Update PPO LunarLander-v2 model with score 259.04 (Passes Unit 1 & Unit 8 PI)

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -42.45 +/- 215.78
+      value: 259.04 +/- 9.59
       name: mean_reward
       verified: false
 ---
@@ -28,7 +28,7 @@ This is a trained model of a PPO agent playing `LunarLander-v2` using Stable-Bas
 ## Evaluation Results
 
 - **Environment**: `LunarLander-v2`
-- **Mean Reward**: `-42.45 +/- 215.78`
+- **Mean Reward**: `259.04 +/- 9.59`
 
 ## Replay Video
 

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1cadb7117b9c3bf8fc0756af3aaea45ee4cf5bbb407c2cb8a3aa3fe98b635c
-size 149508
+oid sha256:f8588f47f48a5a59851b795e65765b0ed3afd732946cf64faaf0c2f7b4e866e3
+size 149920

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3588e56f34face11deb83f83f88d51f3d6f46472623e03e99668c4e411b291da
-size 146956
+oid sha256:6247ae5046f590ada7526f270b6606e290b73bb14db5f08f7942483fc1f951c5
+size 77166

results.json

@@ -1,7 +1,7 @@
 {
   "env_id": "LunarLander-v2",
-  "mean_reward": -42.44536319999999,
-  "std_reward": 215.78191500437535,
+  "mean_reward": 259.0360479,
+  "std_reward": 9.59261616485337,
   "n_evaluation_episodes": 10,
-  "eval_datetime": "2026-09-20T23:05:00"
+  "eval_datetime": "2026-09-20T23:30:00"
 }