Premium
Distributed Nash equilibrium learning: A second‐order proximal algorithm
Author(s) -
Pan Wei,
Lu Yu,
Jia Zehua,
Zhang Weidong
Publication year - 2021
Publication title -
international journal of robust and nonlinear control
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.361
H-Index - 106
eISSN - 1099-1239
pISSN - 1049-8923
DOI - 10.1002/rnc.5618
Subject(s) - nash equilibrium , differentiable function , quadratic growth , convergence (economics) , order (exchange) , computer science , rate of convergence , mathematical optimization , selection (genetic algorithm) , epsilon equilibrium , algorithm , distributed algorithm , best response , mathematics , mathematical economics , artificial intelligence , distributed computing , pure mathematics , economics , computer network , channel (broadcasting) , finance , economic growth
This article addresses the distributed Nash equilibrium (NE) seeking problem for multiagent networked games with partial decision information. We employ a quadratically approximated alternating direction method of multipliers together with an augmented consensus procedure to compute the NE of games with twice differentiable cost functions. The resulting second‐order proximal algorithm enjoys relatively fast convergence rate and less burden on step size selection compared with the existing works. Numerical simulations are consistent with our theoretical analysis.