larger batch size

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 286.74 +/- 17.34
+      value: 286.48 +/- 15.61
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 286.74252650000005, "std_reward": 17.34352580372744, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-16T01:06:33.640723"}
+{"mean_reward": 286.4837183, "std_reward": 15.605217078312466, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-16T01:07:19.129690"}

zhiwei_ppo_m6.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b145b3e70ada888135cbd84a47de1b73d14f5d35da5502a92685af22fec606
+oid sha256:b19039386058bf922dd9ab9a6a3163d0b90eeffc3c8d9eaecd2393498df1298c
 size 153312