On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Wenhao, Xie, Yuexiang, Sun, Yuchang, Chen, Yanxi, Wang, Guoyin, Li, Yaliang, Ding, Bolin, Zhou, Jingren
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/2508.11408