Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 253.77 +/- 26.81
+      value: 251.06 +/- 15.43
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4cb7ad2c344b1cf3a17050aacd58a938367fc3cda0ff78810e5f024e1c031a
+oid sha256:e9d034232fc51af4da5244e5353c3395f55552f562b107c59bb18471232dac7e
 size 148124

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78da1c8ee44dc3d6cf67dec2b6fcd760d07bbbd1b1d1a7f432c2ccac91987eeb
-size 179697
+oid sha256:1b2a33bdac09230fe45bd82658f8265fc7762cea9f440dac7a58ea56c4dd52c7
+size 182119

results.json

@@ -1 +1 @@
-{"mean_reward": 253.77462680000002, "std_reward": 26.80931641302786, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T17:46:55.876447"}
+{"mean_reward": 251.0570531, "std_reward": 15.433886330639297, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T17:47:38.630626"}