dfreddi/PPO-test-LunarLander-v2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 111.86 +/- 118.07
+      value: 83.07 +/- 96.31
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30a1c841e48b3949bf5d26ab8c56a6f199f070f9878a837043d7c3969eabe11
+oid sha256:ec82fd5c8dd38f7fdeebe65b04173211b7d79f36cde049efade62d606e07aad4
 size 148016

results.json

@@ -1 +1 @@
-{"mean_reward": 111.86407060000002, "std_reward": 118.07194004431507, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-30T13:53:40.719322"}
+{"mean_reward": 83.06894050000001, "std_reward": 96.30672603692858, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-30T14:02:52.878371"}