Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -342.14 +/- 173.35
+      value: -311.75 +/- 143.84
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8da2a488a140538b4e4f6f62a42335eb309a16d75ce5013f3b11f65eb625eb3
+oid sha256:886ea06e9beaa9b58d03e5049f54a7bf38ea5a941eecbf6316962a14dda5dcc8
 size 52946

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b686a83f4b525e9d1cd170fb8254e4573a003e0781a1d140bc73214e8474755d
+oid sha256:358df8bf7e78f5cb053f9222076ae752ae834d81c48e5b9c79877e38fd03b640
 size 43265

results.json

@@ -1 +1 @@
-{"mean_reward": -342.1406293726992, "std_reward": 173.34856210661187, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-21T13:23:40.564934"}
+{"mean_reward": -311.7473829105496, "std_reward": 143.83528969072057, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-21T14:18:04.141235"}