Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.11
+      value: -0.20 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51bd4037e4247462baed25b51b0faa1a822bc31972364172abb63cd5715207eb
+oid sha256:e3f236a5ee7b6a0841bdae5f05602679c2325a4d9f24d218999a6c0a0a8f7acc
 size 113592

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20471477173268796, "std_reward": 0.11286201263204529, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-15T08:53:25.846661"}
+{"mean_reward": -0.1965315880253911, "std_reward": 0.0862652092548754, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-15T08:58:44.523700"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee7a66d95b624c46e9b4d80222bc9719f46ed1f41c679bbb3c71f2ef37575c3
-size 2643
+oid sha256:29ddbf0ccf5ec6c06deaa4e099bbca49d6ece96f5d0b229aeef4ce64bd54607c
+size 2656