Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 258.15 +/- 22.25
+      value: 255.84 +/- 20.84
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f15500cf131e45ece7b1e3f4a20228df17f7fd930a3916a5de59c7b123dfb0d
+oid sha256:3784f8022be11e7c67c60aeacf97938bde15599c93f38c09f2e75bb994858318
 size 148016

results.json

@@ -1 +1 @@
-{"mean_reward": 258.1485528, "std_reward": 22.249821035244143, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-01T03:10:40.924359"}
+{"mean_reward": 255.84207749341036, "std_reward": 20.841539761305533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-01T03:12:46.460340"}