Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.11
+      value: -10.78 +/- 6.18
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad6bf7a248f35e4e7ea1f4d603a6b9ec71f86915ad85d9a8d305fd39f8d1991
+oid sha256:07571f6cc221ba7020a7d156fd812d8c3be708e5415cbf2238f0f3d9e4ce7aa0
 size 114188

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2355538371950388, "std_reward": 0.11150865629394571, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T04:01:20.168261"}
+{"mean_reward": -10.77893065623939, "std_reward": 6.180521870059227, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T04:13:13.755819"}