Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 149.59 +/- 93.91
+      value: 72.18 +/- 118.58
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90cb960e66005b914159c77d2ab6b15fd819dd9642a04db066879c474e52e723
+oid sha256:edaf39b916f33fdf6e8f2b1848682230c1668c7936c8bbc671aaee9eae0a3323
 size 148122

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111ee55be1d24c8f2803e44be54a85101ce4dd4a6e23946bf35ed240b6f1ac12
-size 164837
+oid sha256:195c1076ac4925086a0c6dfd35e90fe524925e0a8e59313c53bc57133d1c624c
+size 177121

results.json

@@ -1 +1 @@
-{"mean_reward": 149.5858824, "std_reward": 93.90819732089352, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-13T16:06:09.842464"}
+{"mean_reward": 72.1773290435829, "std_reward": 118.58399838816939, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-13T16:11:06.226911"}