Upload PPO lander trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.14 +/- 23.87
+      value: 254.90 +/- 24.86
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404cec5372652c3f4ef7ec6c99519a59e832b803672f188b63a0244b7e4b7679
+oid sha256:5492eb7b776dccdfaad09b6cab2d4a3d917363244f0316000f8d2117787fad3c
 size 148136

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6688ba0ddb3e09874851f4d03e6041c96cbe2c9269a39742a98e35e5016f5296
-size 171890
+oid sha256:0fbe47521f61702b1f025ce3c61fd310d1194842f4e5a5ba507d2fa16c4ef106
+size 170374

results.json

@@ -1 +1 @@
-{"mean_reward": 247.13935538996307, "std_reward": 23.86928073031924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-21T16:52:19.599272"}
+{"mean_reward": 254.9039764516896, "std_reward": 24.861891129975017, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-21T17:01:58.994092"}