Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 285.12 +/- 21.21
+      value: 284.97 +/- 18.46
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-3M.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04970335a22c27d4d72e272128d81a68de8a135492770d6f7fb99eb776fad3fa
+oid sha256:0e3536f731cd1b4a21cb2e05c9cfb8827715419ede49ec4c32606395c5850c83
 size 148171

results.json

@@ -1 +1 @@
-{"mean_reward": 285.1194170428612, "std_reward": 21.210751911153977, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T02:59:19.669509"}
+{"mean_reward": 284.9660289600063, "std_reward": 18.45793382855636, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T02:59:40.535134"}