Skip to Main content Skip to Navigation
Conference papers

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.
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00752382
Contributor : Catherine Magnet <>
Submitted on : Thursday, November 15, 2012 - 3:37:17 PM
Last modification on : Wednesday, December 12, 2018 - 11:24:12 AM

Identifiers

Collections

Citation

M. Khan, Hamidou Tembine. Risk-sensitive Learners in Network Selection Games. 2012 International Conference on Wireless Communications and Signal Processing (WCSP) , Oct 2012, Huangshan city, Anhui Province, China. ⟨10.1109/WCSP.2012.6542987⟩. ⟨hal-00752382⟩

Share

Metrics

Record views

293