A mean field LQG game with soft-constrained disturbance as an adversarial player

Jianhui Huang; Minyi Huang

doi:10.1109/CDC.2015.7402910

A mean field LQG game with soft-constrained disturbance as an adversarial player

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

This paper considers a class of mean field linear-quadratic-Gaussian (LQG) games with model uncertainty. The drift term in the dynamics of the agents contains a common unknown function. We take a robust optimization approach where a representative agent in the limiting model views the drift uncertainty as an adversarial player. By incorporating the temporal evolution of the mean field in an augmented state space, we solve two optimal control problems sequentially subject to a consistency requirement for the mean field approximation. A set of decentralized control strategies is obtained as a robust e -Nash equilibrium.

Original language	English
Title of host publication	54rd IEEE Conference on Decision and Control,CDC 2015
Publisher	IEEE
Pages	4424-4429
Number of pages	6
Volume	54rd IEEE Conference on Decision and Control,CDC 2015
ISBN (Electronic)	9781479978861
DOIs	https://doi.org/10.1109/CDC.2015.7402910
Publication status	Published - 8 Feb 2015
Event	54th IEEE Conference on Decision and Control, CDC 2015 - Osaka International Convention Center (Grand Cube), Osaka, Japan Duration: 15 Dec 2015 → 18 Dec 2015

Conference

Conference	54th IEEE Conference on Decision and Control, CDC 2015
Country/Territory	Japan
City	Osaka
Period	15/12/15 → 18/12/15

ASJC Scopus subject areas

Control and Systems Engineering
Modelling and Simulation
Control and Optimization

More information

10.1109/CDC.2015.7402910

Cite this

@inproceedings{e0135e0b053948929b89f45aea4daf0e,

title = "A mean field LQG game with soft-constrained disturbance as an adversarial player",

abstract = "This paper considers a class of mean field linear-quadratic-Gaussian (LQG) games with model uncertainty. The drift term in the dynamics of the agents contains a common unknown function. We take a robust optimization approach where a representative agent in the limiting model views the drift uncertainty as an adversarial player. By incorporating the temporal evolution of the mean field in an augmented state space, we solve two optimal control problems sequentially subject to a consistency requirement for the mean field approximation. A set of decentralized control strategies is obtained as a robust e -Nash equilibrium.",

author = "Jianhui Huang and Minyi Huang",

year = "2015",

month = feb,

day = "8",

doi = "10.1109/CDC.2015.7402910",

language = "English",

volume = "54rd IEEE Conference on Decision and Control,CDC 2015",

pages = "4424--4429",

booktitle = "54rd IEEE Conference on Decision and Control,CDC 2015",

publisher = "IEEE",

address = "United States",

note = "54th IEEE Conference on Decision and Control, CDC 2015 ; Conference date: 15-12-2015 Through 18-12-2015",

}

Huang, J & Huang, M 2015, A mean field LQG game with soft-constrained disturbance as an adversarial player. in 54rd IEEE Conference on Decision and Control,CDC 2015. vol. 54rd IEEE Conference on Decision and Control,CDC 2015, 7402910, IEEE, pp. 4424-4429, 54th IEEE Conference on Decision and Control, CDC 2015, Osaka, Japan, 15/12/15. https://doi.org/10.1109/CDC.2015.7402910

A mean field LQG game with soft-constrained disturbance as an adversarial player. / Huang, Jianhui; Huang, Minyi.
54rd IEEE Conference on Decision and Control,CDC 2015. Vol. 54rd IEEE Conference on Decision and Control,CDC 2015 IEEE, 2015. p. 4424-4429 7402910.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A mean field LQG game with soft-constrained disturbance as an adversarial player

AU - Huang, Jianhui

AU - Huang, Minyi

PY - 2015/2/8

Y1 - 2015/2/8

N2 - This paper considers a class of mean field linear-quadratic-Gaussian (LQG) games with model uncertainty. The drift term in the dynamics of the agents contains a common unknown function. We take a robust optimization approach where a representative agent in the limiting model views the drift uncertainty as an adversarial player. By incorporating the temporal evolution of the mean field in an augmented state space, we solve two optimal control problems sequentially subject to a consistency requirement for the mean field approximation. A set of decentralized control strategies is obtained as a robust e -Nash equilibrium.

AB - This paper considers a class of mean field linear-quadratic-Gaussian (LQG) games with model uncertainty. The drift term in the dynamics of the agents contains a common unknown function. We take a robust optimization approach where a representative agent in the limiting model views the drift uncertainty as an adversarial player. By incorporating the temporal evolution of the mean field in an augmented state space, we solve two optimal control problems sequentially subject to a consistency requirement for the mean field approximation. A set of decentralized control strategies is obtained as a robust e -Nash equilibrium.

UR - http://www.scopus.com/inward/record.url?scp=84962003990&partnerID=8YFLogxK

U2 - 10.1109/CDC.2015.7402910

DO - 10.1109/CDC.2015.7402910

M3 - Conference article published in proceeding or book

VL - 54rd IEEE Conference on Decision and Control,CDC 2015

SP - 4424

EP - 4429

BT - 54rd IEEE Conference on Decision and Control,CDC 2015

PB - IEEE

T2 - 54th IEEE Conference on Decision and Control, CDC 2015

Y2 - 15 December 2015 through 18 December 2015

ER -

A mean field LQG game with soft-constrained disturbance as an adversarial player

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this