Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.66 +/- 0.61
+      value: -4.03 +/- 0.48
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15321fb6769b462fcc1f7aa392e89ad332d601c754784d6466371790b8f1245e
+oid sha256:99ae6f17f28a3e8d2068bf1b10169488d45681f0dff9dac3431cf4e848f59b1f
 size 108157

results.json

@@ -1 +1 @@
-{"mean_reward": -3.661233573034406, "std_reward": 0.6133163102783467, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-29T12:55:24.926358"}
+{"mean_reward": -4.034858308080584, "std_reward": 0.4775269546075044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-29T13:02:10.878735"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be35e4127468b415dc16121ddf09d83ae5f82a5b0be31f3f9b4d26de6703eca3
+oid sha256:834850b919ab36661c28e4e8cac09afab6ffc7f66373350531fa9e2fe7347a79
 size 2387