Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.11
+      value: -0.23 +/- 0.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ca7bad0d6de7a74c4bbe99658a1fa1d384ea0251f8ae3cb6e08f85e2c7e9e4
+oid sha256:f01f85f8d53564bf59abb0e9196579876abb7240ec48f9be157f622ec1bf2b59
 size 111330

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19787079165689647, "std_reward": 0.11374296086155565, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-28T11:29:42.016492"}
+{"mean_reward": -0.23323373012244702, "std_reward": 0.05819870513031608, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-28T11:33:58.103480"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55bd9300ef1c6af6bff0457b7459d747d4c05549b02fc09e75c16a8f3337c8a4
+oid sha256:32d4965372c9c51232ae19ce49c832900fd6ac60febe063c0d04188f719aca0e
 size 2565