Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -1.60 +/- 0.23
+      value: -2.18 +/- 0.54
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d8d5a99fe759ce6dd660efff215757b8a75e3420fa0d014d523c5856af010d
+oid sha256:353bd98e0e850b4126873d3e9656ca0bbd4dcf5773552f52e4d99a6baa461d06
 size 108145

results.json

@@ -1 +1 @@
-{"mean_reward": -1.604054619721137, "std_reward": 0.23066892067300687, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-22T18:32:15.890600"}
+{"mean_reward": -2.181717186048627, "std_reward": 0.5421997579339837, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-22T18:34:43.176690"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b66a6b00257d361e82fe15733a367f1223e7f6168e745fe63517ad4d9d97f96
+oid sha256:37eb771d92587788c11f9cfe7f3afa7231c187e919b992ee65df8ac6fb7c165b
 size 2387