, reward mean: 3.3502 +---------------------------------------------------------------------------------- +| alpha | 0.0289 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.758 | +| loss/actor | -302 | +| loss/alpha | 0.0111 | +| loss/critic | 4.77 | +| penalty/lcb_mean | 0.241 | +| penalty/lcb_std | 0.521 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249295, reward mean: 3.3308 +num rollout transitions: 249325, reward mean: 3.3297 +num rollout transitions: 249310, reward mean: 3.3571 +num rollout transitions: 249304, reward mean: 3.3464 +num rollout transitions: 249311, reward mean: 3.3457 +num rollout transitions: 249323, reward mean: 3.3468 +num rollout transitions: 249348, reward mean: 3.3453 +num rollout transitions: 249333, reward mean: 3.3506 +num rollout transitions: 249307, reward mean: 3.3352 +num rollout transitions: 249358, reward mean: 3.3431 +num rollout transitions: 249275, reward mean: 3.3399 +num rollout transitions: 249372, reward mean: 3.3530 +num rollout transitions: 249326, reward mean: 3.3579 +num rollout transitions: 249331, reward mean: 3.3466 +num rollout transitions: 249387, reward mean: 3.3303 +num rollout transitions: 249415, reward mean: 3.3568 +num rollout transitions: 249334, reward mean: 3.3532 +num rollout transitions: 249264, reward mean: 3.3370 +num rollout transitions: 249361, reward mean: 3.3260 +num rollout transitions: 249393, reward mean: 3.3538 +num rollout transitions: 249262, reward mean: 3.3428 +num rollout transitions: 249375, reward mean: 3.3325 +num rollout transitions: 249329, reward mean: 3.3364 +num rollout transitions: 249295, reward mean: 3.3189 +num rollout transitions: 249277, reward mean: 3.3245 +num rollout transitions: 249375, reward mean: 3.3529 +num rollout transitions: 249351, reward mean: 3.3275 +num rollout transitions: 249337, reward mean: 3.3678 +num rollout transitions: 249284, reward mean: 3.3539 +num rollout transitions: 249264, reward mean: 3.3482 +num rollout transitions: 249288, reward mean: 3.3284 +num rollout transitions: 249305, reward mean: 3.3508 +num rollout transitions: 249330, reward mean: 3.3450 +num rollout transitions: 249300, reward mean: 3.3637 +num rollout transitions: 249326, reward mean: 3.3442 +num rollout transitions: 249420, reward mean: 3.3370 +num rollout transitions: 249359, reward mean: 3.3359 +num rollout transitions: 249327, reward mean: 3.3513 +num rollout transitions: 249290, reward mean: 3.3242 +num rollout transitions: 249382, reward mean: 3.3395 +num rollout transitions: 249363, reward mean: 3.3384 +num rollout transitions: 249303, reward mean: 3.3325 +num rollout transitions: 249303, reward mean: 3.3387 +num rollout transitions: 249377, reward mean: 3.3322 +num rollout transitions: 249332, reward mean: 3.3684 +num rollout transitions: 249337, reward mean: 3.3489 +num rollout transitions: 249283, reward mean: 3.3614 +num rollout transitions: 249344, reward mean: 3.3498 +num rollout transitions: 249320, reward mean: 3.3567 +num rollout transitions: 249267, reward mean: 3.3523 +---------------------------------------------------------------------------------- +| alpha | 0.0283 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.771 | +| loss/actor | -302 | +| loss/alpha | -0.00012 | +| loss/critic | 4.94 | +| penalty/lcb_mean | 0.244 | +| penalty/lcb_std | 0.527 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249418, reward mean: 3.3294 +num rollout transitions: 249375, reward mean: 3.3332 +num rollout transitions: 249398, reward mean: 3.3467 +num rollout transitions: 249255, reward mean: 3.3317 +num rollout transitions: 249319, reward mean: 3.3378 +num rollout transitions: 249297, reward mean: 3.3349 +num rollout transitions: 249372, reward mean: 3.3406 +num rollout transitions: 249332, reward mean: 3.3259 +num rollout transitions: 249348, reward mean: 3.3350 +num rollout transitions: 249330, reward mean: 3.3438 +num rollout transitions: 249285, reward mean: 3.3486 +num rollout transitions: 249306, reward mean: 3.3365 +num rollout transitions: 249358, reward mean: 3.3228 +num rollout transitions: 249345, reward mean: 3.3286 +num rollout transitions: 249348, reward mean: 3.3190 +num rollout transitions: 249391, reward mean: 3.3383 +num rollout transitions: 249272, reward mean: 3.3626 +num rollout transitions: 249336, reward mean: 3.3230 +num rollout transitions: 249314, reward mean: 3.3344 +num rollout transitions: 249293, reward mean: 3.3283 +num rollout transitions: 249376, reward mean: 3.3348 +num rollout transitions: 249257, reward mean: 3.3414 +num rollout transitions: 249306, reward mean: 3.3492 +num rollout transitions: 249318, reward mean: 3.3466 +num rollout transitions: 249320, reward mean: 3.3329 +num rollout transitions: 249366, reward mean: 3.3553 +num rollout transitions: 249339, reward mean: 3.3299 +num rollout transitions: 249313, reward mean: 3.3264 +num rollout transitions: 249268, reward mean: 3.3302 +num rollout transitions: 249362, reward mean: 3.3225 +num rollout transitions: 249387, reward mean: 3.3130 +num rollout transitions: 249356, reward mean: 3.3603 +num rollout transitions: 249293, reward mean: 3.3299 +num rollout transitions: 249337, reward mean: 3.3513 +num rollout transitions: 249364, reward mean: 3.3445 +num rollout transitions: 249182, reward mean: 3.3678 +num rollout transitions: 249417, reward mean: 3.3546 +num rollout transitions: 249353, reward mean: 3.3506 +num rollout transitions: 249244, reward mean: 3.3556 +num rollout transitions: 249256, reward mean: 3.3427 +num rollout transitions: 249372, reward mean: 3.3278 +num rollout transitions: 249367, reward mean: 3.3545 +num rollout transitions: 249261, reward mean: 3.3295 +num rollout transitions: 249233, reward mean: 3.3368 +num rollout transitions: 249311, reward mean: 3.3030 +num rollout transitions: 249240, reward mean: 3.3292 +num rollout transitions: 249282, reward mean: 3.3519 +num rollout transitions: 249276, reward mean: 3.3253 +num rollout transitions: 249328, reward mean: 3.3269 +num rollout transitions: 249368, reward mean: 3.3475 +---------------------------------------------------------------------------------- +| alpha | 0.0284 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.825 | +| loss/actor | -302 | +| loss/alpha | 0.00248 | +| loss/critic | 5.38 | +| penalty/lcb_mean | 0.242 | +| penalty/lcb_std | 0.534 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249316, reward mean: 3.3256 +num rollout transitions: 249290, reward mean: 3.3295 +num rollout transitions: 249280, reward mean: 3.3575 +num rollout transitions: 249335, reward mean: 3.3344 +num rollout transitions: 249305, reward mean: 3.3371 +num rollout transitions: 249246, reward mean: 3.3304 +num rollout transitions: 249351, reward mean: 3.3224 +num rollout transitions: 249380, reward mean: 3.3461 +num rollout transitions: 249258, reward mean: 3.3312 +num rollout transitions: 249348, reward mean: 3.3382 +num rollout transitions: 249276, reward mean: 3.3266 +num rollout transitions: 249350, reward mean: 3.3479 +num rollout transitions: 249319, reward mean: 3.3486 +num rollout transitions: 249343, reward mean: 3.3241 +num rollout transitions: 249264, reward mean: 3.3380 +num rollout transitions: 249318, reward mean: 3.3303 +num rollout transitions: 249330, reward mean: 3.3424 +num rollout transitions: 249279, reward mean: 3.3346 +num rollout transitions: 249266, reward mean: 3.3338 +num rollout transitions: 249356, reward mean: 3.3303 +num rollout transitions: 249289, reward mean: 3.3269 +num rollout transitions: 249290, reward mean: 3.3223 +num rollout transitions: 249344, reward mean: 3.3365 +num rollout transitions: 249314, reward mean: 3.3393 +num rollout transitions: 249338, reward mean: 3.3383 +num rollout transitions: 249394, reward mean: 3.3316 +num rollout transitions: 249422, reward mean: 3.3364 +num rollout transitions: 249285, reward mean: 3.3393 +num rollout transitions: 249252, reward mean: 3.3308 +num rollout transitions: 249262, reward mean: 3.3420 +num rollout transitions: 249325, reward mean: 3.3436 +num rollout transitions: 249292, reward mean: 3.3373 +num rollout transitions: 249337, reward mean: 3.3404 +num rollout transitions: 249266, reward mean: 3.3430 +num rollout transitions: 249304, reward mean: 3.3478 +num rollout transitions: 249308, reward mean: 3.3362 +num rollout transitions: 249354, reward mean: 3.3530 +num rollout transitions: 249305, reward mean: 3.3315 +num rollout transitions: 249334, reward mean: 3.3372 +num rollout transitions: 249330, reward mean: 3.3247 +num rollout transitions: 249247, reward mean: 3.3457 +num rollout transitions: 249350, reward mean: 3.3253 +num rollout transitions: 249320, reward mean: 3.3511 +num rollout transitions: 249344, reward mean: 3.3479 +num rollout transitions: 249222, reward mean: 3.3575 +num rollout transitions: 249315, reward mean: 3.3205 +num rollout transitions: 249323, reward mean: 3.3422 +num rollout transitions: 249358, reward mean: 3.3556 +num rollout transitions: 249325, reward mean: 3.3408 +num rollout transitions: 249304, reward mean: 3.3481 +---------------------------------------------------------------------------------- +| alpha | 0.0283 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.733 | +| loss/actor | -302 | +| loss/alpha | -0.00122 | +| loss/critic | 5.43 | +| penalty/lcb_mean | 0.241 | +| penalty/lcb_std | 0.535 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249298, reward mean: 3.3316 +num rollout transitions: 249280, reward mean: 3.3372 +num rollout transitions: 249378, reward mean: 3.3452 +num rollout transitions: 249357, reward mean: 3.3399 +num rollout transitions: 249338, reward mean: 3.3237 +num rollout transitions: 249292, reward mean: 3.3463 +num rollout transitions: 249296, reward mean: 3.3275 +num rollout transitions: 249321, reward mean: 3.3397 +num rollout transitions: 249316, reward mean: 3.3315 +num rollout transitions: 249360, reward mean: 3.3356 +num rollout transitions: 249363, reward mean: 3.3464 +num rollout transitions: 249347, reward mean: 3.3448 +num rollout transitions: 249441, reward mean: 3.3207 +num rollout transitions: 249302, reward mean: 3.3458 +num rollout transitions: 249367, reward mean: 3.3334 +num rollout transitions: 249339, reward mean: 3.3478 +num rollout transitions: 249331, reward mean: 3.3447 +num rollout transitions: 249360, reward mean: 3.3185 +num rollout transitions: 249314, reward mean: 3.3397 +num rollout transitions: 249300, reward mean: 3.3542 +num rollout transitions: 249306, reward mean: 3.3498 +num rollout transitions: 249277, reward mean: 3.3358 +num rollout transitions: 249408, reward mean: 3.3367 +num rollout transitions: 249349, reward mean: 3.3268 +num rollout transitions: 249372, reward mean: 3.3301 +num rollout transitions: 249309, reward mean: 3.3248 +num rollout transitions: 249319, reward mean: 3.3275 +num rollout transitions: 249340, reward mean: 3.3384 +num rollout transitions: 249338, reward mean: 3.3361 +num rollout transitions: 249238, reward mean: 3.3288 +num rollout transitions: 249344, reward mean: 3.3378 +num rollout transitions: 249292, reward mean: 3.3341 +num rollout transitions: 249302, reward mean: 3.3256 +num rollout transitions: 249272, reward mean: 3.3099 +num rollout transitions: 249342, reward mean: 3.3643 +num rollout transitions: 249261, reward mean: 3.3375 +num rollout transitions: 249228, reward mean: 3.3366 +num rollout transitions: 249340, reward mean: 3.3625 +num rollout transitions: 249331, reward mean: 3.3276 +num rollout transitions: 249453, reward mean: 3.3365 +num rollout transitions: 249207, reward mean: 3.3221 +num rollout transitions: 249354, reward mean: 3.3367 +num rollout transitions: 249292, reward mean: 3.3304 +num rollout transitions: 249225, reward mean: 3.3360 +num rollout transitions: 249311, reward mean: 3.3163 +num rollout transitions: 249373, reward mean: 3.3186 +num rollout transitions: 249330, reward mean: 3.3305 +num rollout transitions: 249363, reward mean: 3.3428 +num rollout transitions: 249425, reward mean: 3.3343 +num rollout transitions: 249339, reward mean: 3.3385 +---------------------------------------------------------------------------------- +| alpha | 0.0274 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.777 | +| loss/actor | -302 | +| loss/alpha | -0.00271 | +| loss/critic | 4.39 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249308, reward mean: 3.3428 +num rollout transitions: 249269, reward mean: 3.3491 +num rollout transitions: 249351, reward mean: 3.3203 +num rollout transitions: 249323, reward mean: 3.3329 +num rollout transitions: 249337, reward mean: 3.3301 +num rollout transitions: 249279, reward mean: 3.3486 +num rollout transitions: 249294, reward mean: 3.3378 +num rollout transitions: 249301, reward mean: 3.3449 +num rollout transitions: 249340, reward mean: 3.3355 +num rollout transitions: 249337, reward mean: 3.3263 +num rollout transitions: 249339, reward mean: 3.3372 +num rollout transitions: 249316, reward mean: 3.3357 +num rollout transitions: 249316, reward mean: 3.3214 +num rollout transitions: 249283, reward mean: 3.3392 +num rollout transitions: 249328, reward mean: 3.3270 +num rollout transitions: 249248, reward mean: 3.2958 +num rollout transitions: 249317, reward mean: 3.3438 +num rollout transitions: 249378, reward mean: 3.3399 +num rollout transitions: 249286, reward mean: 3.3382 +num rollout transitions: 249331, reward mean: 3.3355 +num rollout transitions: 249429, reward mean: 3.3508 +num rollout transitions: 249328, reward mean: 3.3443 +num rollout transitions: 249272, reward mean: 3.3354 +num rollout transitions: 249283, reward mean: 3.3269 +num rollout transitions: 249348, reward mean: 3.3576 +num rollout transitions: 249327, reward mean: 3.3655 +num rollout transitions: 249416, reward mean: 3.3419 +num rollout transitions: 249346, reward mean: 3.3586 +num rollout transitions: 249257, reward mean: 3.3367 +num rollout transitions: 249287, reward mean: 3.3202 +num rollout transitions: 249339, reward mean: 3.3446 +num rollout transitions: 249244, reward mean: 3.3459 +num rollout transitions: 249374, reward mean: 3.3336 +num rollout transitions: 249385, reward mean: 3.3406 +num rollout transitions: 249336, reward mean: 3.3406 +num rollout transitions: 249283, reward mean: 3.3259 +num rollout transitions: 249311, reward mean: 3.3237 +num rollout transitions: 249314, reward mean: 3.3390 +num rollout transitions: 249372, reward mean: 3.3332 +num rollout transitions: 249303, reward mean: 3.3370 +num rollout transitions: 249263, reward mean: 3.3392 +num rollout transitions: 249322, reward mean: 3.3326 +num rollout transitions: 249329, reward mean: 3.3459 +num rollout transitions: 249417, reward mean: 3.3473 +num rollout transitions: 249262, reward mean: 3.3360 +num rollout transitions: 249305, reward mean: 3.3436 +num rollout transitions: 249330, reward mean: 3.3359 +num rollout transitions: 249334, reward mean: 3.3556 +num rollout transitions: 249349, reward mean: 3.3453 +num rollout transitions: 249346, reward mean: 3.3346 +---------------------------------------------------------------------------------- +| alpha | 0.0278 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.844 | +| loss/actor | -303 | +| loss/alpha | 0.00385 | +| loss/critic | 5.41 | +| penalty/lcb_mean | 0.238 | +| penalty/lcb_std | 0.532 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249386, reward mean: 3.3483 +num rollout transitions: 249315, reward mean: 3.3365 +num rollout transitions: 249257, reward mean: 3.3498 +num rollout transitions: 249359, reward mean: 3.3449 +num rollout transitions: 249350, reward mean: 3.3321 +num rollout transitions: 249321, reward mean: 3.3345 +num rollout transitions: 249367, reward mean: 3.3358 +num rollout transitions: 249365, reward mean: 3.3412 +num rollout transitions: 249314, reward mean: 3.3503 +num rollout