Upload PPO LunarLander-v2 trained agent, second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 244.96 +/- 14.75
+      value: 248.79 +/- 19.51
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65ab80782ad17f20ab2120a588ff3df5b32944c3cc616f75eb729ba60a573f4
+oid sha256:d9f6483e50fd379e6459878fa15cdf69d3372db468240add9abb794883388252
 size 148008

results.json

@@ -1 +1 @@
-{"mean_reward": 244.95828550000002, "std_reward": 14.75096006838728, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-06T16:52:05.694843"}
+{"mean_reward": 248.78875709999997, "std_reward": 19.505103552049484, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-06T16:54:51.121812"}