Learning linear-quadratic regulators efficiently with only √T regret

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present the first computationally-efficient algorithm with Õ(√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).

Original languageEnglish
Title of host publication36th International Conference on Machine Learning, ICML 2019
Pages2313-2322
Number of pages10
ISBN (Electronic)9781510886988
StatePublished - 2019
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: 9 Jun 201915 Jun 2019

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach
Period9/06/1915/06/19

All Science Journal Classification (ASJC) codes

  • Education
  • Computer Science Applications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Learning linear-quadratic regulators efficiently with only √T regret'. Together they form a unique fingerprint.

Cite this