transitions: 249221, reward mean: 3.3604 +num rollout transitions: 249207, reward mean: 3.3556 +num rollout transitions: 249278, reward mean: 3.3417 +num rollout transitions: 249313, reward mean: 3.3340 +num rollout transitions: 249335, reward mean: 3.3395 +num rollout transitions: 249269, reward mean: 3.3122 +num rollout transitions: 249414, reward mean: 3.3220 +num rollout transitions: 249312, reward mean: 3.3501 +num rollout transitions: 249380, reward mean: 3.3444 +num rollout transitions: 249292, reward mean: 3.3489 +num rollout transitions: 249338, reward mean: 3.3340 +num rollout transitions: 249358, reward mean: 3.3260 +num rollout transitions: 249270, reward mean: 3.3339 +num rollout transitions: 249343, reward mean: 3.3483 +num rollout transitions: 249349, reward mean: 3.3485 +num rollout transitions: 249290, reward mean: 3.3249 +num rollout transitions: 249292, reward mean: 3.3471 +num rollout transitions: 249258, reward mean: 3.3280 +num rollout transitions: 249376, reward mean: 3.3528 +num rollout transitions: 249306, reward mean: 3.3259 +num rollout transitions: 249280, reward mean: 3.3371 +num rollout transitions: 249287, reward mean: 3.3361 +num rollout transitions: 249355, reward mean: 3.3126 +num rollout transitions: 249301, reward mean: 3.3360 +num rollout transitions: 249311, reward mean: 3.3302 +num rollout transitions: 249336, reward mean: 3.3111 +num rollout transitions: 249355, reward mean: 3.3128 +num rollout transitions: 249298, reward mean: 3.3251 +num rollout transitions: 249362, reward mean: 3.3373 +num rollout transitions: 249301, reward mean: 3.3405 +num rollout transitions: 249285, reward mean: 3.3230 +num rollout transitions: 249424, reward mean: 3.3424 +num rollout transitions: 249412, reward mean: 3.3307 +num rollout transitions: 249283, reward mean: 3.3462 +num rollout transitions: 249281, reward mean: 3.3433 +num rollout transitions: 249307, reward mean: 3.3230 +num rollout transitions: 249348, reward mean: 3.3376 +num rollout transitions: 249253, reward mean: 3.3491 +num rollout transitions: 249326, reward mean: 3.3214 +num rollout transitions: 249283, reward mean: 3.3471 +num rollout transitions: 249258, reward mean: 3.3522 +---------------------------------------------------------------------------------- +| alpha | 0.0271 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 114 | +| eval/normalized_episode_reward_std | 0.821 | +| loss/actor | -303 | +| loss/alpha | 5.79e-05 | +| loss/critic | 4.11 | +| penalty/lcb_mean | 0.234 | +| penalty/lcb_std | 0.517 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249328, reward mean: 3.3230 +num rollout transitions: 249302, reward mean: 3.3325 +num rollout transitions: 249340, reward mean: 3.3299 +num rollout transitions: 249290, reward mean: 3.3349 +num rollout transitions: 249279, reward mean: 3.3309 +num rollout transitions: 249305, reward mean: 3.3307 +num rollout transitions: 249291, reward mean: 3.3423 +num rollout transitions: 249318, reward mean: 3.3462 +num rollout transitions: 249217, reward mean: 3.3469 +num rollout transitions: 249273, reward mean: 3.3430 +num rollout transitions: 249265, reward mean: 3.3220 +num rollout transitions: 249307, reward mean: 3.3378 +num rollout transitions: 249375, reward mean: 3.3392 +num rollout transitions: 249309, reward mean: 3.3338 +num rollout transitions: 249337, reward mean: 3.3486 +num rollout transitions: 249362, reward mean: 3.3604 +num rollout transitions: 249363, reward mean: 3.3330 +num rollout transitions: 249308, reward mean: 3.3231 +num rollout transitions: 249348, reward mean: 3.3345 +num rollout transitions: 249301, reward mean: 3.3507 +num rollout transitions: 249384, reward mean: 3.3264 +num rollout transitions: 249317, reward mean: 3.3447 +num rollout transitions: 249280, reward mean: 3.3493 +num rollout transitions: 249349, reward mean: 3.3489 +num rollout transitions: 249274, reward mean: 3.3448 +num rollout transitions: 249332, reward mean: 3.3437 +num rollout transitions: 249300, reward mean: 3.3388 +num rollout transitions: 249303, reward mean: 3.3355 +num rollout transitions: 249319, reward mean: 3.3340 +num rollout transitions: 249394, reward mean: 3.3410 +num rollout transitions: 249296, reward mean: 3.3252 +num rollout transitions: 249328, reward mean: 3.3342 +num rollout transitions: 249241, reward mean: 3.3437 +num rollout transitions: 249312, reward mean: 3.3475 +num rollout transitions: 249335, reward mean: 3.3355 +num rollout transitions: 249385, reward mean: 3.3379 +num rollout transitions: 249304, reward mean: 3.3372 +num rollout transitions: 249360, reward mean: 3.3292 +num rollout transitions: 249405, reward mean: 3.3288 +num rollout transitions: 249295, reward mean: 3.3212 +num rollout transitions: 249412, reward mean: 3.3690 +num rollout transitions: 249413, reward mean: 3.3504 +num rollout transitions: 249397, reward mean: 3.3579 +num rollout transitions: 249410, reward mean: 3.3642 +num rollout transitions: 249406, reward mean: 3.3318 +num rollout transitions: 249337, reward mean: 3.3292 +num rollout transitions: 249265, reward mean: 3.3241 +num rollout transitions: 249351, reward mean: 3.3226 +num rollout transitions: 249293, reward mean: 3.3423 +num rollout transitions: 249239, reward mean: 3.3512 +---------------------------------------------------------------------------------- +| alpha | 0.0276 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.828 | +| loss/actor | -304 | +| loss/alpha | -0.0108 | +| loss/critic | 4.34 | +| penalty/lcb_mean | 0.237 | +| penalty/lcb_std | 0.524 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249302, reward mean: 3.3305 +num rollout transitions: 249309, reward mean: 3.3428 +num rollout transitions: 249315, reward mean: 3.3483 +num rollout transitions: 249229, reward mean: 3.3347 +num rollout transitions: 249274, reward mean: 3.3227 +num rollout transitions: 249326, reward mean: 3.3341 +num rollout transitions: 249391, reward mean: 3.3373 +num rollout transitions: 249305, reward mean: 3.3299 +num rollout transitions: 249349, reward mean: 3.3314 +num rollout transitions: 249348, reward mean: 3.3226 +num rollout transitions: 249327, reward mean: 3.3448 +num rollout transitions: 249336, reward mean: 3.3522 +num rollout transitions: 249389, reward mean: 3.3374 +num rollout transitions: 249317, reward mean: 3.3431 +num rollout transitions: 249341, reward mean: 3.3138 +num rollout transitions: 249243, reward mean: 3.3264 +num rollout transitions: 249268, reward mean: 3.3314 +num rollout transitions: 249339, reward mean: 3.3470 +num rollout transitions: 249335, reward mean: 3.3515 +num rollout transitions: 249239, reward mean: 3.3491 +num rollout transitions: 249364, reward mean: 3.3578 +num rollout transitions: 249295, reward mean: 3.3648 +num rollout transitions: 249367, reward mean: 3.3465 +num rollout transitions: 249318, reward mean: 3.3401 +num rollout transitions: 249353, reward mean: 3.3402 +num rollout transitions: 249371, reward mean: 3.3418 +num rollout transitions: 249269, reward mean: 3.3308 +num rollout transitions: 249273, reward mean: 3.3239 +num rollout transitions: 249375, reward mean: 3.3466 +num rollout transitions: 249283, reward mean: 3.3333 +num rollout transitions: 249319, reward mean: 3.3532 +num rollout transitions: 249327, reward mean: 3.3529 +num rollout transitions: 249285, reward mean: 3.3466 +num rollout transitions: 249355, reward mean: 3.3465 +num rollout transitions: 249297, reward mean: 3.3263 +num rollout transitions: 249318, reward mean: 3.3423 +num rollout transitions: 249295, reward mean: 3.3212 +num rollout transitions: 249291, reward mean: 3.3310 +num rollout transitions: 249310, reward mean: 3.3273 +num rollout transitions: 249318, reward mean: 3.3471 +num rollout transitions: 249296, reward mean: 3.3159 +num rollout transitions: 249301, reward mean: 3.3350 +num rollout transitions: 249325, reward mean: 3.3378 +num rollout transitions: 249270, reward mean: 3.3197 +num rollout transitions: 249225, reward mean: 3.3202 +num rollout transitions: 249320, reward mean: 3.3729 +num rollout transitions: 249329, reward mean: 3.3347 +num rollout transitions: 249267, reward mean: 3.3433 +num rollout transitions: 249240, reward mean: 3.3643 +num rollout transitions: 249371, reward mean: 3.3527 +---------------------------------------------------------------------------------- +| alpha | 0.0265 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.903 | +| loss/actor | -304 | +| loss/alpha | 0.0207 | +| loss/critic | 4.57 | +| penalty/lcb_mean | 0.234 | +| penalty/lcb_std | 0.508 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249325, reward mean: 3.3623 +num rollout transitions: 249329, reward mean: 3.3256 +num rollout transitions: 249294, reward mean: 3.3316 +num rollout transitions: 249315, reward mean: 3.3372 +num rollout transitions: 249416, reward mean: 3.3389 +num rollout transitions: 249365, reward mean: 3.3410 +num rollout transitions: 249311, reward mean: 3.3378 +num rollout transitions: 249242, reward mean: 3.3338 +num rollout transitions: 249316, reward mean: 3.3183 +num rollout transitions: 249259, reward mean: 3.3503 +num rollout transitions: 249263, reward mean: 3.3545 +num rollout transitions: 249333, reward mean: 3.3379 +num rollout transitions: 249304, reward mean: 3.3243 +num rollout transitions: 249397, reward mean: 3.3486 +num rollout transitions: 249377, reward mean: 3.3316 +num rollout transitions: 249320, reward mean: 3.3376 +num rollout transitions: 249276, reward mean: 3.3313 +num rollout transitions: 249347, reward mean: 3.3393 +num rollout transitions: 249337, reward mean: 3.3204 +num rollout transitions: 249319, reward mean: 3.3272 +num rollout transitions: 249290, reward mean: 3.3250 +num rollout transitions: 249356, reward mean: 3.3463 +num rollout transitions: 249293, reward mean: 3.3271 +num rollout transitions: 249389, reward mean: 3.3280 +num rollout transitions: 249269, reward mean: 3.3232 +num rollout transitions: 249326, reward mean: 3.3476 +num rollout transitions: 249367, reward mean: 3.3516 +num rollout transitions: 249317, reward mean: 3.3263 +num rollout transitions: 249390, reward mean: 3.3306 +num rollout transitions: 249413, reward mean: 3.3322 +num rollout transitions: 249338, reward mean: 3.3335 +num rollout transitions: 249337, reward mean: 3.3455 +num rollout transitions: 249325, reward mean: 3.3531 +num rollout transitions: 249342, reward mean: 3.3522 +num rollout transitions: 249259, reward mean: 3.3439 +num rollout transitions: 249280, reward mean: 3.3394 +num rollout transitions: 249341, reward mean: 3.3363 +num rollout transitions: 249342, reward mean: 3.3347 +num rollout transitions: 249313, reward mean: 3.3370 +num rollout transitions: 249358, reward mean: 3.3533 +num rollout transitions: 249373, reward mean: 3.3576 +num rollout transitions: 249312, reward mean: 3.3495 +num rollout transitions: 249369, reward mean: 3.3352 +num rollout transitions: 249310, reward mean: 3.3605 +num rollout transitions: 249301, reward mean: 3.3290 +num rollout transitions: 249400, reward mean: 3.3407 +num rollout transitions: 249313, reward mean: 3.3288 +num rollout transitions: 249284, reward mean: 3.3386 +num rollout transitions: 249407, reward mean: 3.3426 +num rollout transitions: 249264, reward mean: 3.3334 +---------------------------------------------------------------------------------- +| alpha | 0.0273 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.864 | +| loss/actor | -304 | +| loss/alpha | -0.00504 | +| loss/critic | 4 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.504 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249315, reward mean: 3.3371 +num rollout transitions: 249339, reward mean: 3.3298 +num rollout transitions: 249293, reward mean: 3.3245 +num rollout transitions: 249335, reward mean: 3.3318 +num rollout transitions: 249291, reward mean: 3.3337 +num rollout transitions: 249400, reward mean: 3.3450 +num rollout transitions: 249286, reward mean: 3.3340 +num rollout transitions: 249402, reward mean: 3.3384 +num rollout transitions: 249357, reward mean: 3.3412 +num rollout transitions: 249325, reward mean: 3.3381 +num rollout transitions: 249284, reward mean: 3.3447 +num rollout transitions: 249326, reward mean: 3.3487 +num rollout transitions: 249250, reward mean: 3.3353 +num rollout transitions: 249308, reward mean: 3.3417 +num rollout transitions: 249366, reward mean: 3.3459 +num rollout transitions: 249348, reward mean: 3.3381 +num rollout transitions: 249302, reward mean: 3.3478 +num rollout transitions: 249373, reward mean: 3.3413 +num rollout transitions: 249311, reward mean: 3.3414 +num rollout transitions: 249367, reward mean: 3.3364 +num rollout transitions: 249367, reward mean: 3.3416 +num rollout transitions: 249400, reward mean: 3.3364 +num rollout transitions: 249291, reward mean: 3.3281 +num rollout transitions: 249383, reward mean: 3.3397 +num rollout transitions: 249246, reward mean: 3.3288 +num rollout transitions: 249288, reward mean: 3.3335 +num rollout transitions: 249335, reward mean: 3.3469 +num rollout transitions: 249363, reward mean: 3.3462 +num rollout transitions: 249243, reward mean: 3.3388 +num rollout transitions: 249326, reward mean: 3.3396 +num rollout transitions: 249307, reward mean: 3.3298 +num rollout transitions: 249364, reward mean: 3.3558 +num rollout transitions: 249424, reward mean: 3.3534 +num rollout transitions: 249282, reward mean: 3.3391 +num rollout transitions: 249223, reward mean: 3.3413 +num rollout transitions: 249323, reward mean: 3.3296 +num rollout transitions: 249319, reward mean: 3.3442 +num rollout transitions: 249344, reward mean: 3.3424 +num rollout transitions: 249306, reward mean: 3.3348 +num rollout transitions: 249237, reward mean: 3.3389 +num rollout transitions: 249397, reward mean: 3.3260 +num rollout transitions: 249273, reward mean: 3.3303 +num rollout transitions: 249304, reward mean: 3.3346 +num rollout transitions: 249193, reward mean: 3.3175 +num rollout transitions: 249346, reward mean: 3.3306 +num rollout transitions: 249280, reward mean: 3.3331 +num rollout transitions: 249272, reward mean: 3.3341 +num rollout transitions: 249339, reward mean: 3.3346 +num rollout transitions: 249287, reward mean: 3.3338 +num rollout transitions: 249342, reward mean: 3.3326 +---------------------------------------------------------------------------------- +| alpha | 0.0262 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 114 | +| eval/normalized_episode_reward_std | 0.826 | +| loss/actor | -305 | +| loss/alpha | -0.0151 | +| loss/critic | 3.57 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.496 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249280, reward mean: 3.3313 +num rollout transitions: 249333, reward mean: 3.3145 +num rollout transitions: 249337, reward mean: 3.3619 +num rollout transitions: 249326, reward mean: 3.3515 +num rollout transitions: 249337, reward mean: 3.3292 +num rollout transitions: 249276, reward mean: 3.3318 +num rollout transitions: 249199, reward mean: 3.3331 +num rollout transitions: 249342, reward mean: 3.3438 +num rollout transitions: 249310, reward mean: 3.3509 +num rollout transitions: 249395, reward mean: 3.3325 +num rollout transitions: 249366, reward mean: 3.3264 +num rollout transitions: 249385, reward mean: 3.3383 +num rollout transitions: 249278, reward mean: 3.3323 +num rollout transitions: 249347, reward mean: 3.3382 +num rollout transitions: 249398, reward mean: 3.3431 +num rollout transitions: 249344, reward mean: 3.3291 +num rollout transitions: 249299, reward mean: 3.3310 +num rollout transitions: 249328, reward mean: 3.3382 +num rollout transitions: 249313, reward mean: 3.3340 +num rollout transitions: 249418, reward mean: 3.3300 +num rollout transitions: 249286, reward mean: 3.3263 +num rollout transitions: 249328, reward mean: 3.3358 +num