Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 253.45 +/- 17.50
+      value: 266.34 +/- 12.95
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9025b3d9931868966bd44fcfef49262b893fa544967e287dea742534224edf
+oid sha256:79173f31bfcdba3359b6e41ea1b16f4bbcd7b35b0e8ad45c582f333ace5f71f4
 size 151053

results.json

@@ -1 +1 @@
-{"mean_reward": 253.45051787208712, "std_reward": 17.504890076387795, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-31T14:10:39.695043"}
+{"mean_reward": 266.3418259, "std_reward": 12.94565794060564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-31T14:11:33.050083"}