Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.83 +/- 0.34
+      value: -3.18 +/- 0.43
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a9378a76277ba170568766bf2bd70bdb8306c3f6b8f47ad234b405bff55c9c
+oid sha256:c48f46eab9ebff4bafbc334f7bddb4904ee30d72502134c12221216132d68978
 size 108075

results.json

@@ -1 +1 @@
-{"mean_reward": -3.8335901458747683, "std_reward": 0.33872934900920665, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-19T17:45:53.794700"}
+{"mean_reward": -3.1765289100352674, "std_reward": 0.4344353277378388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-19T17:46:14.160752"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:915154e7b09eb2017ed063611b50102f4f2b721d63824fa2dda7eb6d1bcc1b96
+oid sha256:0fae87db4c622563ea6eff2b9b409926d984441a45b596766db1941e57c440f9
 size 2387