Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -18.45 +/- 6.22
+      value: -13.09 +/- 2.58
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e56b69baf71474aeb3527a2b243f6a8d9040ec05d285c6481fa27063fd7e5a
+oid sha256:137b64f09016132c728ebef56b5aec3a2d6196b928453b6265daeaf610fd727a
 size 114099

results.json

@@ -1 +1 @@
-{"mean_reward": -18.449813398718835, "std_reward": 6.224356565199301, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T05:16:02.152710"}
+{"mean_reward": -13.088169884681701, "std_reward": 2.584828341517318, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-29T05:33:47.655169"}