The multi-armed bandit with stochastic plays

Antoine Lesage-Landry; Joshua A. Taylor

doi:10.1109/TAC.2017.2765501

The multi-armed bandit with stochastic plays

Antoine Lesage-Landry, Joshua A. Taylor

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

We extend the stochastic multi-armed bandit to the case where the number of arms to play evolves as a stationary process. Our work is motivated by demand response in power systems, in which the number of arms to play, or loads to dispatch, depends on a random power imbalance. We give an upper confidence bound-based algorithm that achieves sublinear pseudo-regret. We apply our results in several examples from demand response.

Original language	English (US)
Pages (from-to)	2280-2286
Number of pages	7
Journal	IEEE Transactions on Automatic Control
Volume	63
Issue number	7
DOIs	https://doi.org/10.1109/TAC.2017.2765501
State	Published - Jul 2018
Externally published	Yes

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Keywords

Demand response
multi-armed bandit (MAB)
online learning
stochastic bandit

Access to Document

10.1109/TAC.2017.2765501

Cite this

@article{13019ea2b20b45fab14d7234150dabc7,

title = "The multi-armed bandit with stochastic plays",

abstract = "We extend the stochastic multi-armed bandit to the case where the number of arms to play evolves as a stationary process. Our work is motivated by demand response in power systems, in which the number of arms to play, or loads to dispatch, depends on a random power imbalance. We give an upper confidence bound-based algorithm that achieves sublinear pseudo-regret. We apply our results in several examples from demand response.",

keywords = "Demand response, multi-armed bandit (MAB), online learning, stochastic bandit",

author = "Antoine Lesage-Landry and Taylor, \{Joshua A.\}",

note = "Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",

year = "2018",

month = jul,

doi = "10.1109/TAC.2017.2765501",

language = "English (US)",

volume = "63",

pages = "2280--2286",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "7",

}

TY - JOUR

T1 - The multi-armed bandit with stochastic plays

AU - Lesage-Landry, Antoine

AU - Taylor, Joshua A.

PY - 2018/7

Y1 - 2018/7

N2 - We extend the stochastic multi-armed bandit to the case where the number of arms to play evolves as a stationary process. Our work is motivated by demand response in power systems, in which the number of arms to play, or loads to dispatch, depends on a random power imbalance. We give an upper confidence bound-based algorithm that achieves sublinear pseudo-regret. We apply our results in several examples from demand response.

AB - We extend the stochastic multi-armed bandit to the case where the number of arms to play evolves as a stationary process. Our work is motivated by demand response in power systems, in which the number of arms to play, or loads to dispatch, depends on a random power imbalance. We give an upper confidence bound-based algorithm that achieves sublinear pseudo-regret. We apply our results in several examples from demand response.

KW - Demand response

KW - multi-armed bandit (MAB)

KW - online learning

KW - stochastic bandit

UR - https://www.scopus.com/pages/publications/85032703487

UR - https://www.scopus.com/inward/citedby.url?scp=85032703487&partnerID=8YFLogxK

U2 - 10.1109/TAC.2017.2765501

DO - 10.1109/TAC.2017.2765501

M3 - Article

AN - SCOPUS:85032703487

SN - 0018-9286

VL - 63

SP - 2280

EP - 2286

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 7

ER -

The multi-armed bandit with stochastic plays

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this