Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -8.95 +/- 3.63
+      value: -7.85 +/- 3.99
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9703f8237f8bd64b94548dd0783a46d396656006a44e48ffa78d32a01ffdb59b
+oid sha256:d56b320bdbdf267675420217678fba9a406c89fbd298615b4633fa687fef6fde
 size 111855

results.json

@@ -1 +1 @@
-{"mean_reward": -8.950916520506144, "std_reward": 3.625293817703563, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:21:53.886502"}
+{"mean_reward": -7.849386167526245, "std_reward": 3.990718739450071, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:22:14.715178"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bc4d1cf1710c70fdb77c30f2e402be93805b0943bf381562825a911b7fd325
+oid sha256:ac5ba6ae78d3ef432c1476765f34520691c7a97881ecde78bf67ca8db832c82d
 size 2646