Model-free adaptive learning solutions for discrete-time dynamic graphical games

Mohammed I. Abouheaf; Frank L. Lewis; Magdi S. Mahmoud

doi:10.1109/CDC.2014.7039945

Model-free adaptive learning solutions for discrete-time dynamic graphical games

Mohammed I. Abouheaf, Frank L. Lewis, Magdi S. Mahmoud

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

9 Scopus citations

Abstract

This paper introduces novel model-free adaptive learning algorithm to solve the dynamic graphical games in real-time. It allows online model-free tuning of the controller and critic networks. This algorithm solves the dynamic graphical game in a distributed fashion. Novel coupled Bellman equations and Hamiltonian functions are developed for the dynamic graphical games. Nash solution for the dynamic graphical game is given in terms of the solution to a set of coupled Hamilton-Jacobi-Bellman equations developed herein. An online model-free policy iteration algorithm is developed to learn the Nash solution for the dynamic graphical game in real-time. A proof of convergence for this algorithm is given under mild assumptions about the inter-connectivity properties of the graph.

Original language	English
Title of host publication	53rd IEEE Conference on Decision and Control,CDC 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3578-3583
Number of pages	6
Edition	February
ISBN (Electronic)	9781479977468
DOIs	https://doi.org/10.1109/CDC.2014.7039945
State	Published - 2014

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
Number	February
Volume	2015-February
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

ASJC Scopus subject areas

Control and Systems Engineering
Modeling and Simulation
Control and Optimization

Access to Document

10.1109/CDC.2014.7039945

Cite this

Abouheaf, M. I., Lewis, F. L., & Mahmoud, M. S. (2014). Model-free adaptive learning solutions for discrete-time dynamic graphical games. In 53rd IEEE Conference on Decision and Control,CDC 2014 (February ed., pp. 3578-3583). Article 7039945 (Proceedings of the IEEE Conference on Decision and Control; Vol. 2015-February, No. February). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CDC.2014.7039945

@inproceedings{8c7d3a1d13714f6eba51d7a601f756ac,

title = "Model-free adaptive learning solutions for discrete-time dynamic graphical games",

abstract = "This paper introduces novel model-free adaptive learning algorithm to solve the dynamic graphical games in real-time. It allows online model-free tuning of the controller and critic networks. This algorithm solves the dynamic graphical game in a distributed fashion. Novel coupled Bellman equations and Hamiltonian functions are developed for the dynamic graphical games. Nash solution for the dynamic graphical game is given in terms of the solution to a set of coupled Hamilton-Jacobi-Bellman equations developed herein. An online model-free policy iteration algorithm is developed to learn the Nash solution for the dynamic graphical game in real-time. A proof of convergence for this algorithm is given under mild assumptions about the inter-connectivity properties of the graph.",

author = "Abouheaf, {Mohammed I.} and Lewis, {Frank L.} and Mahmoud, {Magdi S.}",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",

year = "2014",

doi = "10.1109/CDC.2014.7039945",

language = "English",

series = "Proceedings of the IEEE Conference on Decision and Control",

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

number = "February",

pages = "3578--3583",

booktitle = "53rd IEEE Conference on Decision and Control,CDC 2014",

address = "United States",

edition = "February",

}

Abouheaf, MI, Lewis, FL & Mahmoud, MS 2014, Model-free adaptive learning solutions for discrete-time dynamic graphical games. in 53rd IEEE Conference on Decision and Control,CDC 2014. February edn, 7039945, Proceedings of the IEEE Conference on Decision and Control, no. February, vol. 2015-February, Institute of Electrical and Electronics Engineers Inc., pp. 3578-3583. https://doi.org/10.1109/CDC.2014.7039945

Model-free adaptive learning solutions for discrete-time dynamic graphical games. / Abouheaf, Mohammed I.; Lewis, Frank L.; Mahmoud, Magdi S.
53rd IEEE Conference on Decision and Control,CDC 2014. February. ed. Institute of Electrical and Electronics Engineers Inc., 2014. p. 3578-3583 7039945 (Proceedings of the IEEE Conference on Decision and Control; Vol. 2015-February, No. February).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Model-free adaptive learning solutions for discrete-time dynamic graphical games

AU - Abouheaf, Mohammed I.

AU - Lewis, Frank L.

AU - Mahmoud, Magdi S.

PY - 2014

Y1 - 2014

N2 - This paper introduces novel model-free adaptive learning algorithm to solve the dynamic graphical games in real-time. It allows online model-free tuning of the controller and critic networks. This algorithm solves the dynamic graphical game in a distributed fashion. Novel coupled Bellman equations and Hamiltonian functions are developed for the dynamic graphical games. Nash solution for the dynamic graphical game is given in terms of the solution to a set of coupled Hamilton-Jacobi-Bellman equations developed herein. An online model-free policy iteration algorithm is developed to learn the Nash solution for the dynamic graphical game in real-time. A proof of convergence for this algorithm is given under mild assumptions about the inter-connectivity properties of the graph.

AB - This paper introduces novel model-free adaptive learning algorithm to solve the dynamic graphical games in real-time. It allows online model-free tuning of the controller and critic networks. This algorithm solves the dynamic graphical game in a distributed fashion. Novel coupled Bellman equations and Hamiltonian functions are developed for the dynamic graphical games. Nash solution for the dynamic graphical game is given in terms of the solution to a set of coupled Hamilton-Jacobi-Bellman equations developed herein. An online model-free policy iteration algorithm is developed to learn the Nash solution for the dynamic graphical game in real-time. A proof of convergence for this algorithm is given under mild assumptions about the inter-connectivity properties of the graph.

UR - http://www.scopus.com/inward/record.url?scp=84988267432&partnerID=8YFLogxK

U2 - 10.1109/CDC.2014.7039945

DO - 10.1109/CDC.2014.7039945

M3 - Conference contribution

AN - SCOPUS:84988267432

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 3578

EP - 3583

BT - 53rd IEEE Conference on Decision and Control,CDC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Abouheaf MI, Lewis FL, Mahmoud MS. Model-free adaptive learning solutions for discrete-time dynamic graphical games. In 53rd IEEE Conference on Decision and Control,CDC 2014. February ed. Institute of Electrical and Electronics Engineers Inc. 2014. p. 3578-3583. 7039945. (Proceedings of the IEEE Conference on Decision and Control; February). doi: 10.1109/CDC.2014.7039945

Model-free adaptive learning solutions for discrete-time dynamic graphical games

Abstract

Publication series

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this