A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lei, Shiye, Cheng, Zhihao, Tao, Dacheng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.22718