Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 225.11 +/- 25.25
+      value: 238.77 +/- 20.25
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2decb2369f142be016101198984cf5801175ba470a193b202bf0fc8042e762a
+oid sha256:18eefe11384e36079fac786d756776df5a09738ec3dcca0343e1dce0333a06f9
 size 148084

results.json

@@ -1 +1 @@
-{"mean_reward": 225.1063099568808, "std_reward": 25.253357171683753, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-18T13:19:33.276363"}
+{"mean_reward": 238.77412414356877, "std_reward": 20.251768537366964, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-18T13:31:02.822090"}