Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 283.85 +/- 23.12
+      value: 282.88 +/- 18.63
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621d04c8bd461093e2d050f2e980c7f957473ab98ecf9ef13fa90881bd4c939b
+oid sha256:0bde812ff6c255fd1e895dae8e043497cc0dfe3cc270227773591ce4997ccedd
 size 147973

results.json

@@ -1 +1 @@
-{"mean_reward": 283.8537876513256, "std_reward": 23.12059001312143, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-29T08:18:23.982918"}
+{"mean_reward": 282.8778042814974, "std_reward": 18.633460509097635, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-29T08:18:42.650349"}