Just run more epochs

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 253.30 +/- 56.30
+      value: 284.62 +/- 13.62
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c7ba824da59ca422308d364c745e09bd0f387846df56bf9cf8f6e2c47580cb
+oid sha256:30897cdb33167a4985b5999f75b9fff1f2132da12fa66ed388b5e261e5be5372
 size 147599

results.json

@@ -1 +1 @@
-{"mean_reward": 253.304826, "std_reward": 56.300143237495156, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-25T11:45:44.320094"}
+{"mean_reward": 284.6211254, "std_reward": 13.619079990372382, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-25T11:55:17.434714"}