PPO LunarLander-v2 trained agent

PPO_70.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2435040dfe51ca853344a761bb68ce4a96041eab3ad4e59b7cb2b82bfbfafe6
+oid sha256:03d91ef07d6ee165ba26b2f8dd6f902cdecb661f73e493045d4e6e1b87dcd1c7
 size 150928

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 285.50 +/- 19.26
+      value: 279.69 +/- 24.73
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 285.50088300000004, "std_reward": 19.260808570194975, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:05:06.621618"}
+{"mean_reward": 279.689702, "std_reward": 24.734429131477857, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:05:21.979555"}