Online Control with Adversarial Disturbances

Naman Agarwal, Brian Bullins, Elad Hazan, Sham Kakade, Karan Singh
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:111-119, 2019.

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 this Paper


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.} }
Endnote
%0 Conference Paper %T Online Control with Adversarial Disturbances %A Naman Agarwal %A Brian Bullins %A Elad Hazan %A Sham Kakade %A Karan Singh %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-agarwal19c %I PMLR %P 111--119 %U https://proceedings.mlr.press/v97/agarwal19c.html %V 97 %X 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.
APA
Agarwal, N., Bullins, B., Hazan, E., Kakade, S. & Singh, K.. (2019). Online Control with Adversarial Disturbances. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:111-119 Available from https://proceedings.mlr.press/v97/agarwal19c.html.

Related Material