Online linear quadratic control

A. Cohen, A. Hassidim, T. Koren, N. Lazic, Y. Mansour, K. Talwar

Research output: Working paperPreprint

Abstract

We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee O(T−−√) regret under mild assumptions, where T is the time horizon. Our algorithms rely on a novel SDP relaxation for the steady-state distribution of the system. Crucially, and in contrast to previously proposed relaxations, the feasible solutions of our SDP all correspond to "strongly stable" policies that mix exponentially fast to a steady state.
Original languageEnglish
Number of pages22
Volume7104
DOIs
StatePublished - 19 Jun 2018

Publication series

NamearXiv preprint arXiv:1806.,

Fingerprint

Dive into the research topics of 'Online linear quadratic control'. Together they form a unique fingerprint.

Cite this