Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 246.16 +/- 58.21
+      value: 257.36 +/- 15.51
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc7070429d711c397e52aeee5d137b7d4d8f1081f2dd663ab364558b5410264
+oid sha256:b7c086a02c0ea6d30635463f7049dabd7f648c4d07559c306abe9f49a1cc9165
 size 148088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b253b9dc456adbf6837b8713daca0de37a759dac18452407f80f3120d080360
-size 188958
+oid sha256:55c58fbb975e0d27b22b3ad6b5fb079b5b41deed9c088b247693e65478b1f036
+size 176916

results.json

@@ -1 +1 @@
-{"mean_reward": 246.1629595, "std_reward": 58.20703798005862, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-12T00:37:34.036932"}
+{"mean_reward": 257.359357, "std_reward": 15.50870029151756, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-12T00:42:47.977969"}