Online Control with Adversarial Disturbances
Abstract
We study the control of linear dynamical systems with adversarial disturbances, as opposed to statistical noise. We present an efficient algorithm that achieves nearly-tight regret bounds in this setting. Our result generalizes upon previous work in two main aspects: the algorithm can accommodate adversarial noise in the dynamics, and can handle general convex costs.
Cite
Text
Agarwal et al. "Online Control with Adversarial Disturbances." International Conference on Machine Learning, 2019.Markdown
[Agarwal et al. "Online Control with Adversarial Disturbances." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/agarwal2019icml-online/)BibTeX
@inproceedings{agarwal2019icml-online,
title = {{Online Control with Adversarial Disturbances}},
author = {Agarwal, Naman and Bullins, Brian and Hazan, Elad and Kakade, Sham and Singh, Karan},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {111-119},
volume = {97},
url = {https://mlanthology.org/icml/2019/agarwal2019icml-online/}
}