Show mean +/- std in evaluation results for hdppo-InvertedPendulum-v5

README.md

@@ -18,7 +18,7 @@ model-index:
       type: InvertedPendulum-v5
     metrics:
     - type: mean_reward
-      value: 1000.00
+      value: 1000.00 +/- 0.00
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ Published by [LTU-AI](https://huggingface.co/LTU-AI).
 3. Fine-tune each pruned checkpoint with PPO.
 
 Published checkpoint: seed **123**, compact **D=64** model
-(held-out eval mean reward **1000.00**).
+(held-out eval mean reward **1000.00 ± 0.00**).
 
 ## Usage