Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 242.54 +/- 35.56
+      value: 251.92 +/- 14.66
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8449b63477d53bb860a664c59a6a01986bd914e9339b6cd59ed4ab64bc14a89
+oid sha256:ac61b03d92ce378b39eba90494a526f0ce49bd53c44a6d1c122fdac7adcb1ff1
 size 148243

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ba52cf3aa9889eb6f9725a77af2e99f509242fb30f8a3c1e14d1da02bd0e30
+size 160059

results.json

@@ -1 +1 @@
-{"mean_reward": 242.53654549999996, "std_reward": 35.558835666377924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-05T17:42:53.729369"}
+{"mean_reward": 251.92263029999998, "std_reward": 14.659753103699453, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-05T17:47:05.921113"}