Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 196.71 +/- 90.11
+      value: 238.20 +/- 34.18
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e76612a3e24cb022504173b3c676911210da5c3985addde57e9d0e01fa9ff07
+oid sha256:8c54afc6f6458d0bb32a71eb6b0026ece22c099854324cec79e9b70fec734341
 size 146087

results.json

@@ -1 +1 @@
-{"mean_reward": 196.7140179, "std_reward": 90.11244903556265, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T07:18:12.243982"}
+{"mean_reward": 238.2036837, "std_reward": 34.178097588621306, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T07:18:25.447133"}