Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret

Alon Cohen, Tomer Koren, Yishay Mansour
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:1300-1309, 2019.

Abstract

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

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-cohen19b, title = {Learning Linear-Quadratic Regulators Efficiently with only $\sqrt{T}$ Regret}, author = {Cohen, Alon and Koren, Tomer and Mansour, Yishay}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {1300--1309}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/cohen19b/cohen19b.pdf}, url = {https://proceedings.mlr.press/v97/cohen19b.html}, abstract = {We present the first computationally-efficient algorithm with $\widetilde{O}(\sqrt{T})$ regret for learning in Linear Quadratic Control systems with unknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and Szepesvari (2011) and Dean,Mania, Matni, Recht, and Tu (2018).} }
Endnote
%0 Conference Paper %T Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret %A Alon Cohen %A Tomer Koren %A Yishay Mansour %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-cohen19b %I PMLR %P 1300--1309 %U https://proceedings.mlr.press/v97/cohen19b.html %V 97 %X We present the first computationally-efficient algorithm with $\widetilde{O}(\sqrt{T})$ regret for learning in Linear Quadratic Control systems with unknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and Szepesvari (2011) and Dean,Mania, Matni, Recht, and Tu (2018).
APA
Cohen, A., Koren, T. & Mansour, Y.. (2019). Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:1300-1309 Available from https://proceedings.mlr.press/v97/cohen19b.html.

Related Material