Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 276.69 +/- 21.08
+      value: 269.69 +/- 10.74
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd7759826f4b9fb5b9595b13367f1a303575ed404ee56991998d06201f8d2ec
+oid sha256:1c4de5b3bfcdb218c38911bdfc045a04043240992a9ec92323fc1acb20a3445a
 size 150537

results.json

@@ -1 +1 @@
-{"mean_reward": 276.69068486968945, "std_reward": 21.076399906839534, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-16T05:57:04.861662"}
+{"mean_reward": 269.6928989107713, "std_reward": 10.73747023004931, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-16T05:59:41.275479"}