Upload a test PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 175.79 +/- 103.31
+      value: 248.17 +/- 28.46
       name: mean_reward
       verified: false
 ---

ppo_lunarlander_unit1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1c07d3608c54ea4594037f62a8498272443f8038c6ed670b6719a6d83bd1db
+oid sha256:f6a8b1bf9cdb223fea46527c801c9c7ac49d9f481ba54c473235e107a1fdf3ae
 size 146063

results.json

@@ -1 +1 @@
-{"mean_reward": 175.79372061606796, "std_reward": 103.30922067688482, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-27T10:22:56.925276"}
+{"mean_reward": 248.16570526306168, "std_reward": 28.46294444588795, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-27T10:27:39.234470"}