Bayesian quadratic network game filters

Ceyhun Eksin, Pooya Molavi, Alejandro Ribeiro, Ali Jadbabaie

Research output: Contribution to journalArticlepeer-review

11 Scopus citations

Abstract

A repeated network game where agents have quadratic utilities that depend on information externalities-an unknown underlying state-as well as payoff externalities-the actions of all other agents in the network-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 Cournot market competition game and a coordination game to implement navigation of an autonomous team.

Original languageEnglish (US)
Article number6750770
Pages (from-to)2250-2264
Number of pages15
JournalIEEE Transactions on Signal Processing
Volume62
Issue number9
DOIs
StatePublished - May 1 2014

Keywords

  • Repeated Bayesian games
  • learning in networks
  • linear quadratic Gaussian games

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Bayesian quadratic network game filters'. Together they form a unique fingerprint.

Cite this