Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -11.66 +/- 0.79
+      value: -0.17 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855be1fa41f8fdfb5603f0e1636399eb92d6df21be19c78bcc1fbc16405e9c52
+oid sha256:aef8152eda730193a5c85af89f53748214095fcea8e9728dbf80b4bb8a31af05
 size 112907

results.json

@@ -1 +1 @@
-{"mean_reward": -11.661744700000002, "std_reward": 0.7862634508628836, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-11T00:45:04.349995"}
+{"mean_reward": -0.1741826952667907, "std_reward": 0.09594527006430881, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-11T00:46:06.544856"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb46ce641e1b010cdf4c55e18901b337fac14aaaec6aca91dc89d3122250723
-size 2657
+oid sha256:23bd849e53e2414ee617960682b44e7ca6fb0f520d32c25640c1b88b38a4a5af
+size 2644