DISTRIBUTED FILTERS FOR BAYESIAN NETWORK GAMES Conference Paper

abstract

• We consider a repeated network game where agents' utilities are quadratic functions of the state of the world and actions of all the agents. The state of the world is represented by a vector on which agents receive private signals with Gaussian noise. We define the solution concept as Bayesian Nash equilibrium and present a recursion to compute equilibrium strategies locally if an equilibrium exists at all stages. We further provide conditions under which a unique equilibrium exists. We conclude with an example of the proposed recursion in a repeated Cournot competition game and discuss properties of convergence such as efficient learning and convergence rate. 2013 EURASIP.

authors

• Eksin, Ceyhun

published proceedings

• 2013 PROCEEDINGS OF THE 21ST EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO)

author list (cited authors)

• Eksin, C., Molavi, P., Ribeiro, A., & Jadbabaie, A.

complete list of authors

• Eksin, Ceyhun||Molavi, Pooya||Ribeiro, Alejandro||Jadbabaie, Ali

publication date

• January 2013

published in

• European Signal Processing Conference  Journal

keywords

• Bayesian Learning
• Distributed Algorithms
• Repeated Network Games

International Standard Book Number (ISBN) 13

• 9780992862602