Online Control with Adversarial Disturbances

Authors:

Preprint

23 February 2019

preprint
Published by arXiv in arXiv

DOI:10.48550/arXiv.1902.08721

Abstract

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result is an efficient algorithm that provides nearly tight regret bounds for this problem. From a technical standpoint, this work generalizes upon previous work in two main aspects: our model allows for adversarial noise in the dynamics, and allows for general convex costs.

Keywords

All Related Versions

Version 1, 2019-02-23, ArXiv

This publication has 4 references indexed in Scilit:

A System-Level Approach to Controller Synthesis
IEEE Transactions on Automatic Control, 2019
Introduction to Online Convex Optimization
Foundations and Trends® in Optimization, 2016
Online Learning and Online Convex Optimization
Foundations and Trends in Machine Learning, 2012
Markov Decision Processes with Arbitrary Reward Processes
Mathematics of Operations Research, 2009