Distributed Solving Exact Potential Games via Differential Inclusions and Consensus Algorithms
Chương V. Nguyen, Hyo‐Sung Ahn · 2018
This paper presents a number of ideas combining consensus algorithms and differential inclusions to effectively solve exact potential games with continuous strategy space in a multi-agent network. Solving these games or finding their Nash equilibrium (NE) is conducted in a distributed manner via the forms of two interconnected subsystems, the first one estimating necessary information by average consensus algorithm, and another using differential inclusion to seek NE with respect to distributed constraints on players' actions. Firstly, a special form of exact potential games is considered. Secondly, larger potential games are taken into consideration. It is shown that designed dynamical systems are semi-practically globally asymptotically stable (SPA), enabling players' actions to converge to NE non-locally. Two simulations on an energy network and on a cognitive radio network (CRN) are carried out to investigate the correctness of our algorithms.