second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.06 +/- 1.10
+      value: -3.36 +/- 0.59
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11d32d3801dafe1aa721685cfd95a7f750c36a4a2983c022089d3b44d126f84
+oid sha256:81333a713bb58080ba7c458f53201d98794d06ef1a1b9c1ce1fedea6419aafd7
 size 108059

results.json

@@ -1 +1 @@
-{"mean_reward": -3.0592543583828955, "std_reward": 1.100039270106044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-27T11:00:45.469919"}
+{"mean_reward": -3.362829123437405, "std_reward": 0.5895588973834004, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-27T11:04:50.338797"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb82963b9d9da525abe92feacae9d11b5e77becd9c3a7343dcbf257877a2a8e
+oid sha256:998eccebaf3b907ef7c1c8893bc36cc981717f3f0e7da242440005a223e78f7c
 size 2381