Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 202.98 +/- 89.94
+      value: 257.50 +/- 11.50
       name: mean_reward
       verified: false
 ---

ppo_lunar_lander_v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ffd7a3f9b5a5be6f73d6d4d0ef52b093260c8920ed635a5c60952250466654
+oid sha256:0200037fc63a8224e54290867ee33441e49c47e09545648340b783da8dc89a20
 size 151625

results.json

@@ -1 +1 @@
-{"mean_reward": 202.97571219999998, "std_reward": 89.94443313584303, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T20:56:24.228012"}
+{"mean_reward": 257.4987474, "std_reward": 11.498480918490374, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-16T20:57:55.324876"}