rollout transitions: 249360, reward mean: 3.3344 +num rollout transitions: 249382, reward mean: 3.3413 +num rollout transitions: 249326, reward mean: 3.3227 +num rollout transitions: 249335, reward mean: 3.3254 +num rollout transitions: 249371, reward mean: 3.3350 +num rollout transitions: 249313, reward mean: 3.3333 +num rollout transitions: 249316, reward mean: 3.3333 +num rollout transitions: 249358, reward mean: 3.3451 +num rollout transitions: 249277, reward mean: 3.3385 +num rollout transitions: 249388, reward mean: 3.3388 +num rollout transitions: 249386, reward mean: 3.3470 +num rollout transitions: 249337, reward mean: 3.3550 +num rollout transitions: 249310, reward mean: 3.3411 +num rollout transitions: 249296, reward mean: 3.3398 +num rollout transitions: 249304, reward mean: 3.3322 +num rollout transitions: 249270, reward mean: 3.3251 +num rollout transitions: 249296, reward mean: 3.3421 +num rollout transitions: 249364, reward mean: 3.3554 +num rollout transitions: 249359, reward mean: 3.3440 +num rollout transitions: 249337, reward mean: 3.3394 +num rollout transitions: 249266, reward mean: 3.3527 +num rollout transitions: 249366, reward mean: 3.3469 +num rollout transitions: 249341, reward mean: 3.3694 +num rollout transitions: 249377, reward mean: 3.3594 +num rollout transitions: 249348, reward mean: 3.3609 +num rollout transitions: 249288, reward mean: 3.3493 +num rollout transitions: 249289, reward mean: 3.3359 +num rollout transitions: 249355, reward mean: 3.3423 +---------------------------------------------------------------------------------- +| alpha | 0.0261 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.731 | +| loss/actor | -305 | +| loss/alpha | 0.00677 | +| loss/critic | 4.01 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.497 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249307, reward mean: 3.3455 +num rollout transitions: 249309, reward mean: 3.3303 +num rollout transitions: 249307, reward mean: 3.3400 +num rollout transitions: 249364, reward mean: 3.3146 +num rollout transitions: 249298, reward mean: 3.3353 +num rollout transitions: 249351, reward mean: 3.3387 +num rollout transitions: 249334, reward mean: 3.3441 +num rollout transitions: 249325, reward mean: 3.3374 +num rollout transitions: 249378, reward mean: 3.3289 +num rollout transitions: 249337, reward mean: 3.3285 +num rollout transitions: 249375, reward mean: 3.3214 +num rollout transitions: 249249, reward mean: 3.3421 +num rollout transitions: 249339, reward mean: 3.3375 +num rollout transitions: 249365, reward mean: 3.3343 +num rollout transitions: 249315, reward mean: 3.3252 +num rollout transitions: 249348, reward mean: 3.3302 +num rollout transitions: 249320, reward mean: 3.3512 +num rollout transitions: 249266, reward mean: 3.3253 +num rollout transitions: 249263, reward mean: 3.3392 +num rollout transitions: 249328, reward mean: 3.3212 +num rollout transitions: 249324, reward mean: 3.3389 +num rollout transitions: 249320, reward mean: 3.3378 +num rollout transitions: 249416, reward mean: 3.3478 +num rollout transitions: 249355, reward mean: 3.3409 +num rollout transitions: 249313, reward mean: 3.3536 +num rollout transitions: 249304, reward mean: 3.3389 +num rollout transitions: 249348, reward mean: 3.3481 +num rollout transitions: 249313, reward mean: 3.3422 +num rollout transitions: 249339, reward mean: 3.3400 +num rollout transitions: 249345, reward mean: 3.3407 +num rollout transitions: 249289, reward mean: 3.3472 +num rollout transitions: 249368, reward mean: 3.3479 +num rollout transitions: 249356, reward mean: 3.3360 +num rollout transitions: 249244, reward mean: 3.3510 +num rollout transitions: 249266, reward mean: 3.3424 +num rollout transitions: 249262, reward mean: 3.3453 +num rollout transitions: 249373, reward mean: 3.3252 +num rollout transitions: 249363, reward mean: 3.3183 +num rollout transitions: 249290, reward mean: 3.3400 +num rollout transitions: 249320, reward mean: 3.3577 +num rollout transitions: 249319, reward mean: 3.3305 +num rollout transitions: 249289, reward mean: 3.3387 +num rollout transitions: 249286, reward mean: 3.3584 +num rollout transitions: 249313, reward mean: 3.3361 +num rollout transitions: 249221, reward mean: 3.3419 +num rollout transitions: 249332, reward mean: 3.3427 +num rollout transitions: 249352, reward mean: 3.3329 +num rollout transitions: 249384, reward mean: 3.3516 +num rollout transitions: 249276, reward mean: 3.3492 +num rollout transitions: 249284, reward mean: 3.3530 +---------------------------------------------------------------------------------- +| alpha | 0.0253 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.832 | +| loss/actor | -306 | +| loss/alpha | 0.00343 | +| loss/critic | 3.3 | +| penalty/lcb_mean | 0.225 | +| penalty/lcb_std | 0.488 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249311, reward mean: 3.3500 +num rollout transitions: 249285, reward mean: 3.3280 +num rollout transitions: 249303, reward mean: 3.3276 +num rollout transitions: 249310, reward mean: 3.3366 +num rollout transitions: 249327, reward mean: 3.3360 +num rollout transitions: 249361, reward mean: 3.3465 +num rollout transitions: 249339, reward mean: 3.3547 +num rollout transitions: 249397, reward mean: 3.3525 +num rollout transitions: 249310, reward mean: 3.3575 +num rollout transitions: 249286, reward mean: 3.3569 +num rollout transitions: 249359, reward mean: 3.3429 +num rollout transitions: 249289, reward mean: 3.3498 +num rollout transitions: 249336, reward mean: 3.3323 +num rollout transitions: 249352, reward mean: 3.3586 +num rollout transitions: 249321, reward mean: 3.3366 +num rollout transitions: 249331, reward mean: 3.3446 +num rollout transitions: 249306, reward mean: 3.3467 +num rollout transitions: 249294, reward mean: 3.3533 +num rollout transitions: 249258, reward mean: 3.3510 +num rollout transitions: 249348, reward mean: 3.3350 +num rollout transitions: 249318, reward mean: 3.3531 +num rollout transitions: 249358, reward mean: 3.3416 +num rollout transitions: 249357, reward mean: 3.3513 +num rollout transitions: 249340, reward mean: 3.3237 +num rollout transitions: 249356, reward mean: 3.3393 +num rollout transitions: 249393, reward mean: 3.3465 +num rollout transitions: 249356, reward mean: 3.3362 +num rollout transitions: 249299, reward mean: 3.3356 +num rollout transitions: 249303, reward mean: 3.3446 +num rollout transitions: 249342, reward mean: 3.3467 +num rollout transitions: 249367, reward mean: 3.3491 +num rollout transitions: 249395, reward mean: 3.3410 +num rollout transitions: 249355, reward mean: 3.3522 +num rollout transitions: 249307, reward mean: 3.3377 +num rollout transitions: 249313, reward mean: 3.3404 +num rollout transitions: 249346, reward mean: 3.3334 +num rollout transitions: 249315, reward mean: 3.3282 +num rollout transitions: 249356, reward mean: 3.3336 +num rollout transitions: 249420, reward mean: 3.3360 +num rollout transitions: 249316, reward mean: 3.3558 +num rollout transitions: 249330, reward mean: 3.3390 +num rollout transitions: 249308, reward mean: 3.3253 +num rollout transitions: 249409, reward mean: 3.3523 +num rollout transitions: 249332, reward mean: 3.3533 +num rollout transitions: 249267, reward mean: 3.3528 +num rollout transitions: 249306, reward mean: 3.3471 +num rollout transitions: 249281, reward mean: 3.3566 +num rollout transitions: 249360, reward mean: 3.3367 +num rollout transitions: 249347, reward mean: 3.3317 +num rollout transitions: 249383, reward mean: 3.3378 +---------------------------------------------------------------------------------- +| alpha | 0.0266 | +| eval/episode_length | 248 | +| eval/episode_length_std | 40.2 | +| eval/normalized_episode_reward | 25 | +| eval/normalized_episode_reward_std | 5.33 | +| loss/actor | -306 | +| loss/alpha | -0.00316 | +| loss/critic | 3.89 | +| penalty/lcb_mean | 0.226 | +| penalty/lcb_std | 0.493 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249346, reward mean: 3.3266 +num rollout transitions: 249305, reward mean: 3.3440 +num rollout transitions: 249279, reward mean: 3.3470 +num rollout transitions: 249309, reward mean: 3.3326 +num rollout transitions: 249377, reward mean: 3.3484 +num rollout transitions: 249300, reward mean: 3.3326 +num rollout transitions: 249288, reward mean: 3.3533 +num rollout transitions: 249328, reward mean: 3.3376 +num rollout transitions: 249357, reward mean: 3.3382 +num rollout transitions: 249298, reward mean: 3.3343 +num rollout transitions: 249432, reward mean: 3.3459 +num rollout transitions: 249320, reward mean: 3.3369 +num rollout transitions: 249377, reward mean: 3.3343 +num rollout transitions: 249311, reward mean: 3.3399 +num rollout transitions: 249440, reward mean: 3.3246 +num rollout transitions: 249298, reward mean: 3.3233 +num rollout transitions: 249342, reward mean: 3.3312 +num rollout transitions: 249295, reward mean: 3.3261 +num rollout transitions: 249282, reward mean: 3.3366 +num rollout transitions: 249326, reward mean: 3.3430 +num rollout transitions: 249336, reward mean: 3.3517 +num rollout transitions: 249350, reward mean: 3.3365 +num rollout transitions: 249224, reward mean: 3.3337 +num rollout transitions: 249336, reward mean: 3.3389 +num rollout transitions: 249311, reward mean: 3.3276 +num rollout transitions: 249350, reward mean: 3.3440 +num rollout transitions: 249306, reward mean: 3.3467 +num rollout transitions: 249390, reward mean: 3.3280 +num rollout transitions: 249240, reward mean: 3.3380 +num rollout transitions: 249333, reward mean: 3.3494 +num rollout transitions: 249346, reward mean: 3.3437 +num rollout transitions: 249326, reward mean: 3.3366 +num rollout transitions: 249400, reward mean: 3.3341 +num rollout transitions: 249356, reward mean: 3.3130 +num rollout transitions: 249335, reward mean: 3.3437 +num rollout transitions: 249282, reward mean: 3.3449 +num rollout transitions: 249383, reward mean: 3.3299 +num rollout transitions: 249323, reward mean: 3.3244 +num rollout transitions: 249337, reward mean: 3.3359 +num rollout transitions: 249242, reward mean: 3.3432 +num rollout transitions: 249340, reward mean: 3.3360 +num rollout transitions: 249337, reward mean: 3.3412 +num rollout transitions: 249325, reward mean: 3.3406 +num rollout transitions: 249327, reward mean: 3.3223 +num rollout transitions: 249411, reward mean: 3.3377 +num rollout transitions: 249315, reward mean: 3.3388 +num rollout transitions: 249331, reward mean: 3.3387 +num rollout transitions: 249411, reward mean: 3.3388 +num rollout transitions: 249331, reward mean: 3.3344 +num rollout transitions: 249357, reward mean: 3.3615 +---------------------------------------------------------------------------------- +| alpha | 0.0258 | +| eval/episode_length | 983 | +| eval/episode_length_std | 119 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 14.5 | +| loss/actor | -307 | +| loss/alpha | 0.00577 | +| loss/critic | 3.16 | +| penalty/lcb_mean | 0.224 | +| penalty/lcb_std | 0.488 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249336, reward mean: 3.3551 +num rollout transitions: 249234, reward mean: 3.3449 +num rollout transitions: 249376, reward mean: 3.3308 +num rollout transitions: 249324, reward mean: 3.3203 +num rollout transitions: 249361, reward mean: 3.3513 +num rollout transitions: 249291, reward mean: 3.3427 +num rollout transitions: 249244, reward mean: 3.3508 +num rollout transitions: 249221, reward mean: 3.3419 +num rollout transitions: 249387, reward mean: 3.3378 +num rollout transitions: 249331, reward mean: 3.3536 +num rollout transitions: 249403, reward mean: 3.3541 +num rollout transitions: 249355, reward mean: 3.3437 +num rollout transitions: 249338, reward mean: 3.3414 +num rollout transitions: 249344, reward mean: 3.3281 +num rollout transitions: 249323, reward mean: 3.3408 +num rollout transitions: 249325, reward mean: 3.3478 +num rollout transitions: 249280, reward mean: 3.3501 +num rollout transitions: 249341, reward mean: 3.3364 +num rollout transitions: 249372, reward mean: 3.3484 +num rollout transitions: 249248, reward mean: 3.3234 +num rollout transitions: 249315, reward mean: 3.3242 +num rollout transitions: 249365, reward mean: 3.3330 +num rollout transitions: 249324, reward mean: 3.3451 +num rollout transitions: 249370, reward mean: 3.3319 +num rollout transitions: 249293, reward mean: 3.3389 +num rollout transitions: 249274, reward mean: 3.3412 +num rollout transitions: 249390, reward mean: 3.3458 +num rollout transitions: 249372, reward mean: 3.3240 +num rollout transitions: 249309, reward mean: 3.3360 +num rollout transitions: 249378, reward mean: 3.3483 +num rollout transitions: 249374, reward mean: 3.3295 +num rollout transitions: 249330, reward mean: 3.3382 +num rollout transitions: 249398, reward mean: 3.3311 +num rollout transitions: 249348, reward mean: 3.3372 +num rollout transitions: 249372, reward mean: 3.3474 +num rollout transitions: 249281, reward mean: 3.3314 +num rollout transitions: 249320, reward mean: 3.3325 +num rollout transitions: 249368, reward mean: 3.3292 +num rollout transitions: 249341, reward mean: 3.3296 +num rollout transitions: 249362, reward mean: 3.3434 +num rollout transitions: 249314, reward mean: 3.3326 +num rollout transitions: 249335, reward mean: 3.3372 +num rollout transitions: 249280, reward mean: 3.3362 +num rollout transitions: 249267, reward mean: 3.3369 +num rollout transitions: 249351, reward mean: 3.3396 +num rollout transitions: 249306, reward mean: 3.3311 +num rollout transitions: 249360, reward mean: 3.3486 +num rollout transitions: 249318, reward mean: 3.3616 +num rollout transitions: 249248, reward mean: 3.3366 +num rollout transitions: 249331, reward mean: 3.3340 +----------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.797 | +| loss/actor | -307 | +| loss/alpha | -0.000519 | +| loss/critic | 3.59 | +| penalty/lcb_mean | 0.226 | +| penalty/lcb_std | 0.5 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 249337, reward mean: 3.3605 +num rollout transitions: 249342, reward mean: 3.3419 +num rollout transitions: 249379, reward mean: 3.3334 +num rollout transitions: 249275, reward mean: 3.3398 +num rollout transitions: 249307, reward mean: 3.3480 +num rollout transitions: 249281, reward mean: 3.3557 +num rollout transitions: 249402, reward mean: 3.3517 +num rollout transitions: 249384, reward mean: 3.3546 +num rollout transitions: 249296, reward mean: 3.3361 +num rollout transitions: 249359, reward mean: 3.3508 +num rollout transitions: 249339, reward mean: 3.3461 +num rollout transitions: 249376, reward mean: 3.3388 +num rollout transitions: 249374, reward mean: 3.3528 +num rollout transitions: 249213, reward mean: 3.3308 +num rollout transitions: 249297, reward mean: 3.3572 +num rollout transitions: 249364, reward mean: 3.3451 +num rollout transitions: 249283, reward mean: 3.3292 +num rollout transitions: 249350, reward mean: 3.3437 +num rollout transitions: 249416, reward mean: 3.3612 +num rollout transitions: 249304, reward mean: 3.3383 +num rollout transitions: 249316, reward mean: 3.3414 +num rollout transitions: 249321, reward mean: 3.3513 +num rollout transitions: 249313, reward mean: 3.3362 +num rollout transitions: 249305, reward mean: 3.3430 +num rollout transitions: 249356, reward mean: 3.3477 +num rollout transitions: 249332, reward mean: 3.3414 +num rollout transitions: 249329, reward mean: 3.3323 +num rollout transitions: 249411, reward mean: 3.3440 +num rollout transitions: 249349, reward mean: 3.3411 +num rollout transitions: 249320, reward mean: 3.3371 +num rollout transitions: 249322, reward mean: 3.3483 +num rollout transitions: 249308, reward mean: 3.3539 +num rollout transitions: 249250, reward mean: 3.3447 +num rollout transitions: 249335, reward mean: 3.3500 +num rollout transitions: 249359, reward mean: 3.3418 +num rollout