Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.34 +/- 21.41
+      value: 244.98 +/- 25.38
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef77b8f03673c15646bdfcd646d1dc66490771708ebdbf66c100bf5f7a5cd74
+oid sha256:d96d3c318fa34d3804fc55b02516bac19a07090b1b8385ccec72c9411f5affeb
 size 148068

results.json

@@ -1 +1 @@
-{"mean_reward": 247.33899929187282, "std_reward": 21.410916032262286, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-05T18:33:47.100730"}
+{"mean_reward": 244.9764334234883, "std_reward": 25.37887436580225, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-05T18:34:09.741349"}