Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 236.59 +/- 15.58
+      value: 260.51 +/- 16.80
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b143c8904f726d37b1a73de9f3869202ff12ba5a766a67eb635a4779aa840b
+oid sha256:1f590eda811e357e0d16ffcf282728d1c107a14a0dd8b71e4a8b5262fdab31a7
 size 146750

results.json

@@ -1 +1 @@
-{"mean_reward": 236.5855244933254, "std_reward": 15.581478621429941, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-22T01:06:49.983643"}
+{"mean_reward": 260.5076970526176, "std_reward": 16.80262961533891, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-22T01:07:26.908247"}