transitions: 249300, reward mean: 3.3429 +num rollout transitions: 249341, reward mean: 3.3261 +num rollout transitions: 249314, reward mean: 3.3540 +num rollout transitions: 249272, reward mean: 3.3404 +num rollout transitions: 249392, reward mean: 3.3523 +num rollout transitions: 249285, reward mean: 3.3341 +num rollout transitions: 249185, reward mean: 3.3384 +num rollout transitions: 249307, reward mean: 3.3404 +num rollout transitions: 249264, reward mean: 3.3389 +num rollout transitions: 249370, reward mean: 3.3272 +num rollout transitions: 249286, reward mean: 3.3480 +num rollout transitions: 249331, reward mean: 3.3545 +num rollout transitions: 249339, reward mean: 3.3517 +num rollout transitions: 249193, reward mean: 3.3353 +num rollout transitions: 249213, reward mean: 3.3434 +---------------------------------------------------------------------------------- +| alpha | 0.0265 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.819 | +| loss/actor | -306 | +| loss/alpha | 0.00361 | +| loss/critic | 3.57 | +| penalty/lcb_mean | 0.223 | +| penalty/lcb_std | 0.481 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249302, reward mean: 3.3498 +num rollout transitions: 249301, reward mean: 3.3471 +num rollout transitions: 249273, reward mean: 3.3496 +num rollout transitions: 249391, reward mean: 3.3489 +num rollout transitions: 249368, reward mean: 3.3530 +num rollout transitions: 249279, reward mean: 3.3462 +num rollout transitions: 249350, reward mean: 3.3517 +num rollout transitions: 249249, reward mean: 3.3538 +num rollout transitions: 249332, reward mean: 3.3338 +num rollout transitions: 249338, reward mean: 3.3292 +num rollout transitions: 249278, reward mean: 3.3315 +num rollout transitions: 249253, reward mean: 3.3470 +num rollout transitions: 249356, reward mean: 3.3402 +num rollout transitions: 249210, reward mean: 3.3301 +num rollout transitions: 249346, reward mean: 3.3318 +num rollout transitions: 249295, reward mean: 3.3303 +num rollout transitions: 249304, reward mean: 3.3416 +num rollout transitions: 249360, reward mean: 3.3603 +num rollout transitions: 249361, reward mean: 3.3683 +num rollout transitions: 249313, reward mean: 3.3702 +num rollout transitions: 249333, reward mean: 3.3406 +num rollout transitions: 249355, reward mean: 3.3363 +num rollout transitions: 249355, reward mean: 3.3394 +num rollout transitions: 249341, reward mean: 3.3416 +num rollout transitions: 249340, reward mean: 3.3461 +num rollout transitions: 249309, reward mean: 3.3455 +num rollout transitions: 249302, reward mean: 3.3514 +num rollout transitions: 249280, reward mean: 3.3533 +num rollout transitions: 249361, reward mean: 3.3396 +num rollout transitions: 249289, reward mean: 3.3535 +num rollout transitions: 249384, reward mean: 3.3486 +num rollout transitions: 249313, reward mean: 3.3332 +num rollout transitions: 249328, reward mean: 3.3423 +num rollout transitions: 249364, reward mean: 3.3346 +num rollout transitions: 249320, reward mean: 3.3408 +num rollout transitions: 249348, reward mean: 3.3458 +num rollout transitions: 249289, reward mean: 3.3418 +num rollout transitions: 249327, reward mean: 3.3486 +num rollout transitions: 249363, reward mean: 3.3380 +num rollout transitions: 249306, reward mean: 3.3345 +num rollout transitions: 249386, reward mean: 3.3391 +num rollout transitions: 249353, reward mean: 3.3443 +num rollout transitions: 249301, reward mean: 3.3362 +num rollout transitions: 249305, reward mean: 3.3315 +num rollout transitions: 249365, reward mean: 3.3492 +num rollout transitions: 249356, reward mean: 3.3431 +num rollout transitions: 249266, reward mean: 3.3262 +num rollout transitions: 249335, reward mean: 3.3445 +num rollout transitions: 249341, reward mean: 3.3356 +num rollout transitions: 249305, reward mean: 3.3568 +---------------------------------------------------------------------------------- +| alpha | 0.0267 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 0.771 | +| loss/actor | -306 | +| loss/alpha | 0.00297 | +| loss/critic | 3.81 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.483 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249355, reward mean: 3.3669 +num rollout transitions: 249237, reward mean: 3.3480 +num rollout transitions: 249329, reward mean: 3.3542 +num rollout transitions: 249300, reward mean: 3.3538 +num rollout transitions: 249355, reward mean: 3.3481 +num rollout transitions: 249276, reward mean: 3.3405 +num rollout transitions: 249360, reward mean: 3.3300 +num rollout transitions: 249331, reward mean: 3.3442 +num rollout transitions: 249359, reward mean: 3.3410 +num rollout transitions: 249318, reward mean: 3.3400 +num rollout transitions: 249272, reward mean: 3.3414 +num rollout transitions: 249362, reward mean: 3.3377 +num rollout transitions: 249323, reward mean: 3.3316 +num rollout transitions: 249320, reward mean: 3.3233 +num rollout transitions: 249379, reward mean: 3.3365 +num rollout transitions: 249324, reward mean: 3.3385 +num rollout transitions: 249333, reward mean: 3.3375 +num rollout transitions: 249249, reward mean: 3.3306 +num rollout transitions: 249398, reward mean: 3.3359 +num rollout transitions: 249247, reward mean: 3.3306 +num rollout transitions: 249295, reward mean: 3.3296 +num rollout transitions: 249314, reward mean: 3.3541 +num rollout transitions: 249349, reward mean: 3.3379 +num rollout transitions: 249269, reward mean: 3.3349 +num rollout transitions: 249224, reward mean: 3.3401 +num rollout transitions: 249320, reward mean: 3.3252 +num rollout transitions: 249278, reward mean: 3.3444 +num rollout transitions: 249337, reward mean: 3.3384 +num rollout transitions: 249262, reward mean: 3.3419 +num rollout transitions: 249342, reward mean: 3.3307 +num rollout transitions: 249376, reward mean: 3.3497 +num rollout transitions: 249231, reward mean: 3.3480 +num rollout transitions: 249384, reward mean: 3.3596 +num rollout transitions: 249361, reward mean: 3.3472 +num rollout transitions: 249274, reward mean: 3.3430 +num rollout transitions: 249308, reward mean: 3.3342 +num rollout transitions: 249309, reward mean: 3.3491 +num rollout transitions: 249361, reward mean: 3.3356 +num rollout transitions: 249320, reward mean: 3.3464 +num rollout transitions: 249354, reward mean: 3.3341 +num rollout transitions: 249315, reward mean: 3.3355 +num rollout transitions: 249265, reward mean: 3.3372 +num rollout transitions: 249293, reward mean: 3.3447 +num rollout transitions: 249421, reward mean: 3.3572 +num rollout transitions: 249457, reward mean: 3.3389 +num rollout transitions: 249282, reward mean: 3.3591 +num rollout transitions: 249266, reward mean: 3.3451 +num rollout transitions: 249352, reward mean: 3.3492 +num rollout transitions: 249228, reward mean: 3.3420 +num rollout transitions: 249301, reward mean: 3.3490 +---------------------------------------------------------------------------------- +| alpha | 0.0264 | +| eval/episode_length | 598 | +| eval/episode_length_std | 427 | +| eval/normalized_episode_reward | 66.1 | +| eval/normalized_episode_reward_std | 50.4 | +| loss/actor | -307 | +| loss/alpha | -0.0117 | +| loss/critic | 3.78 | +| penalty/lcb_mean | 0.219 | +| penalty/lcb_std | 0.473 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249244, reward mean: 3.3298 +num rollout transitions: 249336, reward mean: 3.3240 +num rollout transitions: 249262, reward mean: 3.3266 +num rollout transitions: 249229, reward mean: 3.3427 +num rollout transitions: 249373, reward mean: 3.3459 +num rollout transitions: 249309, reward mean: 3.3361 +num rollout transitions: 249322, reward mean: 3.3493 +num rollout transitions: 249267, reward mean: 3.3392 +num rollout transitions: 249271, reward mean: 3.3359 +num rollout transitions: 249256, reward mean: 3.3271 +num rollout transitions: 249388, reward mean: 3.3436 +num rollout transitions: 249361, reward mean: 3.3354 +num rollout transitions: 249369, reward mean: 3.3383 +num rollout transitions: 249353, reward mean: 3.3394 +num rollout transitions: 249309, reward mean: 3.3481 +num rollout transitions: 249267, reward mean: 3.3415 +num rollout transitions: 249385, reward mean: 3.3441 +num rollout transitions: 249396, reward mean: 3.3400 +num rollout transitions: 249302, reward mean: 3.3328 +num rollout transitions: 249344, reward mean: 3.3442 +num rollout transitions: 249423, reward mean: 3.3465 +num rollout transitions: 249319, reward mean: 3.3352 +num rollout transitions: 249393, reward mean: 3.3433 +num rollout transitions: 249336, reward mean: 3.3327 +num rollout transitions: 249315, reward mean: 3.3374 +num rollout transitions: 249387, reward mean: 3.3467 +num rollout transitions: 249310, reward mean: 3.3352 +num rollout transitions: 249356, reward mean: 3.3363 +num rollout transitions: 249374, reward mean: 3.3317 +num rollout transitions: 249367, reward mean: 3.3341 +num rollout transitions: 249252, reward mean: 3.3401 +num rollout transitions: 249246, reward mean: 3.3338 +num rollout transitions: 249308, reward mean: 3.3345 +num rollout transitions: 249271, reward mean: 3.3453 +num rollout transitions: 249234, reward mean: 3.3134 +num rollout transitions: 249330, reward mean: 3.3377 +num rollout transitions: 249356, reward mean: 3.3411 +num rollout transitions: 249342, reward mean: 3.3482 +num rollout transitions: 249297, reward mean: 3.3307 +num rollout transitions: 249218, reward mean: 3.3387 +num rollout transitions: 249339, reward mean: 3.3292 +num rollout transitions: 249366, reward mean: 3.3504 +num rollout transitions: 249313, reward mean: 3.3446 +num rollout transitions: 249356, reward mean: 3.3467 +num rollout transitions: 249345, reward mean: 3.3381 +num rollout transitions: 249291, reward mean: 3.3484 +num rollout transitions: 249303, reward mean: 3.3433 +num rollout transitions: 249322, reward mean: 3.3399 +num rollout transitions: 249373, reward mean: 3.3353 +num rollout transitions: 249320, reward mean: 3.3282 +---------------------------------------------------------------------------------- +| alpha | 0.0258 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.825 | +| loss/actor | -307 | +| loss/alpha | 0.00702 | +| loss/critic | 3.35 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.484 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249318, reward mean: 3.3374 +num rollout transitions: 249260, reward mean: 3.3324 +num rollout transitions: 249311, reward mean: 3.3425 +num rollout transitions: 249290, reward mean: 3.3500 +num rollout transitions: 249324, reward mean: 3.3472 +num rollout transitions: 249307, reward mean: 3.3363 +num rollout transitions: 249411, reward mean: 3.3546 +num rollout transitions: 249354, reward mean: 3.3421 +num rollout transitions: 249403, reward mean: 3.3457 +num rollout transitions: 249385, reward mean: 3.3404 +num rollout transitions: 249310, reward mean: 3.3296 +num rollout transitions: 249321, reward mean: 3.3383 +num rollout transitions: 249289, reward mean: 3.3524 +num rollout transitions: 249310, reward mean: 3.3435 +num rollout transitions: 249390, reward mean: 3.3296 +num rollout transitions: 249308, reward mean: 3.3340 +num rollout transitions: 249388, reward mean: 3.3360 +num rollout transitions: 249315, reward mean: 3.3357 +num rollout transitions: 249391, reward mean: 3.3249 +num rollout transitions: 249320, reward mean: 3.3308 +num rollout transitions: 249287, reward mean: 3.3336 +num rollout transitions: 249258, reward mean: 3.3402 +num rollout transitions: 249239, reward mean: 3.3433 +num rollout transitions: 249385, reward mean: 3.3362 +num rollout transitions: 249283, reward mean: 3.3522 +num rollout transitions: 249376, reward mean: 3.3390 +num rollout transitions: 249272, reward mean: 3.3321 +num rollout transitions: 249281, reward mean: 3.3404 +num rollout transitions: 249358, reward mean: 3.3198 +num rollout transitions: 249381, reward mean: 3.3388 +num rollout transitions: 249308, reward mean: 3.3384 +num rollout transitions: 249331, reward mean: 3.3331 +num rollout transitions: 249371, reward mean: 3.3376 +num rollout transitions: 249420, reward mean: 3.3446 +num rollout transitions: 249300, reward mean: 3.3449 +num rollout transitions: 249221, reward mean: 3.3304 +num rollout transitions: 249329, reward mean: 3.3340 +num rollout transitions: 249347, reward mean: 3.3477 +num rollout transitions: 249275, reward mean: 3.3264 +num rollout transitions: 249382, reward mean: 3.3324 +num rollout transitions: 249313, reward mean: 3.3361 +num rollout transitions: 249362, reward mean: 3.3267 +num rollout transitions: 249358, reward mean: 3.3437 +num rollout transitions: 249335, reward mean: 3.3298 +num rollout transitions: 249311, reward mean: 3.3519 +num rollout transitions: 249308, reward mean: 3.3322 +num rollout transitions: 249335, reward mean: 3.3306 +num rollout transitions: 249385, reward mean: 3.3489 +num rollout transitions: 249294, reward mean: 3.3460 +num rollout transitions: 249257, reward mean: 3.3435 +---------------------------------------------------------------------------------- +| alpha | 0.0256 | +| eval/episode_length | 403 | +| eval/episode_length_std | 391 | +| eval/normalized_episode_reward | 43.4 | +| eval/normalized_episode_reward_std | 46.2 | +| loss/actor | -307 | +| loss/alpha | -0.00846 | +| loss/critic | 3.38 | +| penalty/lcb_mean | 0.224 | +| penalty/lcb_std | 0.487 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249312, reward mean: 3.3437 +num rollout transitions: 249312, reward mean: 3.3303 +num rollout transitions: 249308, reward mean: 3.3359 +num rollout transitions: 249361, reward mean: 3.3343 +num rollout transitions: 249353, reward mean: 3.3444 +num rollout transitions: 249346, reward mean: 3.3438 +num rollout transitions: 249313, reward mean: 3.3366 +num rollout transitions: 249393, reward mean: 3.3497 +num rollout transitions: 249313, reward mean: 3.3363 +num rollout transitions: 249376, reward mean: 3.3590 +num rollout transitions: 249377, reward mean: 3.3455 +num rollout transitions: 249409, reward mean: 3.3405 +num rollout transitions: 249322, reward mean: 3.3413 +num rollout transitions: 249318, reward mean: 3.3290 +num rollout transitions: 249372, reward mean: 3.3474 +num rollout transitions: 249246, reward mean: 3.3359 +num rollout transitions: 249392, reward mean: 3.3385 +num rollout transitions: 249311, reward mean: 3.3379 +num rollout transitions: 249380, reward mean: 3.3341 +num rollout transitions: 249312, reward mean: 3.3350 +num rollout transitions: 249355, reward mean: 3.3509 +num rollout transitions: 249341, reward mean: 3.3450 +num rollout transitions: 249275, reward mean: 3.3587 +num rollout transitions: 249393, reward mean: 3.3316 +num rollout transitions: 249371, reward mean: 3.3511 +num rollout transitions: 249328, reward mean: 3.3497 +num rollout transitions: 249313, reward mean: 3.3349 +num rollout transitions: 249346, reward mean: 3.3364 +num rollout transitions: 249314, reward mean: 3.3404 +num rollout transitions: 249295, reward mean: 3.3571 +num rollout transitions: 249285, reward mean: 3.3572 +num rollout transitions: 249371, reward mean: 3.3521 +num rollout transitions: 249288, reward mean: 3.3490 +num rollout transitions: 249305, reward mean: 3.3407 +num rollout transitions: 249355, reward mean: 3.3444 +num rollout transitions: 249326, reward mean: 3.3492 +num rollout transitions: 249374, reward mean: 3.3371 +num rollout transitions: 249300, reward mean: 3.3417 +num rollout transitions: 249364, reward mean: 3.3308 +num rollout transitions: 249394, reward mean: 3.3379 +num rollout transitions: 249314, reward mean: 3.3490 +num rollout transitions: 249318, reward mean: 3.3339 +num rollout transitions: 249312, reward mean: 3.3406 +num rollout transitions: 249270, reward mean: 3.3375 +num rollout transitions: 249342, reward mean: 3.3442 +num rollout transitions: 249397, reward mean: 3.3284 +num