Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.14
+      value: -0.24 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c433753b82bc648e59bd1ab84632329c839cc8c183eb7f3974a86be6bb887c3
+oid sha256:be4d53099ec1b815820995ebe4fb87b8e5ba6ae0a938d0ed1087d57a559ffdbc
 size 113034

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2580797504633665, "std_reward": 0.13540760416841574, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-10T15:15:38.656128"}
+{"mean_reward": -0.23686171481385826, "std_reward": 0.12518467184642998, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-10T15:17:44.047985"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:811ce1949d002923f549428edce35803b866c19a432dbda466c0558cc4e69651
+oid sha256:fa3e7cc8bc164726fc92e878d6201c3b54a89fe66e5c9405602196a1a73957cc
 size 2657