On the optimization dynamics of RLVR: Gradient gap and step size thresholds

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suk, Joe, Duan, Yaqi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Information Theory Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.08539