Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.52 +/- 66.35
+      value: -122.92 +/- 37.98
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a61f9201460df06d2b1ee18d77f45f2de49303fb19473664630ccc2347d037ab
+oid sha256:87e0643667bfc37be14d96d6d8dcbc578065fa1a640c897f40c8aa9a183d266a
 size 53927

results.json

@@ -1 +1 @@
-{"mean_reward": -140.5209957207262, "std_reward": 66.3536754409093, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T19:03:39.652028"}
+{"mean_reward": -122.92458161596187, "std_reward": 37.977493762273994, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-02T19:10:51.456000"}