Initial car racing model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 492.69 +/- 245.05
+      value: 627.21 +/- 126.96
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-CarRacing.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4501d8422284ddcbbdb73060047c5e5be31ad2fd85b9a86a9e09adf121b462f
-size 27023483
+oid sha256:71f5824945d22f258f7212bfe837423a952d2d262ed6dc658f7ffa06d6e6b828
+size 27023488

ppo-CarRacing/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8dcf71878fd7b3250110f217207d85d21bbc0a60cc6143770247f8cca8f861
+oid sha256:1c834441ec29d574b9e77fa891e8df50c12d223275d219472fdf780c746a96c8
 size 17412055

ppo-CarRacing/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf182fdcb3d8b8c8f5eef945180e1008a93237464b77595302c2d11125ccc92
+oid sha256:b995535aebf34a53ded8f5fbcbbbf8fcb58456c5312e7c2893a6b8b5386d976b
 size 8706942

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8619c69de9f984444ca42c20db62c68d73c8b214bede521818844ae91748b9
-size 922979
+oid sha256:c7e46a7185d38d53942bf2d03015fcb538ffe8aab7d3197dae1a5e34f79f1d40
+size 845942

results.json

@@ -1 +1 @@
-{"mean_reward": 492.6949251435697, "std_reward": 245.05002009081542, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-03T06:05:04.921000"}
+{"mean_reward": 627.2098754033447, "std_reward": 126.95656141100422, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-03T10:57:05.029641"}