Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.09
+      value: -0.23 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd70faaba11e19227f37753ebb5418dbbee8f93f8889540baf9e2f6e741dd9d
+oid sha256:a1ac553dd747b00304adf52554b9abdf9e57c0e68a6fab9c233857860830f715
 size 110433

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19749439265578986, "std_reward": 0.09054987892763917, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-03T20:42:26.756791"}
+{"mean_reward": -0.23036114033311605, "std_reward": 0.10806662102866177, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-03T20:43:16.294197"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44af06f0a35bd4b11bec8621efdff03df36ea7de8775363df4f97faf2c6adc7
-size 2646
+oid sha256:c7c561c5f92aebd55c276fd9a5e3792dc24edf3d6adc4e98857ab0cee4e7a95d
+size 2659