Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 272.47 +/- 19.32
+      value: 270.02 +/- 16.07
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a625fffb4ee35fbae5ef815ddfe9fba8dfa612579fa7db10f26e03a5537b192
+oid sha256:217b84c48fa247bf2282f764e98968c4c85defce1b2b0d73bbba2879bf8d2234
 size 151165

results.json

@@ -1 +1 @@
-{"mean_reward": 272.470033, "std_reward": 19.31710425562136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-23T06:22:20.436312"}
+{"mean_reward": 270.01743870000007, "std_reward": 16.068110270075564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-23T06:24:21.809254"}