TY - GEN

T1 - Learning in linear games over networks

AU - Eksin, Ceyhun

AU - Molavi, Pooya

AU - Ribeiro, Alejandro

AU - Jadbabaie, Ali

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We consider a dynamic game over a network with information externalities. Agents' payoffs depend on an unknown true state of the world and actions of everyone else in the network; therefore, the interactions between agents are strategic. Each agent has a private initial piece of information about the underlying state and repeatedly observes actions of her neighbors. We consider strictly concave and supermodular utility functions that exhibit a quadratic form. We analyze the asymptotic behavior of agents' expected utilities in a connected network when it is common knowledge that the agents are myopic and rational. When utility functions are symmetric and adhere to the diagonal dominance criterion, each agent believes that the limit strategies of her neighbors yield the same payoff as her own limit strategy. Given a connected network, this yields a consensus in the actions of agents in the limit. We demonstrate our results using examples from technological and social settings.

AB - We consider a dynamic game over a network with information externalities. Agents' payoffs depend on an unknown true state of the world and actions of everyone else in the network; therefore, the interactions between agents are strategic. Each agent has a private initial piece of information about the underlying state and repeatedly observes actions of her neighbors. We consider strictly concave and supermodular utility functions that exhibit a quadratic form. We analyze the asymptotic behavior of agents' expected utilities in a connected network when it is common knowledge that the agents are myopic and rational. When utility functions are symmetric and adhere to the diagonal dominance criterion, each agent believes that the limit strategies of her neighbors yield the same payoff as her own limit strategy. Given a connected network, this yields a consensus in the actions of agents in the limit. We demonstrate our results using examples from technological and social settings.

UR - http://www.scopus.com/inward/record.url?scp=84875701149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875701149&partnerID=8YFLogxK

U2 - 10.1109/Allerton.2012.6483250

DO - 10.1109/Allerton.2012.6483250

M3 - Conference contribution

AN - SCOPUS:84875701149

SN - 9781467345385

T3 - 2012 50th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2012

SP - 434

EP - 440

BT - 2012 50th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2012

T2 - 2012 50th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2012

Y2 - 1 October 2012 through 5 October 2012

ER -