Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.15 +/- 0.09
+      value: -0.22 +/- 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:e6a85cd52132d9e0ccaf7f1e4c54fad4781572dce2266f3d1d3656345b958583
+oid sha256:c8fc64aa4a09d8ac8e46b1c09d8630d9da7c8bf74c80ab91b90978e8998f2f50
 size 114068

results.json

@@ -1 +1 @@
-{"mean_reward": -0.15418128394521774, "std_reward": 0.09428934753806033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-21T02:12:37.746484"}
+{"mean_reward": -0.22336721569299697, "std_reward": 0.1086471553415012, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-21T02:16:46.964507"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cfc34430c32f914c9b62e8ae6b636cea91bd574b4ef82b9876df6dbe0acc3eb
-size 2644
+oid sha256:85f409d203c0f71967366f15ff042e27203bfc76e65d3c598a5a51686b3dd19a
+size 2657