ICML 2019oral280 citations
Online Control with Adversarial Disturbances
Naman Agarwal, Brian Bullins, Elad Hazan, Sham Kakade, Karan Singh
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.
BibTeX
@InProceedings{pmlr-v97-agarwal19c,
title = {Online Control with Adversarial Disturbances},
author = {Agarwal, Naman and Bullins, Brian and Hazan, Elad and Kakade, Sham and Singh, Karan},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {111--119},
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/agarwal19c/agarwal19c.pdf},
url = {https://proceedings.mlr.press/v97/agarwal19c.html},
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.}
}