Boosting for Control of Dynamical Systems

Naman Agarwal; Nataly Brukhim; Elad Hazan; Zhou Lu

Boosting for Control of Dynamical Systems

Naman Agarwal
, Nataly Brukhim
, Elad Hazan
, Zhou Lu

Research output: Contribution to journal › Conference article › peer-review

Abstract

We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.

Original language	English (US)
Pages (from-to)	96-103
Number of pages	8
Journal	Proceedings of Machine Learning Research
Volume	119
State	Published - 2020
Event	37th International Conference on Machine Learning, ICML 2020 - Virtual, Online Duration: Jul 13 2020 → Jul 18 2020

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Statistics and Probability
Artificial Intelligence

Cite this

@article{ee3e2024b0424ae58f6fe13f31bce49c,

title = "Boosting for Control of Dynamical Systems",

abstract = "We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.",

author = "Naman Agarwal and Nataly Brukhim and Elad Hazan and Zhou Lu",

note = "Publisher Copyright: {\textcopyright} 2020 by the author(s).; 37th International Conference on Machine Learning, ICML 2020 ; Conference date: 13-07-2020 Through 18-07-2020",

year = "2020",

language = "English (US)",

volume = "119",

pages = "96--103",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Boosting for Control of Dynamical Systems

AU - Agarwal, Naman

AU - Brukhim, Nataly

AU - Hazan, Elad

AU - Lu, Zhou

PY - 2020

Y1 - 2020

N2 - We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.

AB - We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.

UR - https://www.scopus.com/pages/publications/105021325411

UR - https://www.scopus.com/pages/publications/105021325411#tab=citedBy

M3 - Conference article

AN - SCOPUS:105021325411

SN - 2640-3498

VL - 119

SP - 96

EP - 103

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 37th International Conference on Machine Learning, ICML 2020

Y2 - 13 July 2020 through 18 July 2020

ER -

Boosting for Control of Dynamical Systems

Abstract

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this