second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.11
+      value: -0.24 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a7b4e1c00edad66f07223a81c160d332cf7d1c5e872129d757f2f919f9a47d
+oid sha256:2dd7ffdd13333abddbc620df7a696ac0a80e5bb571848be7653cb14ba9b58aa2
 size 106832

results.json

@@ -1 +1 @@
-{"mean_reward": -0.196783066727221, "std_reward": 0.11468107179531666, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-27T07:44:36.899290"}
+{"mean_reward": -0.24343753941357135, "std_reward": 0.13082544823872247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-27T07:49:21.526405"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1049e09156c33a8ada187ab5aea6f4a14360095aae22b484bac016d8fb4dec0
-size 2623
+oid sha256:8aaebe20d620b4f8b834a05b0f900aa76f57283b99be34e25d2e5dfb8722d5f4
+size 2636