Second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -5.23 +/- 2.00
+      value: -5.61 +/- 1.59
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3500bd27b01b6ab9927debd9b063e456a1db4bddd034d1299f2b34fbd4033059
+oid sha256:38d11020156e2c9b847473b6d930e9b9140f404ef6adabfa706c87e723c564b3
 size 108064

results.json

@@ -1 +1 @@
-{"mean_reward": -5.228219652571715, "std_reward": 1.9960442558421647, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-03T03:58:06.866730"}
+{"mean_reward": -5.611408982891589, "std_reward": 1.5913235141361883, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-03T04:03:11.208980"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357964bca1c2c616b16d6b544d8e605753e84c078ae16837b1144c1cc0effb86
+oid sha256:a0f66f0019585bd11d9727ebe3f4d0cfbe81b64f9f9a66b0cecf763c9f1aebcd
 size 2387