A discrete-time averaging theorem and its application to zeroth-order Nash equilibrium seeking

TL;DR

This paper introduces a multi-timescale averaging theorem for discrete-time systems and applies it to develop and analyze zeroth-order Nash equilibrium seeking algorithms, demonstrating their convergence in multi-agent systems.

Contribution

The paper presents a novel multi-timescale averaging theorem for discrete-time systems and applies it to establish convergence of zeroth-order Nash equilibrium algorithms.

Findings

Proved semi-global practical convergence of the zeroth-order pseudogradient descent algorithm.

Established convergence of asynchronous pseudogradient descent in unconstrained problems.

Demonstrated application to connectivity control in multi-agent systems.

Abstract

In this paper we present an averaging technique applicable to the design of zeroth-order Nash equilibrium seeking algorithms. First, we propose a multi-timescale discrete-time averaging theorem that requires only that the equilibrium is semi-globally practically stabilized by the averaged system, while also allowing the averaged system to depend on ``fast" states. Furthermore, sequential application of the theorem is possible, which enables its use for multi-layer algorithm design. Second, we apply the aforementioned averaging theorem to prove semi-global practical convergence of the zeroth-order information variant of the discrete-time projected pseudogradient descent algorithm, in the context of strongly monotone, constrained Nash equilibrium problems. Third, we use the averaging theory to prove the semi-global practical convergence of the asynchronous pseudogradient descent algorithm to solve strongly monotone unconstrained Nash equilibrium problems. Lastly, we apply the proposed asynchronous algorithm to the connectivity control problem in multi-agent systems.