Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret
Machine Learning
2019-02-26 v2 Machine Learning
Abstract
We present the first computationally-efficient algorithm with regret for learning in Linear Quadratic Control systems with unknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and Szepesv\'ari (2011) and Dean, Mania, Matni, Recht, and Tu (2018).
Keywords
Cite
@article{arxiv.1902.06223,
title = {Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret},
author = {Alon Cohen and Tomer Koren and Yishay Mansour},
journal= {arXiv preprint arXiv:1902.06223},
year = {2019}
}