increased n_envs and n_steps in model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 59.89 +/- 21.98
+      value: 58.17 +/- 51.28
       name: mean_reward
     task:
       type: reinforcement-learning

car_racing_kk_v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4c493908200663cd6e635ec493e4fd52a219193a69145507b9a5535ef2950c
-size 42891177
+oid sha256:ec518a40931b4bc322c3fad5069c8d5de231c147016783798c2909973f15fb07
+size 43038639

car_racing_kk_v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a5141213d6a4774c01d5a835c32fbe4ce79c0055b7d2d6263716c48857f4ed
+oid sha256:3041905d6426a9b0986ed02e6cf7fb423156ac7a24fba210c3acab0b51e6a2ff
 size 28388247

car_racing_kk_v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621ad259857db5df3d96867f0df994c019359765126157880b775733974a2bc5
+oid sha256:123052a7ac0cc6281916c4a587e08ad3e7173308404fc6276db87ee27b923c96
 size 14194942

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bad9179bdbf8d15f6ff9ffdf3ea17bb69be64287df5c08e490e995f3e400f8
-size 551845
+oid sha256:7789e90cb210331dd1c7699747a43ea2bae5eb1dcb3d98ce9ade2c4a6225bb0f
+size 1011168

results.json

@@ -1 +1 @@
-{"mean_reward": 59.89021572768688, "std_reward": 21.975570145923555, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-16T18:49:45.575866"}
+{"mean_reward": 58.1651180870831, "std_reward": 51.27521834770905, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-16T19:02:04.899818"}