PPO LunarLander-v2 trained agent - batchsize 32, total_timestaps 4M

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 275.93 +/- 15.81
+      value: 285.18 +/- 16.31
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b68f70dda1ed38cf6724ee1dc5772a124199d1488091169e2b0d702688d70902
+oid sha256:d0141657f1c97ee69885229d75bbf221ad929200c671cb9305be1669ab0f4214
 size 147475

results.json

@@ -1 +1 @@
-{"mean_reward": 275.92717039999997, "std_reward": 15.81227977362359, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-19T17:01:02.929586"}
+{"mean_reward": 285.1838499, "std_reward": 16.308912752536944, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-19T17:08:59.648468"}