Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Hongyi, Ye, Kai, Xu, Erhan, Zhu, Jin, Yang, Ying, Gong, Shijin, Shi, Chengchun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.01162