English

Online Linear Quadratic Control

Machine Learning 2018-06-20 v1 Machine Learning

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)O(\sqrt{T}) regret under mild assumptions, where TT 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.

Keywords

Cite

@article{arxiv.1806.07104,
  title  = {Online Linear Quadratic Control},
  author = {Alon Cohen and Avinatan Hassidim and Tomer Koren and Nevena Lazic and Yishay Mansour and Kunal Talwar},
  journal= {arXiv preprint arXiv:1806.07104},
  year   = {2018}
}
R2 v1 2026-06-23T02:34:21.348Z