BAYESIAN QUADRATIC NETWORK GAME FILTERS Conference Paper

abstract

• A repeated network game where agents' utilities depend on information and payoff externalities is considered. Agents play Bayesian Nash Equilibrium strategies with respect to their beliefs on the state of the world and the actions of all other nodes in the network. These beliefs are refined over subsequent stages based on the observed actions of neighboring peers. This paper introduces the Quadratic Network Game (QNG) filter that agents can run locally to update their beliefs, select corresponding optimal actions, and eventually learn a sufficient statistic of the network's state. The QNG filter is demonstrated on a coordination game. 2013 IEEE.

name of conference

• 2013 IEEE International Conference on Acoustics, Speech and Signal Processing

authors

• Eksin, Ceyhun

published proceedings

• 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)

author list (cited authors)

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

citation count

• 6

complete list of authors

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

publication date

• May 2013

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing / sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society. ICASSP (Conference)  Journal

keywords

• Bayesian Nash Equilibrium
• Distributed Signal Processing
• Linear Filtering
• Network Games

Digital Object Identifier (DOI)

• 10.1109/icassp.2013.6638529

International Standard Book Number (ISBN) 13

• 9781479903566

start page

• 4589

end page

• 4593

URL

• http://dx.doi.org/10.1109/icassp.2013.6638529