So long my friend

PPO.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d37d11319b84268c8dac0796e9a57ed00961f1b8d69eb9e5c1e362e7dc1cfa
+oid sha256:93769b4988fb27857f4230037aedfd234b4f1e618d38891f94caf5007a6140bb
 size 149230

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 249.51 +/- 60.12
+      value: 276.36 +/- 12.56
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 249.50728659999996, "std_reward": 60.1185017180558, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T16:36:25.071840"}
+{"mean_reward": 276.35615125677384, "std_reward": 12.559491055736679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T16:39:36.008642"}