Risk-sensitive learners in network selection games

Manzoor Ahmed Khan, Tembine Hamidou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider a network with finite number of users where each user observes only a numerical value of its measurement. The system is interactive in the sense that each user's payoff is affected by the environment state and the choices of all the other users. This scenario can be modeled as dynamic robust game. We examine how risk-sensitive learners influence the convergence time of such a game in a specific network selection problem. Based on imitative combined fully distributed payoff and strategy learning (CODIPAS), we provide a simple class of network selection games in which a convergence to global optimum can be obtained with a very fast convergence rate. We show that the risk-sensitive index can be used to improve the convergence time in a wide range of parameters.

Original languageEnglish (US)
Title of host publication2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012
DOIs
StatePublished - Dec 1 2012
Event2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012 - Huangshan, China
Duration: Oct 25 2012Oct 27 2012

Other

Other2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012
CountryChina
CityHuangshan
Period10/25/1210/27/12

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Khan, M. A., & Hamidou, T. (2012). Risk-sensitive learners in network selection games. In 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012 [6542987] https://doi.org/10.1109/WCSP.2012.6542987

Risk-sensitive learners in network selection games. / Khan, Manzoor Ahmed; Hamidou, Tembine.

2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012. 2012. 6542987.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Khan, MA & Hamidou, T 2012, Risk-sensitive learners in network selection games. in 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012., 6542987, 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012, Huangshan, China, 10/25/12. https://doi.org/10.1109/WCSP.2012.6542987
Khan MA, Hamidou T. Risk-sensitive learners in network selection games. In 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012. 2012. 6542987 https://doi.org/10.1109/WCSP.2012.6542987
Khan, Manzoor Ahmed ; Hamidou, Tembine. / Risk-sensitive learners in network selection games. 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012. 2012.
@inproceedings{06096da481e24277bc67e2feae3baa49,
title = "Risk-sensitive learners in network selection games",
abstract = "We consider a network with finite number of users where each user observes only a numerical value of its measurement. The system is interactive in the sense that each user's payoff is affected by the environment state and the choices of all the other users. This scenario can be modeled as dynamic robust game. We examine how risk-sensitive learners influence the convergence time of such a game in a specific network selection problem. Based on imitative combined fully distributed payoff and strategy learning (CODIPAS), we provide a simple class of network selection games in which a convergence to global optimum can be obtained with a very fast convergence rate. We show that the risk-sensitive index can be used to improve the convergence time in a wide range of parameters.",
author = "Khan, {Manzoor Ahmed} and Tembine Hamidou",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/WCSP.2012.6542987",
language = "English (US)",
isbn = "9781467358293",
booktitle = "2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012",

}

TY - GEN

T1 - Risk-sensitive learners in network selection games

AU - Khan, Manzoor Ahmed

AU - Hamidou, Tembine

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We consider a network with finite number of users where each user observes only a numerical value of its measurement. The system is interactive in the sense that each user's payoff is affected by the environment state and the choices of all the other users. This scenario can be modeled as dynamic robust game. We examine how risk-sensitive learners influence the convergence time of such a game in a specific network selection problem. Based on imitative combined fully distributed payoff and strategy learning (CODIPAS), we provide a simple class of network selection games in which a convergence to global optimum can be obtained with a very fast convergence rate. We show that the risk-sensitive index can be used to improve the convergence time in a wide range of parameters.

AB - We consider a network with finite number of users where each user observes only a numerical value of its measurement. The system is interactive in the sense that each user's payoff is affected by the environment state and the choices of all the other users. This scenario can be modeled as dynamic robust game. We examine how risk-sensitive learners influence the convergence time of such a game in a specific network selection problem. Based on imitative combined fully distributed payoff and strategy learning (CODIPAS), we provide a simple class of network selection games in which a convergence to global optimum can be obtained with a very fast convergence rate. We show that the risk-sensitive index can be used to improve the convergence time in a wide range of parameters.

UR - http://www.scopus.com/inward/record.url?scp=84881083502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881083502&partnerID=8YFLogxK

U2 - 10.1109/WCSP.2012.6542987

DO - 10.1109/WCSP.2012.6542987

M3 - Conference contribution

AN - SCOPUS:84881083502

SN - 9781467358293

BT - 2012 International Conference on Wireless Communications and Signal Processing, WCSP 2012

ER -