GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Zhengqing, Liu, Xinyang, Zhang, Yi, Guo, Fan, Jia, ChengXun, Wan, Junchen, Liu, Yao, Liu, Qi, Huang, Jihao, Song, Kang
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.06795