Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.10
+      value: -0.20 +/- 0.14
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa3f0ccc3868789d90a4306f29123987a6b54164decc33b72e34295c84c9945
+oid sha256:4eebeedf2689f83c9ede16ba51b3a6dd85e18c1731c5c8c97e860f267042ddde
 size 111462

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20343351401388646, "std_reward": 0.09754387535558759, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-25T10:53:18.656453"}
+{"mean_reward": -0.2019900598563254, "std_reward": 0.13550011283678443, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-25T11:02:12.995677"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5814a469080ae4e5822eba17eb9404fbcb6c959a0e86492c9d3e4a3357d6827
-size 2636
+oid sha256:fd4064da1056a65a02150c5ed52158434b9f322cdbc88b2a012052aaee9ad612
+size 2623