Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Xuerui, Xie, Shufang, Liu, Guoqing, Xia, Yingce, Luo, Renqian, Jin, Peiran, Ma, Zhiming, Wang, Yue, Wang, Zun, Liu, Yuting
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2504.04524