English

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 O~(T)\widetilde O(\sqrt{T}) 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}
}
R2 v1 2026-06-23T07:42:54.612Z