Upload PPO Lunarlander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 109.04 +/- 56.86
+      value: 99.25 +/- 77.41
       name: mean_reward
       verified: false
 ---

ppo_lunarlander.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08694ecc846f1bf4408a0701dfce82d48c711733ac28452cdb0c826d4506ea99
+oid sha256:742cf2fa0f552a7b829fbae99f70c5bb9625bea169471fb01c668f3c8c370c07
 size 147426

results.json

@@ -1 +1 @@
-{"mean_reward": 109.0440527, "std_reward": 56.86480596253884, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T11:30:18.836830"}
+{"mean_reward": 99.24949939999999, "std_reward": 77.41262730307886, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T11:36:48.663223"}