Second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.12
+      value: -0.20 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9538cad8d22d3e197f57fc0d26eb774c4dbfc96e7791cd939ac2e4cc96291f80
+oid sha256:220f364bb7320b053d7bec0020ffd6a53ba9db5d4b6b8f2a06b65f8ff7b04364
 size 114184

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23739332533441485, "std_reward": 0.1183462537633397, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T20:54:49.681730"}
+{"mean_reward": -0.2045908212661743, "std_reward": 0.10147378744392842, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-12T20:57:34.166326"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee937187fbd9477cc19ef84b45e669cff4d98764b70505dae404995160c1c752
-size 2643
+oid sha256:684bb2b1a5996020e118fb1f109661f74b817808856963172dab3d4c8751e471
+size 2656