Google Research

Learning Linear-Quadratic Regulators Efficiently with only √ T Regret

ICML (2019) (to appear)

Abstract

We present the first computationally-efficient algorithm with $\tO(\sqrt{T})$ regret for learning in Linear Quadratic Control systems with unknown linear dynamics and known quadratic costs.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work