Updated to use rgb_array for rendering

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.95 +/- 47.46
+      value: 249.90 +/- 40.15
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae26c09dda08f7602ffed589c0d5ba5b0687f2dfd5326c309475d40eca552493
+oid sha256:8f5859f93192d3f2088a78db41792ddece9182442f700dfa751054b182f78a3c
 size 148046

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f5eb0e38a39d5df63fff354e2d9e124a963a7d2657a6413562360023639af7
-size 149389
+oid sha256:14f99bb3ede82c63c645a259d43a18db2170b5c4db5f14f8dbab78b9909c7901
+size 142446

results.json

@@ -1 +1 @@
-{"mean_reward": 247.94878250000002, "std_reward": 47.46329812302868, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-25T13:29:46.632694"}
+{"mean_reward": 249.89852419999997, "std_reward": 40.14933016536234, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-25T13:34:42.388508"}