Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -6.59 +/- 2.36
+      value: -7.71 +/- 2.25
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad7b1462af0a6a51e80c00c497173f608f919b0ad2c9f4d2926e8722202c2cb
+oid sha256:3a6e0af85cf8af30838ee85c3ae8d0bd82585aa5194b23d3ccf790ca369deff8
 size 59107

results.json

@@ -1 +1 @@
-{"mean_reward": -6.593149636685848, "std_reward": 2.3580336931109045, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-31T15:35:35.484904"}
+{"mean_reward": -7.713616155833006, "std_reward": 2.2491752501503113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-31T15:37:53.927035"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7902b6bda4787380801b7e119ff485554a14ea30bcdee5a7848a5be2920d8f51
-size 2630
+oid sha256:174ba76c570f8b83854cc1eddd7ff03e6b4af1972cd28e48c8d8794ce28aef9a
+size 2643