Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.42 +/- 0.70
+      value: -0.25 +/- 0.14
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0fbc0b820c78b648677d09d3810cbdb55cb720d574fb850f8d9851dd30ed1f
+oid sha256:9edcf076b874981e4062aeec03fc89ef1ae5a6a394cf8ff59507fc2349f051cb
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.4239088397473097, "std_reward": 0.7033247757939026, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T02:44:43.370626"}
+{"mean_reward": -0.24759915862232446, "std_reward": 0.13712706902814048, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-05T02:48:07.004711"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8cde300c5b34d10c59da0e5b0196b0c97bb73f1bde771528ce55200dffd224
-size 2646
+oid sha256:aea3c802e26d4f8df4cd9a896141b15bcc0e7fc28b11fac7a3239136c18d1b83
+size 2659