PPO LunarLander-v2 trained agent

PPO_89.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bdda432b6e12f327f0132ad79b97a66246b87dce003d7139a909ddfbdd311ba
+oid sha256:d6772eb45cc410c4d2bccc723170fcfa799ade9e101c228ea71004ee902fa390
 size 152858

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 285.50 +/- 17.24
+      value: 280.04 +/- 16.38
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 285.5025362, "std_reward": 17.24430217526403, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T14:52:32.486925"}
+{"mean_reward": 280.03691499999996, "std_reward": 16.38162947227475, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T14:52:49.514253"}