Distributed stochastic subgradient-free algorithm for Nash equilibrium seeking in two-network zero-sum games

TL;DR

This paper introduces a distributed stochastic subgradient-free algorithm for two-network zero-sum games with unknown local cost functions, ensuring convergence to the Nash equilibrium neighborhood under unbalanced directed graphs.

Contribution

It develops a novel subgradient-free approach for Nash equilibrium seeking in complex networked zero-sum games with unknown costs and directed interactions.

Findings

Algorithm guarantees almost sure convergence to the Nash equilibrium neighborhood.

Neighborhood size can be arbitrarily small with proper parameter tuning.

Numerical simulations validate the theoretical convergence results.

Abstract

This paper investigates the distributed Nash equilibrium seeking problem for two-network zero-sum games with set constraints, where the two networks have the opposite nonsmooth cost functions. The interaction of the agents in each network is characterized by an unbalanced directed graph. We are particularly interested in the case that the local cost function of each agent in the two networks is unknown in this paper. We first construct the stochastic subgradient-free two-variable oracles based on the measurements of the local cost functions. Instead of using subgradients of the local cost functions, the subgradient-free two-variable oracles are employed to design the distributed algorithm for the agents to search the Nash equilibrium. Under the strong connectivity assumption, it is shown that the proposed algorithm guarantees that the states of all the agents converge almost surely to the neighborhood of the Nash equilibrium, where the scale of the neighborhood can be arbitrarily small by selecting suitable smooth parameter in the oracles. Numerical simulations are finally given to validate the theoretical results.