Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.27 +/- 0.12
+      value: -0.25 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4d80e49c4ca9373aa8391fbb6d57a1ff2759414005ff20ea32b4e9a538bc36
+oid sha256:5278d4dff2f37c5de97f7e0db81cf89159868678080ce7399c94b7310c0708df
 size 114275

results.json

@@ -1 +1 @@
-{"mean_reward": -0.27167507661506535, "std_reward": 0.12250515429343867, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:29:07.679013"}
+{"mean_reward": -0.2474898432381451, "std_reward": 0.11017355921216476, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:31:48.311635"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f872f0269265653bd37e8031d2dcf3e820894b6ec332435780506416b45b96c1
+oid sha256:45ab3704d910c624487325540708c7e6a09f0ae569b69604d44f4ae2338582b5
 size 2657