Upload PPO SB3 LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 215.90 +/- 19.41
+      value: 234.43 +/- 30.69
       name: mean_reward
       verified: false
 ---

ppo-SB3-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae4069e9603350a6e91882c5c36c0066d0b51537a171ac33ef22d5db6a1fbfe5
+oid sha256:603eaaf72daebcf3347a4bf10ec589a5cbefab7801fd30036abbf98f7ed11f76
 size 148088

results.json

@@ -1 +1 @@
-{"mean_reward": 215.90333070000003, "std_reward": 19.413936595984637, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-10T10:13:16.330355"}
+{"mean_reward": 234.42674079999998, "std_reward": 30.69469078423679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-10T10:14:27.802333"}