First sweep attempt short eval

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 283.07 +/- 14.97
+      value: 292.08 +/- 20.17
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-sweep.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0f82b4406138f2746653db9aaaa5a266c061701eed8859a90a45cf2496f4eed
+oid sha256:ca92e443317abfe9476ddce17d2588b1dd9ac3151bce6a961547ec03afacb3ab
 size 148250

results.json

@@ -1 +1 @@
-{"mean_reward": 283.07210018586136, "std_reward": 14.973740225593376, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-09T15:14:35.143553"}
+{"mean_reward": 292.08445072440014, "std_reward": 20.17281109333919, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-09T15:38:52.154091"}