Tuned PPO agent trained on LunarLander-v2 (1 million timesteps)

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 284.99 +/- 15.76
+      value: 271.50 +/- 29.53
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952a8325a3e0aa0fecf31765a9fd89bc38a849bea16ec8a3c2294b5ff0574908
+oid sha256:f7ac254788c51bafe34c0b11ffb360ef2e674aaba560eb719a62b7f70582c617
 size 149969

results.json

@@ -1 +1 @@
-{"mean_reward": 284.9926408, "std_reward": 15.756736226783268, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-21T08:19:48.782661"}
+{"mean_reward": 271.4968271, "std_reward": 29.534047054395643, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-21T08:20:07.344138"}