Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.06
+      value: -0.26 +/- 0.15
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c03ad4d65f91da1a30fdf4d1d3a996478acaa4c96abc49e260aa3753c220b3
+oid sha256:875e7c6fef85b910c2f81dbf139ce5cd9ecde9ea07bd134c234e5100708cc15e
 size 114173

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2568624809384346, "std_reward": 0.057856558636409434, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-13T23:14:54.086825"}
+{"mean_reward": -0.26044979998841883, "std_reward": 0.14593412690070623, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-13T23:21:30.487587"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dfe8cb102b036a6e5737a85065da48c7dda6edce813231a2ebdafd432eed25
-size 2657
+oid sha256:941ad14d0476656070c59a76653e375cba89780215e5d0903f49cddc3a684617
+size 2644