Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 131.18 +/- 103.26
+      value: 168.97 +/- 115.73
       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:ba4d24bd59509d172b18d59382bc4fa0534c8c100cdc059b6cff69373a57b5f7
+oid sha256:3067b7624f12e2b38f0c8de0439c51dcf1499656bf4b9ba2591f48ea650647a8
 size 26879542

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd0854d50e111a7224b3c1c55ab92d3fa6364cda18fa139d55ec2802159213e
-size 1054850
+oid sha256:b0491ca846e5ef02a4affe0d07f341285a3dc3c4ff184d649632af803a268fa6
+size 730193

results.json

@@ -1 +1 @@
-{"mean_reward": 131.17592993155122, "std_reward": 103.25725473989432, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-21T11:59:56.341913"}
+{"mean_reward": 168.97033464312554, "std_reward": 115.7304205656672, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-21T12:09:07.622174"}