TY - GEN
T1 - Learning pure-strategy Nash equilibria in networked multi-agent systems with uncertainty
AU - Eksin, Ceyhun
AU - Swenson, Brian
AU - Kar, Soummya
AU - Ribeiro, Alejandro
N1 - Funding Information:
The work of B. Swenson and S. Kar was supported in part by NSF grants CCF-1513936 and ECCS-1408222. The work of C. Eksin and A. Ribeiro was supported in part by the NSF award CAREER CCF-0952867 and the AFOSR MURI FA9550-10-1-0567
Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/27
Y1 - 2016/12/27
N2 - A multi-agent system with uncertainty entails a set of agents intent on maximizing their local utility functions that depend on the actions of other agents and a state of the world while having partial and different information about actions of other agents and the state of the world. When agents repeatedly have to make decisions in these settings, we propose a general class of decision-making dynamics based on the Fictitious Play (FP) algorithm with inertia. We show convergence of the proposed algorithm to pure Nash equilibria for the class of weakly acyclic games - a structural assumption on local utility functions that guarantees existence of pure Nash equilibria - as long as the predictions of the agents of their local utilities satisfy a mild asymptotic accuracy condition. Using the results on the general dynamics, the paper proposes distributed implementations of the FP algorithm with inertia suited for networked multi-agent systems and shows its convergence to pure Nash equilibria. Numerical examples corroborate the analysis providing insights to convergence time.
AB - A multi-agent system with uncertainty entails a set of agents intent on maximizing their local utility functions that depend on the actions of other agents and a state of the world while having partial and different information about actions of other agents and the state of the world. When agents repeatedly have to make decisions in these settings, we propose a general class of decision-making dynamics based on the Fictitious Play (FP) algorithm with inertia. We show convergence of the proposed algorithm to pure Nash equilibria for the class of weakly acyclic games - a structural assumption on local utility functions that guarantees existence of pure Nash equilibria - as long as the predictions of the agents of their local utilities satisfy a mild asymptotic accuracy condition. Using the results on the general dynamics, the paper proposes distributed implementations of the FP algorithm with inertia suited for networked multi-agent systems and shows its convergence to pure Nash equilibria. Numerical examples corroborate the analysis providing insights to convergence time.
UR - http://www.scopus.com/inward/record.url?scp=85010736853&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010736853&partnerID=8YFLogxK
U2 - 10.1109/CDC.2016.7799080
DO - 10.1109/CDC.2016.7799080
M3 - Conference contribution
AN - SCOPUS:85010736853
T3 - 2016 IEEE 55th Conference on Decision and Control, CDC 2016
SP - 5292
EP - 5297
BT - 2016 IEEE 55th Conference on Decision and Control, CDC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 55th IEEE Conference on Decision and Control, CDC 2016
Y2 - 12 December 2016 through 14 December 2016
ER -