Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 301.91 +/- 8.90
+      value: 295.48 +/- 20.47
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda8d0dfd959617b80603fbf709969e595fd2d75c9bd07429a36dde92feb7e27
+oid sha256:c0e39457f9a7d53e81a932c6d34af49098bc6458ee7542afe7b9bb4182fac9f7
 size 152086

results.json

@@ -1 +1 @@
-{"mean_reward": 301.90817125202165, "std_reward": 8.900357205143017, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-18T05:49:17.388672"}
+{"mean_reward": 295.4843871757213, "std_reward": 20.472089649637535, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-18T05:51:48.085213"}