another try

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 804.47 +/- 114.54
+      value: 808.23 +/- 105.55
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-CarRacing-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cded743796ca1ce75e5f443c55fa14fe7455ea96bfd8aa6ec793415b3288326e
+oid sha256:72583967a70584c94194b9d0f02d25d81ea7d1df1596eaa4624b7bb38cffc068
 size 26599906

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fab624af13e3fc97799487d98658f00c46b8c83d4baceadb3f7f8aaf2b32aa3
-size 815840
+oid sha256:a8437cde6fae99d0048840b2f8b70d6ee8a2ce8a09b8e00ab38deacba6a545e1
+size 939390

results.json

@@ -1 +1 @@
-{"mean_reward": 804.4736004687845, "std_reward": 114.54456493864059, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T09:19:45.168671"}
+{"mean_reward": 808.2256240002811, "std_reward": 105.55443781784719, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-15T09:21:38.087227"}