Home > Research > Publications & Outputs > Mixed-strategy learning with continuous action ...

Electronic data

  • PerkinsMertikopoulosLeslie15

    Rights statement: ©2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE."

    Accepted author manuscript, 277 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

  • 07364177

    Rights statement: ©2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Final published version, 323 KB, PDF document

    Available under license: CC BY

Links

Text available via DOI:

View graph of relations

Mixed-strategy learning with continuous action sets

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Mixed-strategy learning with continuous action sets. / Perkins, Steven ; Mertikopoulos, Panayotis; Leslie, David Stuart.

In: IEEE Transactions on Automatic Control, Vol. 62, No. 1, 01.2017, p. 379-384.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Perkins, S, Mertikopoulos, P & Leslie, DS 2017, 'Mixed-strategy learning with continuous action sets', IEEE Transactions on Automatic Control, vol. 62, no. 1, pp. 379-384. https://doi.org/10.1109/TAC.2015.2511930

APA

Perkins, S., Mertikopoulos, P., & Leslie, D. S. (2017). Mixed-strategy learning with continuous action sets. IEEE Transactions on Automatic Control, 62(1), 379-384. https://doi.org/10.1109/TAC.2015.2511930

Vancouver

Perkins S, Mertikopoulos P, Leslie DS. Mixed-strategy learning with continuous action sets. IEEE Transactions on Automatic Control. 2017 Jan;62(1):379-384. https://doi.org/10.1109/TAC.2015.2511930

Author

Perkins, Steven ; Mertikopoulos, Panayotis ; Leslie, David Stuart. / Mixed-strategy learning with continuous action sets. In: IEEE Transactions on Automatic Control. 2017 ; Vol. 62, No. 1. pp. 379-384.

Bibtex

@article{3442224f82c24e38a07ce4647de2e727,
title = "Mixed-strategy learning with continuous action sets",
abstract = "Motivated by the recent applications of game-theoretical learning to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets. We propose an actor-critic reinforcement learning algorithm that adapts mixed strategies over continuous action spaces. To analyse the algorithm we extend the theory of finite-dimensional two-timescale stochastic approximation to a Banach space setting, and prove that the continuous dynamics of the process converge to equilibrium in the case of potential games. These results combine to give a provablyconvergent learning algorithm in which players do not need to keep track of the controls selected by other agents.",
author = "Steven Perkins and Panayotis Mertikopoulos and Leslie, {David Stuart}",
note = "{\textcopyright}2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",
year = "2017",
month = jan,
doi = "10.1109/TAC.2015.2511930",
language = "English",
volume = "62",
pages = "379--384",
journal = "IEEE Transactions on Automatic Control",
issn = "0018-9286",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

RIS

TY - JOUR

T1 - Mixed-strategy learning with continuous action sets

AU - Perkins, Steven

AU - Mertikopoulos, Panayotis

AU - Leslie, David Stuart

N1 - ©2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2017/1

Y1 - 2017/1

N2 - Motivated by the recent applications of game-theoretical learning to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets. We propose an actor-critic reinforcement learning algorithm that adapts mixed strategies over continuous action spaces. To analyse the algorithm we extend the theory of finite-dimensional two-timescale stochastic approximation to a Banach space setting, and prove that the continuous dynamics of the process converge to equilibrium in the case of potential games. These results combine to give a provablyconvergent learning algorithm in which players do not need to keep track of the controls selected by other agents.

AB - Motivated by the recent applications of game-theoretical learning to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets. We propose an actor-critic reinforcement learning algorithm that adapts mixed strategies over continuous action spaces. To analyse the algorithm we extend the theory of finite-dimensional two-timescale stochastic approximation to a Banach space setting, and prove that the continuous dynamics of the process converge to equilibrium in the case of potential games. These results combine to give a provablyconvergent learning algorithm in which players do not need to keep track of the controls selected by other agents.

U2 - 10.1109/TAC.2015.2511930

DO - 10.1109/TAC.2015.2511930

M3 - Journal article

VL - 62

SP - 379

EP - 384

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

SN - 0018-9286

IS - 1

ER -