Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.08
+      value: -0.20 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e72e76f9359945cc009bc8d30f395638d0986ebf84c5fc9cfe70cb9776277d3
+oid sha256:d220e1d809f6b24c9b502825deb990d51406e221d5f488ec209da70bcfd95e9d
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21584897516295315, "std_reward": 0.07651076348975845, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-02T03:16:00.477300"}
+{"mean_reward": -0.20247295089066028, "std_reward": 0.08825593735469414, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-02T03:24:47.258579"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0f6c023cd2705aa4cfa2a8f8dd1bdeac23f92b57f036adbf4ac88142d1d5ecb
-size 2646
+oid sha256:69bff9ad656b6a71e7a3d34c14b2abd31a9be18868266bf042386f8bbb9b721b
+size 2659