Shuyao "Tim" Xu

icon indicating a website link tim-siu.github.io

icon company National University of Singapore icon location Singapore icon location ml enthusiast & typical cs student

Results 2 issues of Shuyao "Tim" Xu

Making Plugins (`mermaid`, `datatables`) Default

1 comment

### Please confirm that you have searched existing issues in the repo Yes, I have searched the existing issues ### Any related issues? _No response_ ### What is the area...

p.Medium
c.Feature 🚀
s.ToInvestigate

feat: optionally track other reward components

1 comment

## Motivation For R1 style of RL, there are many components of reward, like format score or reward score. It is currently not trivial to track different components. It is...