Learning Linear-Quadratic Regulators Efficiently with Only $\sqrt{T}$ Regret

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

Text

Cohen et al. "Learning Linear-Quadratic Regulators Efficiently with Only $\sqrt{T}$ Regret." International Conference on Machine Learning, 2019.

Markdown

[Cohen et al. "Learning Linear-Quadratic Regulators Efficiently with Only $\sqrt{T}$ Regret." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/cohen2019icml-learning/)

BibTeX

@inproceedings{cohen2019icml-learning,
  title     = {{Learning Linear-Quadratic Regulators Efficiently with Only $\sqrt{T}$ Regret}},
  author    = {Cohen, Alon and Koren, Tomer and Mansour, Yishay},
  booktitle = {International Conference on Machine Learning},
  year      = {2019},
  pages     = {1300-1309},
  volume    = {97},
  url       = {https://mlanthology.org/icml/2019/cohen2019icml-learning/}
}