rollout transitions: 249265, reward mean: 3.3220 +num rollout transitions: 249330, reward mean: 3.3328 +num rollout transitions: 249331, reward mean: 3.3440 +num rollout transitions: 249273, reward mean: 3.3482 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 891 | +| eval/episode_length_std | 283 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 33.7 | +| loss/actor | -306 | +| loss/alpha | -0.0081 | +| loss/critic | 3.55 | +| penalty/lcb_mean | 0.228 | +| penalty/lcb_std | 0.499 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249275, reward mean: 3.3398 +num rollout transitions: 249214, reward mean: 3.3435 +num rollout transitions: 249319, reward mean: 3.3315 +num rollout transitions: 249327, reward mean: 3.3327 +num rollout transitions: 249384, reward mean: 3.3362 +num rollout transitions: 249309, reward mean: 3.3253 +num rollout transitions: 249338, reward mean: 3.3404 +num rollout transitions: 249367, reward mean: 3.3460 +num rollout transitions: 249327, reward mean: 3.3518 +num rollout transitions: 249376, reward mean: 3.3564 +num rollout transitions: 249371, reward mean: 3.3432 +num rollout transitions: 249294, reward mean: 3.3458 +num rollout transitions: 249275, reward mean: 3.3208 +num rollout transitions: 249319, reward mean: 3.3319 +num rollout transitions: 249278, reward mean: 3.3301 +num rollout transitions: 249317, reward mean: 3.3344 +num rollout transitions: 249340, reward mean: 3.3491 +num rollout transitions: 249348, reward mean: 3.3337 +num rollout transitions: 249339, reward mean: 3.3404 +num rollout transitions: 249282, reward mean: 3.3562 +num rollout transitions: 249321, reward mean: 3.3373 +num rollout transitions: 249243, reward mean: 3.3321 +num rollout transitions: 249326, reward mean: 3.3421 +num rollout transitions: 249373, reward mean: 3.3439 +num rollout transitions: 249323, reward mean: 3.3396 +num rollout transitions: 249329, reward mean: 3.3421 +num rollout transitions: 249353, reward mean: 3.3270 +num rollout transitions: 249320, reward mean: 3.3346 +num rollout transitions: 249370, reward mean: 3.3392 +num rollout transitions: 249375, reward mean: 3.3497 +num rollout transitions: 249338, reward mean: 3.3374 +num rollout transitions: 249260, reward mean: 3.3565 +num rollout transitions: 249156, reward mean: 3.3525 +num rollout transitions: 249317, reward mean: 3.3395 +num rollout transitions: 249431, reward mean: 3.3396 +num rollout transitions: 249365, reward mean: 3.3363 +num rollout transitions: 249378, reward mean: 3.3383 +num rollout transitions: 249333, reward mean: 3.3490 +num rollout transitions: 249358, reward mean: 3.3598 +num rollout transitions: 249372, reward mean: 3.3461 +num rollout transitions: 249264, reward mean: 3.3469 +num rollout transitions: 249303, reward mean: 3.3567 +num rollout transitions: 249395, reward mean: 3.3367 +num rollout transitions: 249338, reward mean: 3.3383 +num rollout transitions: 249348, reward mean: 3.3381 +num rollout transitions: 249321, reward mean: 3.3249 +num rollout transitions: 249385, reward mean: 3.3357 +num rollout transitions: 249292, reward mean: 3.3421 +num rollout transitions: 249324, reward mean: 3.3354 +num rollout transitions: 249326, reward mean: 3.3447 +---------------------------------------------------------------------------------- +| alpha | 0.0244 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.846 | +| loss/actor | -306 | +| loss/alpha | 0.0045 | +| loss/critic | 3.83 | +| penalty/lcb_mean | 0.224 | +| penalty/lcb_std | 0.494 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249347, reward mean: 3.3372 +num rollout transitions: 249376, reward mean: 3.3410 +num rollout transitions: 249245, reward mean: 3.3450 +num rollout transitions: 249399, reward mean: 3.3349 +num rollout transitions: 249427, reward mean: 3.3349 +num rollout transitions: 249378, reward mean: 3.3405 +num rollout transitions: 249381, reward mean: 3.3335 +num rollout transitions: 249366, reward mean: 3.3278 +num rollout transitions: 249384, reward mean: 3.3383 +num rollout transitions: 249305, reward mean: 3.3390 +num rollout transitions: 249325, reward mean: 3.3305 +num rollout transitions: 249370, reward mean: 3.3385 +num rollout transitions: 249295, reward mean: 3.3323 +num rollout transitions: 249359, reward mean: 3.3307 +num rollout transitions: 249290, reward mean: 3.3282 +num rollout transitions: 249440, reward mean: 3.3303 +num rollout transitions: 249375, reward mean: 3.3321 +num rollout transitions: 249357, reward mean: 3.3301 +num rollout transitions: 249282, reward mean: 3.3321 +num rollout transitions: 249347, reward mean: 3.3266 +num rollout transitions: 249391, reward mean: 3.3194 +num rollout transitions: 249342, reward mean: 3.3387 +num rollout transitions: 249327, reward mean: 3.3373 +num rollout transitions: 249315, reward mean: 3.3435 +num rollout transitions: 249312, reward mean: 3.3424 +num rollout transitions: 249362, reward mean: 3.3324 +num rollout transitions: 249381, reward mean: 3.3229 +num rollout transitions: 249341, reward mean: 3.3257 +num rollout transitions: 249288, reward mean: 3.3477 +num rollout transitions: 249385, reward mean: 3.3293 +num rollout transitions: 249334, reward mean: 3.3336 +num rollout transitions: 249324, reward mean: 3.3434 +num rollout transitions: 249371, reward mean: 3.3347 +num rollout transitions: 249191, reward mean: 3.3290 +num rollout transitions: 249334, reward mean: 3.3273 +num rollout transitions: 249356, reward mean: 3.3387 +num rollout transitions: 249355, reward mean: 3.3327 +num rollout transitions: 249312, reward mean: 3.3431 +num rollout transitions: 249405, reward mean: 3.3543 +num rollout transitions: 249277, reward mean: 3.3410 +num rollout transitions: 249386, reward mean: 3.3428 +num rollout transitions: 249343, reward mean: 3.3429 +num rollout transitions: 249396, reward mean: 3.3409 +num rollout transitions: 249344, reward mean: 3.3330 +num rollout transitions: 249296, reward mean: 3.3244 +num rollout transitions: 249297, reward mean: 3.3293 +num rollout transitions: 249330, reward mean: 3.3412 +num rollout transitions: 249331, reward mean: 3.3375 +num rollout transitions: 249304, reward mean: 3.3279 +num rollout transitions: 249339, reward mean: 3.3354 +---------------------------------------------------------------------------------- +| alpha | 0.0244 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.815 | +| loss/actor | -306 | +| loss/alpha | -0.0114 | +| loss/critic | 3.55 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.502 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249326, reward mean: 3.3419 +num rollout transitions: 249273, reward mean: 3.3372 +num rollout transitions: 249300, reward mean: 3.3331 +num rollout transitions: 249356, reward mean: 3.3361 +num rollout transitions: 249286, reward mean: 3.3325 +num rollout transitions: 249245, reward mean: 3.3194 +num rollout transitions: 249407, reward mean: 3.3312 +num rollout transitions: 249305, reward mean: 3.3412 +num rollout transitions: 249286, reward mean: 3.3299 +num rollout transitions: 249289, reward mean: 3.3357 +num rollout transitions: 249332, reward mean: 3.3414 +num rollout transitions: 249329, reward mean: 3.3220 +num rollout transitions: 249302, reward mean: 3.3264 +num rollout transitions: 249412, reward mean: 3.3365 +num rollout transitions: 249317, reward mean: 3.3285 +num rollout transitions: 249353, reward mean: 3.3390 +num rollout transitions: 249324, reward mean: 3.3478 +num rollout transitions: 249298, reward mean: 3.3325 +num rollout transitions: 249333, reward mean: 3.3371 +num rollout transitions: 249280, reward mean: 3.3493 +num rollout transitions: 249329, reward mean: 3.3355 +num rollout transitions: 249375, reward mean: 3.3318 +num rollout transitions: 249362, reward mean: 3.3256 +num rollout transitions: 249323, reward mean: 3.3405 +num rollout transitions: 249333, reward mean: 3.3402 +num rollout transitions: 249271, reward mean: 3.3390 +num rollout transitions: 249336, reward mean: 3.3336 +num rollout transitions: 249350, reward mean: 3.3337 +num rollout transitions: 249403, reward mean: 3.3298 +num rollout transitions: 249290, reward mean: 3.3325 +num rollout transitions: 249275, reward mean: 3.3450 +num rollout transitions: 249273, reward mean: 3.3492 +num rollout transitions: 249297, reward mean: 3.3307 +num rollout transitions: 249352, reward mean: 3.3369 +num rollout transitions: 249263, reward mean: 3.3352 +num rollout transitions: 249253, reward mean: 3.3386 +num rollout transitions: 249441, reward mean: 3.3315 +num rollout transitions: 249276, reward mean: 3.3430 +num rollout transitions: 249336, reward mean: 3.3413 +num rollout transitions: 249376, reward mean: 3.3426 +num rollout transitions: 249266, reward mean: 3.3345 +num rollout transitions: 249457, reward mean: 3.3345 +num rollout transitions: 249259, reward mean: 3.3279 +num rollout transitions: 249321, reward mean: 3.3379 +num rollout transitions: 249348, reward mean: 3.3303 +num rollout transitions: 249307, reward mean: 3.3437 +num rollout transitions: 249264, reward mean: 3.3326 +num rollout transitions: 249275, reward mean: 3.3373 +num rollout transitions: 249273, reward mean: 3.3227 +num rollout transitions: 249350, reward mean: 3.3283 +---------------------------------------------------------------------------------- +| alpha | 0.0236 | +| eval/episode_length | 196 | +| eval/episode_length_std | 203 | +| eval/normalized_episode_reward | 19.3 | +| eval/normalized_episode_reward_std | 24.2 | +| loss/actor | -306 | +| loss/alpha | -0.00967 | +| loss/critic | 3.38 | +| penalty/lcb_mean | 0.225 | +| penalty/lcb_std | 0.492 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249249, reward mean: 3.3195 +num rollout transitions: 249381, reward mean: 3.3327 +num rollout transitions: 249336, reward mean: 3.3376 +num rollout transitions: 249290, reward mean: 3.3433 +num rollout transitions: 249379, reward mean: 3.3333 +num rollout transitions: 249332, reward mean: 3.3379 +num rollout transitions: 249308, reward mean: 3.3333 +num rollout transitions: 249328, reward mean: 3.3417 +num rollout transitions: 249422, reward mean: 3.3451 +num rollout transitions: 249274, reward mean: 3.3356 +num rollout transitions: 249331, reward mean: 3.3288 +num rollout transitions: 249323, reward mean: 3.3242 +num rollout transitions: 249299, reward mean: 3.3368 +num rollout transitions: 249362, reward mean: 3.3360 +num rollout transitions: 249291, reward mean: 3.3280 +num rollout transitions: 249332, reward mean: 3.3389 +num rollout transitions: 249288, reward mean: 3.3336 +num rollout transitions: 249276, reward mean: 3.3462 +num rollout transitions: 249396, reward mean: 3.3469 +num rollout transitions: 249328, reward mean: 3.3425 +num rollout transitions: 249316, reward mean: 3.3268 +num rollout transitions: 249359, reward mean: 3.3356 +num rollout transitions: 249326, reward mean: 3.3344 +num rollout transitions: 249290, reward mean: 3.3405 +num rollout transitions: 249362, reward mean: 3.3361 +num rollout transitions: 249376, reward mean: 3.3274 +num rollout transitions: 249400, reward mean: 3.3317 +num rollout transitions: 249303, reward mean: 3.3392 +num rollout transitions: 249334, reward mean: 3.3297 +num rollout transitions: 249331, reward mean: 3.3368 +num rollout transitions: 249270, reward mean: 3.3408 +num rollout transitions: 249353, reward mean: 3.3184 +num rollout transitions: 249183, reward mean: 3.3492 +num rollout transitions: 249347, reward mean: 3.3399 +num rollout transitions: 249358, reward mean: 3.3355 +num rollout transitions: 249331, reward mean: 3.3497 +num rollout transitions: 249313, reward mean: 3.3368 +num rollout transitions: 249346, reward mean: 3.3306 +num rollout transitions: 249305, reward mean: 3.3454 +num rollout transitions: 249374, reward mean: 3.3418 +num rollout transitions: 249328, reward mean: 3.3371 +num rollout transitions: 249396, reward mean: 3.3394 +num rollout transitions: 249371, reward mean: 3.3379 +num rollout transitions: 249278, reward mean: 3.3413 +num rollout transitions: 249386, reward mean: 3.3487 +num rollout transitions: 249368, reward mean: 3.3374 +num rollout transitions: 249323, reward mean: 3.3324 +num rollout transitions: 249354, reward mean: 3.3329 +num rollout transitions: 249343, reward mean: 3.3320 +num rollout transitions: 249332, reward mean: 3.3331 +---------------------------------------------------------------------------------- +| alpha | 0.0233 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.868 | +| loss/actor | -307 | +| loss/alpha | 0.00685 | +| loss/critic | 3.66 | +| penalty/lcb_mean | 0.223 | +| penalty/lcb_std | 0.488 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249336, reward mean: 3.3353 +num rollout transitions: 249379, reward mean: 3.3289 +num rollout transitions: 249322, reward mean: 3.3294 +num rollout transitions: 249275, reward mean: 3.3328 +num rollout transitions: 249366, reward mean: 3.3390 +num rollout transitions: 249313, reward mean: 3.3301 +num rollout transitions: 249363, reward mean: 3.3329 +num rollout transitions: 249376, reward mean: 3.3250 +num rollout transitions: 249303, reward mean: 3.3362 +num rollout transitions: 249319, reward mean: 3.3376 +num rollout transitions: 249317, reward mean: 3.3339 +num rollout transitions: 249339, reward mean: 3.3314 +num rollout transitions: 249380, reward mean: 3.3263 +num rollout transitions: 249338, reward mean: 3.3320 +num rollout transitions: 249335, reward mean: 3.3354 +num rollout transitions: 249378, reward mean: 3.3278 +num rollout transitions: 249377, reward mean: 3.3366 +num rollout transitions: 249357, reward mean: 3.3156 +num rollout transitions: 249273, reward mean: 3.3358 +num rollout transitions: 249213, reward mean: 3.3248 +num rollout transitions: 249283, reward mean: 3.3271 +num rollout transitions: 249243, reward mean: 3.3397 +num rollout transitions: 249291, reward mean: 3.3357 +num rollout transitions: 249354, reward mean: 3.3335 +num rollout transitions: 249346, reward mean: 3.3358 +num rollout transitions: 249323, reward mean: 3.3384 +num rollout transitions: 249320, reward mean: 3.3351 +num rollout transitions: 249392, reward mean: 3.3261 +num rollout transitions: 249307, reward mean: 3.3301 +num rollout transitions: 249369, reward mean: 3.3273 +num rollout transitions: 249300, reward mean: 3.3440 +num rollout transitions: 249389, reward mean: 3.3369 +num rollout transitions: 249280, reward mean: 3.3357 +num rollout transitions: 249248, reward mean: 3.3389 +num rollout transitions: 249284, reward mean: 3.3347 +num rollout transitions: 249351, reward mean: 3.3419 +num rollout transitions: 249408, reward mean: 3.3344 +num rollout transitions: 249291, reward mean: 3.3343 +num rollout transitions: 249328, reward mean: 3.3243 +num rollout transitions: 249318, reward mean: 3.3316 +num rollout transitions: 249337, reward mean: 3.3440 +num rollout transitions: 249323, reward mean: 3.3425 +num rollout transitions: 249394, reward mean: 3.3324 +num rollout transitions: 249267, reward mean: 3.3378 +num rollout transitions: 249338, reward mean: 3.3370 +num rollout transitions: 249334, reward mean: 3.3418 +num rollout transitions: 249276, reward mean: 3.3410 +num rollout transitions: 249351, reward mean: 3.3316 +num rollout transitions: 249276, reward mean: 3.3280 +num rollout transitions: 249301, reward mean: 3.3384 +---------------------------------------------------------------------------------- +| alpha | 0.0227 | +| eval/episode_length | 166 | +| eval/episode_length_std | 142 | +| eval/normalized_episode_reward | 15.9 | +| eval/normalized_episode_reward_std | 17.1 | +| loss/actor | -306 | +| loss/alpha | -0.00492 | +| loss/critic | 3.22 | +| penalty/lcb_mean | 0.226 | +| penalty/lcb_std | 0.498 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249385, reward mean: 3.3345 +num rollout