Achieving $\varepsilon^{-2}$ Dependence for Average-Reward Q-Learning with a New Contraction Principle

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Zijun, Chen, Zaiwei, Si, Nian, Wang, Shengbo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.21301