Upload PPO LunarLander-v2 trained agent

LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424fe079d85adcdef4d8f2df8d6a74724711fa52a6adef2f61292f2650ce5647
+oid sha256:34aeb2bc0327bc8e14207acc825a4dfc9acaad182a1fbc155fb08abb67dcfd79
 size 462520

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 279.14 +/- 14.03
+      value: 290.21 +/- 11.28
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4030fa99bef7e5bf793df49699335663a12d8c66dc0fef2a5bcf53e3aeb3f141
-size 152995
+oid sha256:f016538d986e9b3f11c785b0179972e1a0cc218f9e90e21c298b63489c7e5262
+size 141434

results.json

@@ -1 +1 @@
-{"mean_reward": 279.13806007332744, "std_reward": 14.033176401104086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:16:12.450945"}
+{"mean_reward": 290.2061146699146, "std_reward": 11.278385196840974, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T10:17:03.263317"}