transitions: 249350, reward mean: 3.3298 +num rollout transitions: 249316, reward mean: 3.3280 +num rollout transitions: 249416, reward mean: 3.3290 +num rollout transitions: 249310, reward mean: 3.3405 +num rollout transitions: 249357, reward mean: 3.3396 +num rollout transitions: 249287, reward mean: 3.3325 +num rollout transitions: 249356, reward mean: 3.3263 +num rollout transitions: 249325, reward mean: 3.3433 +num rollout transitions: 249333, reward mean: 3.3323 +num rollout transitions: 249305, reward mean: 3.3281 +num rollout transitions: 249326, reward mean: 3.3292 +num rollout transitions: 249395, reward mean: 3.3311 +num rollout transitions: 249321, reward mean: 3.3346 +num rollout transitions: 249344, reward mean: 3.3376 +num rollout transitions: 249389, reward mean: 3.3400 +num rollout transitions: 249302, reward mean: 3.3330 +num rollout transitions: 249356, reward mean: 3.3302 +num rollout transitions: 249340, reward mean: 3.3284 +num rollout transitions: 249348, reward mean: 3.3272 +num rollout transitions: 249318, reward mean: 3.3389 +num rollout transitions: 249277, reward mean: 3.3504 +num rollout transitions: 249366, reward mean: 3.3560 +num rollout transitions: 249347, reward mean: 3.3454 +num rollout transitions: 249348, reward mean: 3.3357 +num rollout transitions: 249327, reward mean: 3.3413 +num rollout transitions: 249376, reward mean: 3.3426 +num rollout transitions: 249416, reward mean: 3.3369 +num rollout transitions: 249340, reward mean: 3.3390 +num rollout transitions: 249277, reward mean: 3.3410 +num rollout transitions: 249288, reward mean: 3.3435 +num rollout transitions: 249312, reward mean: 3.3413 +num rollout transitions: 249355, reward mean: 3.3501 +num rollout transitions: 249327, reward mean: 3.3441 +num rollout transitions: 249375, reward mean: 3.3285 +num rollout transitions: 249371, reward mean: 3.3312 +num rollout transitions: 249329, reward mean: 3.3336 +num rollout transitions: 249314, reward mean: 3.3362 +num rollout transitions: 249334, reward mean: 3.3314 +num rollout transitions: 249301, reward mean: 3.3412 +num rollout transitions: 249312, reward mean: 3.3456 +num rollout transitions: 249359, reward mean: 3.3372 +num rollout transitions: 249421, reward mean: 3.3418 +num rollout transitions: 249298, reward mean: 3.3286 +num rollout transitions: 249299, reward mean: 3.3417 +num rollout transitions: 249351, reward mean: 3.3430 +num rollout transitions: 249379, reward mean: 3.3432 +num rollout transitions: 249365, reward mean: 3.3446 +num rollout transitions: 249358, reward mean: 3.3438 +num rollout transitions: 249302, reward mean: 3.3545 +---------------------------------------------------------------------------------- +| alpha | 0.0238 | +| eval/episode_length | 817 | +| eval/episode_length_std | 324 | +| eval/normalized_episode_reward | 90.7 | +| eval/normalized_episode_reward_std | 38.6 | +| loss/actor | -306 | +| loss/alpha | 0.00951 | +| loss/critic | 3.79 | +| penalty/lcb_mean | 0.234 | +| penalty/lcb_std | 0.521 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249286, reward mean: 3.3356 +num rollout transitions: 249305, reward mean: 3.3478 +num rollout transitions: 249352, reward mean: 3.3460 +num rollout transitions: 249332, reward mean: 3.3406 +num rollout transitions: 249310, reward mean: 3.3376 +num rollout transitions: 249336, reward mean: 3.3409 +num rollout transitions: 249329, reward mean: 3.3422 +num rollout transitions: 249291, reward mean: 3.3416 +num rollout transitions: 249325, reward mean: 3.3283 +num rollout transitions: 249340, reward mean: 3.3375 +num rollout transitions: 249305, reward mean: 3.3419 +num rollout transitions: 249328, reward mean: 3.3412 +num rollout transitions: 249373, reward mean: 3.3343 +num rollout transitions: 249356, reward mean: 3.3352 +num rollout transitions: 249290, reward mean: 3.3428 +num rollout transitions: 249322, reward mean: 3.3341 +num rollout transitions: 249316, reward mean: 3.3494 +num rollout transitions: 249341, reward mean: 3.3470 +num rollout transitions: 249359, reward mean: 3.3420 +num rollout transitions: 249310, reward mean: 3.3404 +num rollout transitions: 249405, reward mean: 3.3395 +num rollout transitions: 249353, reward mean: 3.3279 +num rollout transitions: 249347, reward mean: 3.3370 +num rollout transitions: 249300, reward mean: 3.3363 +num rollout transitions: 249308, reward mean: 3.3317 +num rollout transitions: 249304, reward mean: 3.3394 +num rollout transitions: 249342, reward mean: 3.3439 +num rollout transitions: 249354, reward mean: 3.3419 +num rollout transitions: 249234, reward mean: 3.3484 +num rollout transitions: 249358, reward mean: 3.3494 +num rollout transitions: 249399, reward mean: 3.3425 +num rollout transitions: 249250, reward mean: 3.3372 +num rollout transitions: 249215, reward mean: 3.3347 +num rollout transitions: 249312, reward mean: 3.3400 +num rollout transitions: 249255, reward mean: 3.3342 +num rollout transitions: 249333, reward mean: 3.3374 +num rollout transitions: 249396, reward mean: 3.3373 +num rollout transitions: 249326, reward mean: 3.3401 +num rollout transitions: 249349, reward mean: 3.3437 +num rollout transitions: 249297, reward mean: 3.3388 +num rollout transitions: 249367, reward mean: 3.3415 +num rollout transitions: 249292, reward mean: 3.3394 +num rollout transitions: 249331, reward mean: 3.3306 +num rollout transitions: 249350, reward mean: 3.3400 +num rollout transitions: 249380, reward mean: 3.3340 +num rollout transitions: 249220, reward mean: 3.3427 +num rollout transitions: 249343, reward mean: 3.3529 +num rollout transitions: 249320, reward mean: 3.3464 +num rollout transitions: 249353, reward mean: 3.3447 +num rollout transitions: 249359, reward mean: 3.3419 +---------------------------------------------------------------------------------- +| alpha | 0.0229 | +| eval/episode_length | 717 | +| eval/episode_length_std | 403 | +| eval/normalized_episode_reward | 79.9 | +| eval/normalized_episode_reward_std | 47.4 | +| loss/actor | -306 | +| loss/alpha | -0.00844 | +| loss/critic | 3.69 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.497 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249296, reward mean: 3.3417 +num rollout transitions: 249364, reward mean: 3.3427 +num rollout transitions: 249222, reward mean: 3.3456 +num rollout transitions: 249290, reward mean: 3.3445 +num rollout transitions: 249201, reward mean: 3.3377 +num rollout transitions: 249315, reward mean: 3.3412 +num rollout transitions: 249348, reward mean: 3.3439 +num rollout transitions: 249272, reward mean: 3.3366 +num rollout transitions: 249325, reward mean: 3.3312 +num rollout transitions: 249340, reward mean: 3.3331 +num rollout transitions: 249351, reward mean: 3.3264 +num rollout transitions: 249342, reward mean: 3.3386 +num rollout transitions: 249300, reward mean: 3.3387 +num rollout transitions: 249344, reward mean: 3.3425 +num rollout transitions: 249371, reward mean: 3.3384 +num rollout transitions: 249309, reward mean: 3.3412 +num rollout transitions: 249316, reward mean: 3.3423 +num rollout transitions: 249369, reward mean: 3.3443 +num rollout transitions: 249327, reward mean: 3.3442 +num rollout transitions: 249243, reward mean: 3.3526 +num rollout transitions: 249365, reward mean: 3.3485 +num rollout transitions: 249311, reward mean: 3.3433 +num rollout transitions: 249306, reward mean: 3.3410 +num rollout transitions: 249267, reward mean: 3.3407 +num rollout transitions: 249351, reward mean: 3.3437 +num rollout transitions: 249303, reward mean: 3.3427 +num rollout transitions: 249342, reward mean: 3.3467 +num rollout transitions: 249270, reward mean: 3.3413 +num rollout transitions: 249348, reward mean: 3.3285 +num rollout transitions: 249237, reward mean: 3.3432 +num rollout transitions: 249228, reward mean: 3.3504 +num rollout transitions: 249337, reward mean: 3.3403 +num rollout transitions: 249388, reward mean: 3.3430 +num rollout transitions: 249273, reward mean: 3.3407 +num rollout transitions: 249318, reward mean: 3.3428 +num rollout transitions: 249320, reward mean: 3.3408 +num rollout transitions: 249185, reward mean: 3.3475 +num rollout transitions: 249350, reward mean: 3.3412 +num rollout transitions: 249358, reward mean: 3.3416 +num rollout transitions: 249300, reward mean: 3.3533 +num rollout transitions: 249332, reward mean: 3.3451 +num rollout transitions: 249336, reward mean: 3.3455 +num rollout transitions: 249291, reward mean: 3.3531 +num rollout transitions: 249351, reward mean: 3.3369 +num rollout transitions: 249364, reward mean: 3.3364 +num rollout transitions: 249292, reward mean: 3.3410 +num rollout transitions: 249340, reward mean: 3.3498 +num rollout transitions: 249315, reward mean: 3.3488 +num rollout transitions: 249286, reward mean: 3.3382 +num rollout transitions: 249286, reward mean: 3.3431 +---------------------------------------------------------------------------------- +| alpha | 0.0233 | +| eval/episode_length | 949 | +| eval/episode_length_std | 203 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 24.1 | +| loss/actor | -305 | +| loss/alpha | 0.00423 | +| loss/critic | 4.46 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.501 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249317, reward mean: 3.3459 +num rollout transitions: 249319, reward mean: 3.3409 +num rollout transitions: 249292, reward mean: 3.3417 +num rollout transitions: 249333, reward mean: 3.3392 +num rollout transitions: 249302, reward mean: 3.3357 +num rollout transitions: 249376, reward mean: 3.3434 +num rollout transitions: 249319, reward mean: 3.3448 +num rollout transitions: 249345, reward mean: 3.3410 +num rollout transitions: 249335, reward mean: 3.3306 +num rollout transitions: 249303, reward mean: 3.3302 +num rollout transitions: 249307, reward mean: 3.3321 +num rollout transitions: 249260, reward mean: 3.3340 +num rollout transitions: 249317, reward mean: 3.3373 +num rollout transitions: 249370, reward mean: 3.3333 +num rollout transitions: 249304, reward mean: 3.3433 +num rollout transitions: 249261, reward mean: 3.3385 +num rollout transitions: 249303, reward mean: 3.3435 +num rollout transitions: 249349, reward mean: 3.3370 +num rollout transitions: 249389, reward mean: 3.3365 +num rollout transitions: 249288, reward mean: 3.3352 +num rollout transitions: 249311, reward mean: 3.3391 +num rollout transitions: 249300, reward mean: 3.3394 +num rollout transitions: 249334, reward mean: 3.3255 +num rollout transitions: 249359, reward mean: 3.3337 +num rollout transitions: 249301, reward mean: 3.3314 +num rollout transitions: 249252, reward mean: 3.3308 +num rollout transitions: 249391, reward mean: 3.3283 +num rollout transitions: 249384, reward mean: 3.3335 +num rollout transitions: 249327, reward mean: 3.3380 +num rollout transitions: 249315, reward mean: 3.3418 +num rollout transitions: 249303, reward mean: 3.3423 +num rollout transitions: 249296, reward mean: 3.3456 +num rollout transitions: 249341, reward mean: 3.3442 +num rollout transitions: 249242, reward mean: 3.3410 +num rollout transitions: 249313, reward mean: 3.3336 +num rollout transitions: 249320, reward mean: 3.3323 +num rollout transitions: 249350, reward mean: 3.3308 +num rollout transitions: 249240, reward mean: 3.3353 +num rollout transitions: 249279, reward mean: 3.3361 +num rollout transitions: 249255, reward mean: 3.3263 +num rollout transitions: 249319, reward mean: 3.3309 +num rollout transitions: 249334, reward mean: 3.3447 +num rollout transitions: 249318, reward mean: 3.3404 +num rollout transitions: 249299, reward mean: 3.3435 +num rollout transitions: 249280, reward mean: 3.3432 +num rollout transitions: 249388, reward mean: 3.3416 +num rollout transitions: 249356, reward mean: 3.3366 +num rollout transitions: 249389, reward mean: 3.3327 +num rollout transitions: 249261, reward mean: 3.3432 +num rollout transitions: 249294, reward mean: 3.3348 +---------------------------------------------------------------------------------- +| alpha | 0.0227 | +| eval/episode_length | 689 | +| eval/episode_length_std | 373 | +| eval/normalized_episode_reward | 75.9 | +| eval/normalized_episode_reward_std | 44.4 | +| loss/actor | -304 | +| loss/alpha | 0.00783 | +| loss/critic | 4.76 | +| penalty/lcb_mean | 0.221 | +| penalty/lcb_std | 0.488 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249283, reward mean: 3.3410 +num rollout transitions: 249207, reward mean: 3.3350 +num rollout transitions: 249311, reward mean: 3.3412 +num rollout transitions: 249312, reward mean: 3.3389 +num rollout transitions: 249276, reward mean: 3.3418 +num rollout transitions: 249349, reward mean: 3.3428 +num rollout transitions: 249302, reward mean: 3.3345 +num rollout transitions: 249288, reward mean: 3.3389 +num rollout transitions: 249237, reward mean: 3.3411 +num rollout transitions: 249366, reward mean: 3.3465 +num rollout transitions: 249366, reward mean: 3.3350 +num rollout transitions: 249352, reward mean: 3.3356 +num rollout transitions: 249299, reward mean: 3.3413 +num rollout transitions: 249337, reward mean: 3.3405 +num rollout transitions: 249327, reward mean: 3.3434 +num rollout transitions: 249356, reward mean: 3.3320 +num rollout transitions: 249309, reward mean: 3.3332 +num rollout transitions: 249370, reward mean: 3.3301 +num rollout transitions: 249324, reward mean: 3.3325 +num rollout transitions: 249280, reward mean: 3.3350 +num rollout transitions: 249323, reward mean: 3.3395 +num rollout transitions: 249314, reward mean: 3.3363 +num rollout transitions: 249241, reward mean: 3.3364 +num rollout transitions: 249335, reward mean: 3.3407 +num rollout transitions: 249323, reward mean: 3.3345 +num rollout transitions: 249288, reward mean: 3.3315 +num rollout transitions: 249302, reward mean: 3.3275 +num rollout transitions: 249291, reward mean: 3.3272 +num rollout transitions: 249306, reward mean: 3.3351 +num rollout transitions: 249331, reward mean: 3.3288 +num rollout transitions: 249341, reward mean: 3.3330 +num rollout transitions: 249384, reward mean: 3.3368 +num rollout transitions: 249342, reward mean: 3.3315 +num rollout transitions: 249330, reward mean: 3.3314 +num rollout transitions: 249309, reward mean: 3.3397 +num rollout transitions: 249330, reward mean: 3.3356 +num rollout transitions: 249283, reward mean: 3.3358 +num rollout transitions: 249376, reward mean: 3.3318 +num rollout transitions: 249317, reward mean: 3.3229 +num rollout transitions: 249385, reward mean: 3.3303 +num rollout transitions: 249344, reward mean: 3.3336 +num rollout transitions: 249288, reward mean: 3.3309 +num rollout transitions: 249330, reward mean: 3.3368 +num rollout transitions: 249291, reward mean: 3.3302 +num rollout transitions: 249297, reward mean: 3.3305 +num rollout transitions: 249293, reward mean: 3.3322 +num rollout transitions: 249339, reward mean: 3.3349 +num rollout transitions: 249348, reward mean: 3.3284 +num rollout transitions: 249315, reward mean: 3.3265 +num rollout transitions: 249267, reward mean: 3.3364 +---------------------------------------------------------------------------------- +| alpha | 0.0243 | +| eval/episode_length | 666 | +| eval/episode_length_std | 418 | +| eval/normalized_episode_reward | 73.6 | +| eval/normalized_episode_reward_std | 49.1 | +| loss/actor | -302 | +| loss/alpha | -0.0128 | +| loss/critic | 4.24 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.497 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249339, reward mean: 3.3396 +num rollout transitions: 249435, reward mean: 3.3306 +num rollout transitions: 249422, reward mean: 3.3364 +num rollout transitions: 249367, reward mean: 3.3373 +num rollout transitions: 249323, reward mean: 3.3386 +num rollout transitions: 249296, reward mean: 3.3324 +num rollout transitions: 249281, reward mean: 3.3291 +num rollout