Upload PPO LunarLander-v2 trained agent2

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 256.11 +/- 16.97
+      value: 260.06 +/- 16.47
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07448d2059cab30d1c8c1fb6ed1f40ab69fb7d9651aa6d4ebf4a8d4f2c1d3598
+oid sha256:c68e9043f0c3ed1dd18f5abe569d900f03ee5358688f84a1f9599a7bad2214d8
 size 148369

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:695e68b9b7e66726ec771c6db8e8fc7471345b8908852ac75381868d06e6177b
-size 211409
+oid sha256:ef2eea5c88276d6a31053cad308e56b12c828c541dffcbb8326c6d3b68f88827
+size 212105

results.json

@@ -1 +1 @@
-{"mean_reward": 256.1130271373353, "std_reward": 16.96755247674266, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-04T17:10:39.656373"}
+{"mean_reward": 260.0575900575911, "std_reward": 16.46855918284247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-04T17:12:49.725266"}