Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.12
+      value: -0.22 +/- 0.14
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ece61bba901b94218ccee7c048e1a92b74b59771f29aaac833815ff95ed239
+oid sha256:bd96cd0418d1db417e7e0af1a96faf44dcc868c071be79243177e31164a847c6
 size 113790

results.json

@@ -1 +1 @@
-{"mean_reward": -0.25604618471115825, "std_reward": 0.12294541185069116, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T19:15:56.670360"}
+{"mean_reward": -0.21719708666205406, "std_reward": 0.14091157264525306, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T19:26:15.879478"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4870d5f10097910388a10d510117c1f4b34602b539d68358f10a166c46116289
+oid sha256:abb69d6ff68656c34ebefe47562a8c9028328a664449f5c086c4bde1bf64f9e5
 size 2644