Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.01 +/- 16.28
+      value: 251.77 +/- 19.70
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782bf0e6ec7ea2080f5bb18fcdc1dba63b392f45c049c3902b0c6977f4828a6c
+oid sha256:cf834ba59463687ff44c4d634badd198253982a311ae2235952497baebb9ab39
 size 148127

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5149c7faa002915b0b225717eb3fb01861d72e28b4ed33dfe4e4d9c93e253cea
-size 159487
+oid sha256:2ae489cf4bff72e3eb82c0eec19c5ec08140732585fb3be98b5a5703de639d97
+size 156330

results.json

@@ -1 +1 @@
-{"mean_reward": 265.00812085633925, "std_reward": 16.279142811818268, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-14T10:16:45.080183"}
+{"mean_reward": 251.76590672829533, "std_reward": 19.70408751714331, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-14T10:17:30.834416"}