Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.09
+      value: -0.24 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56627818a95fa621dd40bd30ec218e8f25e5da7c2d0d68fadaa50b1a09b7f5e1
+oid sha256:bad6bf7a248f35e4e7ea1f4d603a6b9ec71f86915ad85d9a8d305fd39f8d1991
 size 114188

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2303632719675079, "std_reward": 0.08864608343233478, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T03:58:33.430848"}
+{"mean_reward": -0.2355538371950388, "std_reward": 0.11150865629394571, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-03T04:01:20.168261"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e778266f21e79b5d9eac5cdabd79b10a131d36dd885a4575253f8f37aff529ef
+oid sha256:edef5238d5b3915b7e7ea11f665383c5f92f0eaf5cf8245971a5fcba3c8bdad2
 size 2650