Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -12.30 +/- 2.59
+      value: -12.69 +/- 2.75
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc35c34d9cf504101e327c940d22f38a72c83da6b01e48c950e24cf55301122
+oid sha256:31366d70f4ffd9a83bbd201415548a040c2a4f8bc46a853e78b6da785e53d933
 size 114099

results.json

@@ -1 +1 @@
-{"mean_reward": -12.295171999558807, "std_reward": 2.5944973756553553, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T05:44:06.908581"}
+{"mean_reward": -12.685704956948758, "std_reward": 2.751210756177914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T06:07:04.008530"}