transitions: 249341, reward mean: 3.3323 +num rollout transitions: 249342, reward mean: 3.3303 +num rollout transitions: 249294, reward mean: 3.3378 +num rollout transitions: 249337, reward mean: 3.3349 +num rollout transitions: 249287, reward mean: 3.3325 +num rollout transitions: 249326, reward mean: 3.3321 +num rollout transitions: 249311, reward mean: 3.3359 +num rollout transitions: 249410, reward mean: 3.3305 +num rollout transitions: 249289, reward mean: 3.3287 +num rollout transitions: 249285, reward mean: 3.3286 +num rollout transitions: 249435, reward mean: 3.3333 +num rollout transitions: 249292, reward mean: 3.3307 +num rollout transitions: 249356, reward mean: 3.3305 +num rollout transitions: 249290, reward mean: 3.3340 +num rollout transitions: 249351, reward mean: 3.3350 +num rollout transitions: 249353, reward mean: 3.3326 +num rollout transitions: 249344, reward mean: 3.3283 +num rollout transitions: 249322, reward mean: 3.3312 +num rollout transitions: 249280, reward mean: 3.3310 +num rollout transitions: 249388, reward mean: 3.3340 +num rollout transitions: 249321, reward mean: 3.3332 +num rollout transitions: 249313, reward mean: 3.3274 +num rollout transitions: 249369, reward mean: 3.3352 +num rollout transitions: 249368, reward mean: 3.3260 +num rollout transitions: 249390, reward mean: 3.3308 +num rollout transitions: 249275, reward mean: 3.3317 +num rollout transitions: 249313, reward mean: 3.3333 +num rollout transitions: 249403, reward mean: 3.3230 +num rollout transitions: 249217, reward mean: 3.3289 +num rollout transitions: 249338, reward mean: 3.3273 +num rollout transitions: 249286, reward mean: 3.3289 +num rollout transitions: 249424, reward mean: 3.3356 +num rollout transitions: 249331, reward mean: 3.3291 +num rollout transitions: 249386, reward mean: 3.3333 +num rollout transitions: 249347, reward mean: 3.3347 +num rollout transitions: 249340, reward mean: 3.3302 +num rollout transitions: 249355, reward mean: 3.3326 +num rollout transitions: 249370, reward mean: 3.3304 +num rollout transitions: 249275, reward mean: 3.3324 +num rollout transitions: 249324, reward mean: 3.3230 +num rollout transitions: 249365, reward mean: 3.3271 +num rollout transitions: 249358, reward mean: 3.3272 +num rollout transitions: 249323, reward mean: 3.3303 +---------------------------------------------------------------------------------- +| alpha | 0.0205 | +| eval/episode_length | 554 | +| eval/episode_length_std | 429 | +| eval/normalized_episode_reward | 60.6 | +| eval/normalized_episode_reward_std | 50.2 | +| loss/actor | -302 | +| loss/alpha | -0.0273 | +| loss/critic | 3.64 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.528 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 55542.38s diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/dynamics_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/dynamics_training_progress.csv similarity index 100% rename from hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/dynamics_training_progress.csv rename to hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/dynamics_training_progress.csv diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/hyper_param.json b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/hyper_param.json similarity index 100% rename from hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-201136/record/hyper_param.json rename to hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/hyper_param.json diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..2f46744872b667fab5f4fedaf6a64888e68de5b4 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.26732974984004626,30.06,0.5444263035526479,2.140052474510096,0.6560949850621316,-370.089423153426,-0.7917793668714195,17.517475339453025,0.4871337239702485,0.668234947758936,0.0,0.0,249279.16,3.4964371042873883,50000 +0.09252154977947336,57.45,1.0523782589924593,3.9337135402981427,0.6881822263420713,-453.5076889599536,-0.04088311218623111,16.471809260525728,0.3805780015769641,0.6752847406855235,0.0,0.0,249316.88000000003,3.4654303996367783,100000 +0.0840219659072153,41.87,1.1802965729002182,2.800967753002671,0.6877297783646523,-370.117087659308,-0.01153736653909079,12.573367606673253,0.339726484960611,0.5321563907796065,0.0,0.0,249299.72,3.426050483327976,150000 +0.06923029483877068,32.04,0.5817215828899596,2.237947671761037,0.6536649362357942,-332.86268904906785,-0.026239608116112586,8.708770483414986,0.2938271607321442,0.4805107904824644,0.0,0.0,249309.16000000003,3.386296143005899,200000 +0.05122561139881601,34.69,1.6714963356226658,2.414116278047138,0.7098399895886885,-316.67917571777036,-0.034827738731577816,6.231089872134947,0.24291493054598237,0.42587357187151803,0.0,0.0,249307.36000000002,3.389670133094079,250000 +0.042945739038512475,45.81,2.2833965927976685,3.0397966373437812,0.7697929194085401,-308.707568919682,-0.011153464798964539,6.829154941749539,0.23174103563368448,0.41275852191240053,0.0,0.0,249324.84000000008,3.3806673415429516,300000 +0.03779721629530202,81.84,101.1796145475955,6.618967998083973,11.392534936274577,-303.8674298229932,-0.012475889454781917,5.529533324333399,0.2236309627470373,0.41198646679103385,0.0,0.0,249312.6,3.3584767034991625,350000 +0.036187822311595765,1000.0,0.0,107.61027741132689,0.8393300586947221,-301.56703381896546,-0.008264567530751075,7.207286485447865,0.2279969123670446,0.42928969596385924,0.0,0.0,249322.59999999998,3.345084096543532,400000 +0.03374382302161335,421.25,256.3546518009767,44.0305741935421,28.931275364475837,-302.68187845947176,-0.00110746238946913,6.991246939637688,0.22021207149595043,0.4263731415858865,0.0,0.0,249305.3,3.3456544498680243,450000 +0.0332975944820786,31.01,0.1729161646579058,1.9006357330931947,0.632541533909548,-301.7323260882538,0.020804267049953407,6.4382347352576845,0.21547066410660484,0.4152935708867034,0.0,0.0,249316.02,3.3393384653834692,500000 +0.03393135152012114,32.95,0.21794494717703367,1.9785026822004719,0.6346721475354691,-301.2401665094034,-0.009785460012368753,5.320681021662989,0.2152076339587561,0.4183892461997278,0.0,0.0,249319.28,3.3261027665949525,550000 +0.03359012787058929,40.97,0.5376802023508026,2.473823840845683,0.6569605585801249,-301.54534704711506,0.00827557790942496,5.739736776130142,0.21687657369762495,0.43130859468371113,0.0,0.0,249307.97999999984,3.3265095904739153,600000 +0.03485778191864549,112.81,0.9131812525451891,8.776682256674267,0.699923286319655,-300.1231897955287,-0.008293155051544583,4.735928933290212,0.22960950076162684,0.4488271296679935,0.0,0.0,249329.42000000007,3.332797843321688,650000 +0.03262733478113967,47.11,0.8819863944528851,3.0524327669114135,0.6784298329055128,-301.1021493658504,-0.0011523945567010938,4.2480479577397166,0.22548904596686495,0.4465903742244842,0.0,0.0,249315.63999999998,3.3487816869285956,700000 +0.030410887409783708,40.76,0.7761443164772901,2.670198283143095,0.6654726514917211,-301.5992524389645,-0.006966160600185393,4.48752230609891,0.22185109329879235,0.45863046585619727,0.0,0.0,249336.44,3.350024489123679,750000 +0.030685026368722106,655.04,255.10844439179192,71.53141756099394,30.167452816781832,-301.5106000994909,-0.010959972648620784,4.763025067210246,0.2271546803236013,0.46660254782855337,0.0,0.0,249323.24000000005,3.351120542358849,800000 +0.02961879941239986,590.97,250.03293603043582,63.9523942615567,29.32199424349565,-302.126238940427,0.010839901707172302,4.744532208623843,0.22701051416486454,0.473905240423678,0.0,0.0,249319.31999999995,3.348780063760013,850000 +0.030746209039650994,1000.0,0.0,112.29094644046205,0.8367167678277369,-300.6452710571307,0.015387719880640627,4.940783504967655,0.23575015862882037,0.4937199326631394,0.0,0.0,249319.41999999995,3.339799808962315,900000 +0.03129328365296174,202.41,1.4289506639488994,19.885993550835508,0.766848335451328,-299.40530581542896,0.01265077325511719,4.878048870885416,0.2425348698973662,0.5103112272810966,0.0,0.0,249330.92,3.3420608019799394,950000 +0.031580295118168365,985.23,68.60697559286518,111.01403567738224,8.53505214761533,-299.4253077227781,-0.02189181425243624,5.387005458747091,0.24483861103445392,0.5152395488408179,0.0,0.0,249316.63999999996,3.346238349552208,1000000 +0.03035935524456197,1000.0,0.0,112.76685368275339,0.7851396607310379,-300.81712554748736,0.007480561581403063,4.9429570323336165,0.2387380254140488,0.5063043806302578,0.0,0.0,249314.28000000003,3.3409434399554843,1050000 +0.02958319393213815,1000.0,0.0,112.91076593545601,0.9303605891844813,-301.3317328613281,-0.006061274321600785,5.977843103636592,0.23623160156160655,0.5030089393421966,0.0,0.0,249314.90000000002,3.3413848931917944,1100000 +0.028149804722703994,583.04,150.77015089201177,64.50282509483725,17.658937886266727,-302.46239248229995,0.01867319542504841,4.359271901969963,0.23773899651765934,0.5144887339460891,0.0,0.0,249313.07999999993,3.3421271249842857,1150000 +0.02912372887518245,737.56,349.8991660464483,81.99214668804296,41.40077417508178,-302.1958448712227,-0.017221456856652804,4.8694488833736616,0.23862475971638836,0.5139581001314493,0.0,0.0,249319.84,3.3436114657279754,1200000 +0.028814591782502653,1000.0,0.0,113.07152559035329,0.9268708637264056,-302.60438469360696,0.005604266371987717,5.185843658584395,0.23556684903979366,0.5162912270048209,0.0,0.0,249321.1,3.3478860807457242,1250000 +0.02891536254122861,1000.0,0.0,112.01273322753855,0.950766877585463,-302.2248410266049,-0.00021622089721271608,5.381962798203166,0.23903997422397089,0.5157749523982347,0.0,0.0,249322.22,3.3471078245305517,1300000 +0.028834305929355264,1000.0,0.0,111.94491603969306,1.1360666613948338,-301.9402687994377,-0.002643838308602506,5.631223604016296,0.239933134623767,0.5197882144883353,0.0,0.0,249317.97999999992,3.342935874169858,1350000 +0.028921169198379188,1000.0,0.0,112.26795067749774,0.757707657664712,-301.6667029998771,0.011083932513967108,4.773773040771469,0.24117072794080024,0.5213719911718424,0.0,0.0,249330.56000000006,3.3395512255772766,1400000 +0.02832472011767331,1000.0,0.0,113.28250442675612,0.7707590944391566,-301.5846264129629,-0.00011950027000145645,4.94391498956091,0.2437708146539337,0.5268597296568737,0.0,0.0,249327.53999999995,3.3437945963110134,1450000 +0.028437294192798914,1000.0,0.0,112.26615746701482,0.8253995968793785,-301.91062504516395,0.0024821551454815485,5.380850046529767,0.241866964935659,0.5335193107774835,0.0,0.0,249322.87999999998,3.3374523163330685,1500000 +0.028284671823419445,1000.0,0.0,113.18337668467144,0.7329997310689867,-301.6212673278846,-0.0012152377901974093,5.4312807541097445,0.24054716501385115,0.5348317357531268,0.0,0.0,249313.26000000004,3.3376266480640084,1550000 +0.027446780861355283,1000.0,0.0,112.85997709048752,0.7769570482163193,-302.4554569879143,-0.002711607467308561,4.387622457917814,0.23617083794981314,0.5204641578233206,0.0,0.0,249326.80000000008,3.3353522173271983,1600000 +0.02782681334417287,1000.0,0.0,113.08796955745983,0.8444364630566907,-302.92299718505734,0.0038503469592333457,5.406385619550973,0.23781557264149275,0.5315402988565083,0.0,0.0,249321.84000000005,3.3380041918859966,1650000 +0.027104375048316767,1000.0,0.0,113.63306988116399,0.8214792486981568,-303.35755044738227,5.788269121193318e-05,4.1129031858229865,0.2340673303774014,0.5172540742597109,0.0,0.0,249317.62000000005,3.3369273373759127,1700000 +0.02762168133225276,1000.0,0.0,113.45092188156151,0.8284671038613128,-303.7575236218219,-0.010828306586369844,4.338849257250981,0.23696387992054024,0.5244777655452555,0.0,0.0,249325.08000000005,3.338669632013153,1750000 +0.026477476768195497,1000.0,0.0,113.29038443096597,0.9033408382385631,-303.8421527642834,0.020743473598063018,4.567301930462272,0.23390486763566548,0.5077897452345455,0.0,0.0,249312.18000000005,3.338945133236771,1800000 +0.02731396237496274,1000.0,0.0,113.38610035737844,0.8644468276798585,-304.3978974182119,-0.005041176837943637,4.0037878913271365,0.2323993679332726,0.5042779969784613,0.0,0.0,249328.46,3.338251565607245,1850000 +0.02624602704875192,1000.0,0.0,113.7077293583986,0.8264067485607071,-304.88936710998155,-0.015134674946889547,3.565788655948604,0.22868687568485813,0.4957882696318579,0.0,0.0,249319.64000000007,3.3374186887566544,1900000 +0.026058907220065326,1000.0,0.0,113.01707642524823,0.7305692241603667,-305.47008412597853,0.006772343558519816,4.0082167597377,0.22717521487444547,0.4969038528144337,0.0,0.0,249330.8000000001,3.3393767754029633,1950000 +0.02534648166362204,1000.0,0.0,113.15325858951594,0.8320565403205304,-305.91578051269875,0.003425396265238463,3.304806644061808,0.22539982546001514,0.48814112535893783,0.0,0.0,249320.8400000001,3.338913427885407,2000000 +0.026627253529727463,247.74,40.22253597176588,25.03053152787652,5.3346565800794155,-305.9989228051743,-0.0031562521529571188,3.8943854587614517,0.22633563161700887,0.4926229482701374,0.0,0.0,249333.16000000003,3.3431102418375094,2050000 +0.02581113961558789,982.98,119.13999999999996,111.08856189336743,14.532839810910348,-306.59456493407987,0.005769569422379116,3.157196790937205,0.2241137417054173,0.48752728524833916,0.0,0.0,249332.02000000005,3.337401899187409,2100000 +0.026301610282510497,1000.0,0.0,112.73480729264607,0.7965050909434338,-306.6398633331311,-0.0005189189408345434,3.586317349992972,0.22596194625705576,0.4995115682727137,0.0,0.0,249328.56000000003,3.3391128007336053,2150000 +0.026536400954201823,1000.0,0.0,112.77283196893006,0.8185577699436191,-306.3382440338035,0.0036067941389977052,3.5663000097620614,0.22301980031847687,0.4809428519570803,0.0,0.0,249319.91999999998,3.343947450144923,2200000 +0.026667742580063453,1000.0,0.0,111.47631591406639,0.770856078311461,-306.34014335449416,0.0029674536217747724,3.8097245853495476,0.22207413588851924,0.48251101629287035,0.0,0.0,249323.58000000016,3.343527346437682,2250000 +0.02638994956724374,597.77,427.1341207396103,66.08307015994495,50.36738715508886,-306.92174009765927,-0.01173761634886262,3.783577249121667,0.21925370459675694,0.47281829789608437,0.0,0.0,249317.50000000006,3.341843309411109,2300000 +0.025828376323990303,1000.0,0.0,113.38796583404715,0.8247503008570781,-307.20556253845103,0.007024032251760339,3.3496512717819327,0.22205912218958215,0.48363490089714584,0.0,0.0,249322.1,3.33820856833978,2350000 +0.025581756842732208,403.47,390.52140671159117,43.43986541342022,46.22274103688326,-306.9959354730194,-0.008458604686558027,3.384346718027567,0.22418668426305113,0.4868240387532079,0.0,0.0,249327.34000000003,3.33835597347062,2400000 +0.02497238341834409,890.83,282.6803160816119,100.61382016937803,33.72054956448774,-306.09376095947573,-0.008096164627969374,3.552815935918113,0.22817866749554871,0.49911148002057926,0.0,0.0,249333.41999999998,3.3415103243652773,2450000 +0.02440723605617897,1000.0,0.0,113.402627049884,0.8460061142174992,-306.34688573119956,0.004502590671181692,3.827621265223054,0.2241778207796813,0.4940923057457846,0.0,0.0,249326.7199999999,3.3406308743945865,2500000 +0.024441122979149087,1000.0,0.0,113.2238190097942,0.8154561083193552,-306.1949959045448,-0.011368373579718195,3.548596081728948,0.2290397940954587,0.5018309535378298,0.0,0.0,249342.34,3.335118331225736,2550000 +0.023553466827310642,195.5,203.25611921907787,19.278317108236713,24.237230564048833,-306.30046384094175,-0.009667639903202744,3.379749469915597,0.22518460100591223,0.4918241100212948,0.0,0.0,249319.74000000005,3.3352887080102582,2600000 +0.023349274378642117,1000.0,0.0,112.96837816642748,0.8678781532386453,-307.1257026782272,0.006848068565949565,3.6640384619700916,0.2232303721588849,0.4884745028343804,0.0,0.0,249331.6200000001,3.3364065310749944,2650000 +0.022711112919636133,166.16,142.09086670155827,15.925687702023453,17.10969138498227,-305.82648655822817,-0.004921216893382157,3.217058442623595,0.2264224487465622,0.4979179700818694,0.0,0.0,249325.62,3.3337367702811593,2700000 +0.023819339896924658,816.74,324.0886489835767,90.67543272515259,38.59174438757709,-305.5470433313001,0.009506803593784937,3.7936304275018355,0.23392506796300247,0.5214733181613689,0.0,0.0,249340.0600000001,3.3377475362664084,2750000 +0.022888526472300195,717.26,402.8729730324436,79.87175786627587,47.40071632442999,-305.5978383715736,-0.008440033617243058,3.6931478300142087,0.22743494312465207,0.49661374931514385,0.0,0.0,249325.16,3.340033356993312,2800000 +0.023345987764969264,948.69,203.09090058395032,106.10266255169911,24.07990439145721,-304.7981939508,0.004231483928337645,4.46266818700785,0.22865921030044467,0.5008965322181571,0.0,0.0,249311.89999999994,3.342128376699873,2850000 +0.022652019095457946,689.27,372.7499659289052,75.89837283921528,44.40630352734093,-303.95563136962295,0.007829063334167077,4.76326773518682,0.22057661773174966,0.48810201963574035,0.0,0.0,249316.80000000005,3.337292553905347,2900000 +0.02429865345135352,665.54,418.29029202217924,73.592430503624,49.056168364486254,-302.1620616546635,-0.012762575187906649,4.240742389819601,0.22882819701313908,0.49724456424265795,0.0,0.0,249316.28,3.3349380264839383,2950000 +0.020509210747368768,553.89,428.6092601659465,60.64652137462437,50.23789594409912,-302.0279590887443,-0.02725951470166427,3.6363177519107173,0.23587216149389734,0.5283744627255222,0.0,0.0,249337.74,3.3315952548756385,3000000 diff --git a/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/tb/events.out.tfevents.1778012824.aysin.1179583.0 b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/tb/events.out.tfevents.1778012824.aysin.1179583.0 new file mode 100644 index 0000000000000000000000000000000000000000..5d00b4ba294fa0c8c32206129c7c1180afa0d11b --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202702/record/tb/events.out.tfevents.1778012824.aysin.1179583.