Regret of exploratory policy improvement and $q$-learning

Wenpin Tang; Xun Yu Zhou

Regret of exploratory policy improvement and $q$-learning

Machine Learning 2024-11-05 v1 Optimization and Control Probability

Authors: Wenpin Tang , Xun Yu Zhou

Abstract

We study the convergence of $q$ -learning and related algorithms introduced by Jia and Zhou (J. Mach. Learn. Res., 24 (2023), 161) for controlled diffusion processes. Under suitable conditions on the growth and regularity of the model parameters, we provide a quantitative error and regret analysis of both the exploratory policy improvement algorithm and the $q$ -learning algorithm.

Keywords

q-learning exploratory policy improvement controlled diffusion processes regret analysis convergence reinforcement learning

Cite

@article{arxiv.2411.01302,
  title  = {Regret of exploratory policy improvement and $q$-learning},
  author = {Wenpin Tang and Xun Yu Zhou},
  journal= {arXiv preprint arXiv:2411.01302},
  year   = {2024}
}

Comments

23 pages, 1 figure

Related papers

View all related →