Second try - changes parameters: n_steps = 2048, batch_size = 128

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 275.53 +/- 24.59
+      value: 284.30 +/- 17.28
       name: mean_reward
       verified: false
 ---

ppo-lunal-lander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09919f880289586a9111838fe0128f42713521db9c61a07dc3726d7af73d9b0
+oid sha256:663bd3bf61c380c0db73d6c8160e822d4da199deb0b779bc215511fe634e569d
 size 147263

results.json

@@ -1 +1 @@
-{"mean_reward": 275.53159336867094, "std_reward": 24.58920158714459, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T23:38:19.728729"}
+{"mean_reward": 284.2997220133261, "std_reward": 17.281453080910197, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T23:38:45.167616"}