Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Xingyu, Wen, Yilin, Wang, En, Su, Du, Liu, Wenbin, Bao, Chenfu, Lv, Zhonghou
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.09369