Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.13
+      value: -0.22 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8d8daed2298247ee66104fdf051e51601820fe7c0cb25f81ca0cbc9f5e066e
+oid sha256:2947e6155466633338d95d5306690fa73732874decb028651d9185e0a83620c1
 size 114189

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20965946074575187, "std_reward": 0.13463054901384683, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-15T11:05:55.664510"}
+{"mean_reward": -0.22067347411066293, "std_reward": 0.12562490661411352, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-15T11:16:24.615105"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771e229c35dee514893a2912ec211383a408851679ba354682dea894f9835135
-size 2657
+oid sha256:30291e66be892fdbc6ca274b427bf8b6d7aa3a1fd30baa2cd9c59c5882a7fb40
+size 2644