Unit1 trained Agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 254.19 +/- 23.91
+      value: 252.93 +/- 15.51
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486af39ab56417dd078a0342f3eba1749f035edd44fb9212475de499b1830f3f
+oid sha256:ad0f095de44ece9b948769d7c0b35018737f831f49e0a1bc3e8a973f5fed77ab
 size 150006

results.json

@@ -1 +1 @@
-{"mean_reward": 254.19099999999997, "std_reward": 23.907868594472195, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T22:40:38.117653"}
+{"mean_reward": 252.92815480000004, "std_reward": 15.51306802149321, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T22:41:40.992725"}