Learning Linear-Quadratic Regulators Efficiently with only √(T) Regret

02/17/2019

∙

by   Alon Cohen, et al.

∙

0

∙

share

We present the first computationally-efficient algorithm with O(√(T)) regret for learning in Linear Quadratic Control systems with unknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and Szepesvári (2011) and Dean, Mania, Matni, Recht, and Tu (2018).