Upload net=[256,128,64] + activation=ReLU PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 279.76 +/- 10.57
+      value: 293.80 +/- 18.03
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b2a32a265856f028d09e75609afd37abcd049851801ad783c3fd4ab4ea3386
+oid sha256:d278e36ef421df3c342f33439265836fe14e8dcc57213c6a7d9f1023b9108393
 size 1082141

results.json

@@ -1 +1 @@
-{"mean_reward": 279.76286229999994, "std_reward": 10.57049708834404, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-04T16:30:13.254983"}
+{"mean_reward": 293.798772, "std_reward": 18.02840668399752, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-04T16:30:58.089215"}