Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.16 +/- 0.12
+      value: -0.20 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0000710dd51cc546e9fbf65fc1839c3cd031ef8f1bbd945045fc664abb88cf54
+oid sha256:4e63eebffd2342526dc41a4c7a5936d1d16d62f586c38a56cd2575594a25a0c4
 size 110246

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1562335081398487, "std_reward": 0.11686742418874997, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-24T03:43:33.062346"}
+{"mean_reward": -0.19813847718760372, "std_reward": 0.11641937366972319, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-24T03:49:06.875242"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce03c6bb10032f13cd2bf80ffc39fc394179cf2e613e11e69a1902d21df4d11
-size 2659
+oid sha256:7640a7b21fa1b42145f802859db0518aed2185d8a0c1fd5cb0f0f2dec17fbdc4
+size 2646