Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 254.62 +/- 13.62
+      value: 272.37 +/- 19.91
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebd6f4b25c027ada51c80e8b3f4f1dccc2178685f5471bacf81891ed1357ec89
+oid sha256:f73cad7077749f54fa034e0a397bb208b3c1b63c920a8ad29ae0a6c245e7620f
 size 150576

results.json

@@ -1 +1 @@
-{"mean_reward": 254.62452910000002, "std_reward": 13.623940164026559, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-28T17:54:20.689718"}
+{"mean_reward": 272.3748787, "std_reward": 19.90531728114236, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-28T18:08:48.185941"}