Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 232.68 +/- 21.75
+      value: 220.42 +/- 17.05
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263760cf6e4002039a4b6a095008f93314649b5117f06f866952e20a1967db8a
+oid sha256:2d1ac80eeeac7c3cf9781c2c57672ad40d7bb05d1edf26241d1d2e05f62e55be
 size 148136

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514335465da6e9be9997afb498e43cb6fd52b497a3c379ac3c8b816fffc517b7
-size 165626
+oid sha256:a8b9dc40e9dfab80e24740e060266482b44ec74e534b27c0d40e34a40492c9cc
+size 162225

results.json

@@ -1 +1 @@
-{"mean_reward": 232.6838747, "std_reward": 21.754059157087962, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-13T17:52:42.445525"}
+{"mean_reward": 220.41699994079195, "std_reward": 17.04906164113168, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-13T17:53:32.119811"}