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05273e131ab7a5d48f2067689d5674f974175404f78e521b6217a7819f4fa1b +size 53236 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae2e6c7c4563809082c4668b4d2a10cf2ff43287 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535a79d8de462c4b7831fe8580d31b80b258230a6538ddba198eea04a1790fa8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9efa283fb2c8850db293f54e92c4c7515e8f87a --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0127_224616_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0bb312d48e9585b4f337f400705eba2dd35ecd7364fd923680d07cc0956b596 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 3c62c2afaa75111551b882ad4f4ffb75eae495eb..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:45a2541b9ff69c325cacbd754ec4807a98cc2f1e42b1fac17e275cc72383b0fa -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index 3691a8fe9ad98c6c443228bdc73a747bbcb0ff89..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_123_0330_093725_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:424a8d5570f05249020a86929d772323206d7c9264f40b26d58102eb65108dab -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae2e6c7c4563809082c4668b4d2a10cf2ff43287 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535a79d8de462c4b7831fe8580d31b80b258230a6538ddba198eea04a1790fa8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbafcd4e741e44d647225812803bb6144c053c99 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0127_170448_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b3a19dbdd36877de77b69bffd6def9293251f541b31ef692101a0bb460189b +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0329_221335_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_42_0329_221335_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae2e6c7c4563809082c4668b4d2a10cf2ff43287 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:535a79d8de462c4b7831fe8580d31b80b258230a6538ddba198eea04a1790fa8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fb3df24b1337871372b3e3fffbbb7f31e82de2a --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0128_022435_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e636ecbb99a8fb9243f7d420d4632a48a0fbebabab934bc6294ea9cd482bd547 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 75bc8381bb85efded2d3d87b8999375dffbdb2d3..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bfdb3497b6943c39afe4e9c1ac7b7bd9769f821a531b28908f9c1a39168c9639 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index a1bded62eaa6ad27597ab81ceae75eeeecbaf73a..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/diffusion/seed_456_0304_041118_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ddeb0be9fe10ccc41a1ecea89b0923e5be4eda5c11649f4d29e0c84fcf65b75c -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d041df4f5839a95073108f43f1c14a51d1a6103d --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f4a66ca81df7b1313cf8a74b6c0fc4905eb25632efd5dc5a6fefef5e33fbce +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7e9144d33a5e83079594e33fa6754333505d5ff --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0127_224327_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf288e4be17ba52122ec97e8b939e1aedb2db22143217a7c857bd2234c7cb71c +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0329_131225_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_123_0329_131225_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d041df4f5839a95073108f43f1c14a51d1a6103d --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f4a66ca81df7b1313cf8a74b6c0fc4905eb25632efd5dc5a6fefef5e33fbce +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..fb3e4deb291a719791e17fca34dc330445a87d1f --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0127_170028_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1abffc85d56b11095c0ae15d910f5b700360c3947b43864512a2327662c5780 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 3c62c2afaa75111551b882ad4f4ffb75eae495eb..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:45a2541b9ff69c325cacbd754ec4807a98cc2f1e42b1fac17e275cc72383b0fa -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index ace5d55958f55ec460e6d45786feb57e4d3ec7f6..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_42_0328_181109_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:de19d9dfade7fc5d56e2f77735c2a1d33fc75d1cececacaf3e3634c125eb824e -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..d041df4f5839a95073108f43f1c14a51d1a6103d --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f4a66ca81df7b1313cf8a74b6c0fc4905eb25632efd5dc5a6fefef5e33fbce +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..29c056ed2446380b1277b702b6a52d7e4c4c45f3 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0128_040455_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7048aba776c4efb9195ad1e337e60e1de7668b51788bc7ad8e826d39810c29 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 962902698f193783fc6850c5eb99cb6702cdd5eb..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e664534a90dd5b4942f69fa57699ed3146632c867e3c8d81566218ddbd3ff24 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index 394fc97c69e2d75c7c89fa92c836f0fd45642a38..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/kde/seed_456_0304_025033_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e027dcb6ab99816b18fc65d8c0a7d9e645d923cb6cb0b20debe4c1adde034385 -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5ee7ac1ef0e3f59170e8abdd0c786f659bfe540 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0079bb3c3414885e2ee4c40349c5abf7016b2719a6b2940cd652b307fa349633 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a7bd1717f02b2761dfdfc696b5151ad8baf9db9 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0121_131046_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f082f2a2cd81fe94e5c211597e69373c79313535a96b57b852899185704e17cd +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 8fde7c12fdebbf857c323051a4f4d87f0485eb17..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a27db87abd3ed6a9d04b0602fd0762da11a4fd49470afc81aa628d77c42310c9 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index ac588e32e53ff0fe9a6814e3b3494b0f214cd4e3..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_123_0330_093937_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fca97d0ac29edd153bf797e1089938b9c89579f5dd75107cddc6c2e4065e33c1 -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5ee7ac1ef0e3f59170e8abdd0c786f659bfe540 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0079bb3c3414885e2ee4c40349c5abf7016b2719a6b2940cd652b307fa349633 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..0310cb87698195b597a1bfb27e93bb25170176cf --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0121_060105_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da4445961e89c28f5f7d76b4b2579005e7a86f1b4e13ff1f9e589e959161dac +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0329_042123_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_42_0329_042123_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5ee7ac1ef0e3f59170e8abdd0c786f659bfe540 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0079bb3c3414885e2ee4c40349c5abf7016b2719a6b2940cd652b307fa349633 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..56f9d565a42472a2c2a7db775a0af93d5df23660 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0121_213903_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08dd10c6ad1c4afd5a6466542a22e2b8b9d64dda6f8dc78d9bbd42b34b597615 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 489feffad570f6b4d1a1a2a4495f68fa4bec4d2c..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a40629eacfcec20e85cdaede1e46fe53b16a536a9130de9737a5b809c352a680 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index a48560a3cfb329178c2a1efc7979c90472b65217..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/neuralODE/seed_456_0304_170330_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7fb20fe48ca791082e688ab43186fbbc5ed9d952cd36b2e6becffc4f5a394dab -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt similarity index 100% rename from walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt rename to walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..c662ea0e256e3c9389952a51256a013da59d4a1d --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0127_223336_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1807a37ad8a958bd80cfc335bdddd1073219d4e6877918557c47112b4381e29a +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0330_000935_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_123_0330_000935_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..74d17645d19d16e6cbaa8d8c49b56e3f5c4698f4 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b48b50a591ca7ddb895c10bd2606a95e7c4fe50afe220fa6dbff0a5d3a818c +size 1584 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd0fbd33e7e72ddd7dbb023c24b6e8685ab7efcc --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0127_170304_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4728f24e7f18f1c15f69831948514f7d5b28288e42af8be33617680296d4dab5 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 0b724ef37889ce354f123826bd15a58130400bff..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4bb1be3cf8616d114792b1acc2e7762e5ceea958fd635f15a74f6590aef4020d -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index ece38da4ba15ed3db8b8af46c40b8c2d19384e1e..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_42_0329_020359_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3beccfdac715a819eee74288b630094a5cff13c0ec92d23d0fa46f5ba5b6e2d8 -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..74d17645d19d16e6cbaa8d8c49b56e3f5c4698f4 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b48b50a591ca7ddb895c10bd2606a95e7c4fe50afe220fa6dbff0a5d3a818c +size 1584 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..0293856f0d2c2f0b74ac74db80b3d7072da424df --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0128_044515_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b36fc802af0f80437c10d7e48540a04a32efa77a5c199015716decbe0b48c2 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 75bc8381bb85efded2d3d87b8999375dffbdb2d3..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bfdb3497b6943c39afe4e9c1ac7b7bd9769f821a531b28908f9c1a39168c9639 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index a6bc8e2c7865a31e53cfa0971f81690a2e95fb92..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/realnvp/seed_456_0304_022938_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1d10dc76a94d473fd28469ba00a087ca31fb45d5128ed7e5f0733de54e62b448 -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..74d17645d19d16e6cbaa8d8c49b56e3f5c4698f4 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b48b50a591ca7ddb895c10bd2606a95e7c4fe50afe220fa6dbff0a5d3a818c +size 1584 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1d5038bcc4bac199d307d4306538079b426c7dc --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0127_223115_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1fa17de08b48debbf3374fa5e8c21e3a9d6ca2b474c3a4090449735ab4616af +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0329_225119_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_123_0329_225119_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..74d17645d19d16e6cbaa8d8c49b56e3f5c4698f4 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b48b50a591ca7ddb895c10bd2606a95e7c4fe50afe220fa6dbff0a5d3a818c +size 1584 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dffb68f403d24fd9f4a09190b58c38f18456889 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0127_170158_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e691880e18f9ea685dea0cef872130c5760d62f9599c058c1542d80886ea84 +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 0b724ef37889ce354f123826bd15a58130400bff..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4bb1be3cf8616d114792b1acc2e7762e5ceea958fd635f15a74f6590aef4020d -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index 0f2b382998a07b42701187169f3dc5678553c34e..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_42_0329_003838_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:17c127eda73e1d48e46ce66471a6711fa954fded8cd65c41f97a8a507da74955 -size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt new file mode 100644 index 0000000000000000000000000000000000000000..59e06c2f492128684f2ba95fee722295b99a8a06 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aad01634d4d0337e0f9494749a04632095e3a70a685c0db98e6ea2f47f52fe8 +size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt new file mode 100644 index 0000000000000000000000000000000000000000..74d17645d19d16e6cbaa8d8c49b56e3f5c4698f4 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/normalizers.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b48b50a591ca7ddb895c10bd2606a95e7c4fe50afe220fa6dbff0a5d3a818c +size 1584 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth new file mode 100644 index 0000000000000000000000000000000000000000..45c4e458926f73bf756054d47a626db14c15e7a5 --- /dev/null +++ b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0128_042512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97cceca44a192021539825a910e581454912f33bfc3f0a667b2907b494c7a7d +size 1473298 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt deleted file mode 100644 index 962902698f193783fc6850c5eb99cb6702cdd5eb..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/dynamics_model/model.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e664534a90dd5b4942f69fa57699ed3146632c867e3c8d81566218ddbd3ff24 -size 3736742 diff --git a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth b/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth deleted file mode 100644 index 66c90cc26f577a59e641a250f82086f542014e55..0000000000000000000000000000000000000000 --- a/walker2d_medium_expert_sparse/mbpo_based/vae/seed_456_0304_023512_walker2d_medium_expert_v2_gormpo_sparse_73/policy_walker2d-medium-expert-v2.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f987ca70097470e0d77680df835d6ca50646873915c4126464bee661b1aa10dc -size 1473298