Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 184.57 +/- 83.56
+      value: 222.60 +/- 98.00
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bfaa2ffc53e1cd7fdaaf0713538d20c1676d3addfa23236325d273e03a88cc
+oid sha256:501102798ebf58cd880f61425adfc6a689bb630a8b3ddb828fa9d1fa9193a505
 size 150619

results.json

@@ -1 +1 @@
-{"mean_reward": 184.56698206171762, "std_reward": 83.56099177037744, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-26T16:01:19.542948"}
+{"mean_reward": 222.60060956129254, "std_reward": 98.0010490239198, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-26T16:09:13.754229"}