Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 244.27 +/- 86.86
+      value: 278.61 +/- 18.37
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba5e8dadb688c087586cea116d1dcb9014eda8efe9d0b172d1071add19ee043
+oid sha256:c6cdf214446c35f0b96492faaa037f4ffc175c8ce7581666e0d62cdf3bf9ba58
 size 151992

results.json

@@ -1 +1 @@
-{"mean_reward": 244.2748588, "std_reward": 86.86407650091634, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-26T17:57:17.230402"}
+{"mean_reward": 278.6118378038735, "std_reward": 18.366166241506235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-26T17:57:41.972152"}