Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.94 +/- 15.17
+      value: 255.32 +/- 18.77
       name: mean_reward
       verified: false
 ---

ppo-lunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f416eb428a38b9542cee9d5688855f17151a52bd9280df8bda2bdc5a2245d4
+oid sha256:ff35674f7a8ebb8634af3772567846f4d23257f6c16654fc44a0a52b50c6fe6a
 size 147427

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd0e6637f1bcbfeca002819cf99dd7aeed995596a5a8588946992d2b39e9f08b
-size 183189
+oid sha256:5ee3755b2e823c78b1cdb7f4349b0e62d5c2aca0d8dc67da234cb8937a8c975f
+size 176470

results.json

@@ -1 +1 @@
-{"mean_reward": 265.940711, "std_reward": 15.167428894863287, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-10T10:38:33.980939"}
+{"mean_reward": 255.3163676, "std_reward": 18.77390371898252, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-10T10:40:04.259201"}