Distributed convergence to Nash equilibria in two-network zero-sum games

TL;DR

This paper develops distributed algorithms for two-network zero-sum games where agents with limited information aim to reach Nash equilibria, proving convergence under undirected and directed network topologies.

Contribution

It introduces novel distributed saddle-point strategies for zero-sum games with partial information, ensuring convergence in undirected and directed network settings.

Findings

Convergence of the proposed dynamics in undirected networks for strictly concave-convex functions.

Non-convergence in general directed networks without modification.

A generalized dynamics that converges in directed networks for differentiable functions.

Abstract

This paper considers a class of strategic scenarios in which two networks of agents have opposing objectives with regards to the optimization of a common objective function. In the resulting zero-sum game, individual agents collaborate with neighbors in their respective network and have only partial knowledge of the state of the agents in the other network. For the case when the interaction topology of each network is undirected, we synthesize a distributed saddle-point strategy and establish its convergence to the Nash equilibrium for the class of strictly concave-convex and locally Lipschitz objective functions. We also show that this dynamics does not converge in general if the topologies are directed. This justifies the introduction, in the directed case, of a generalization of this distributed dynamics which we show converges to the Nash equilibrium for the class of strictly concave-convex differentiable functions with locally Lipschitz gradients. The technical approach combines tools from algebraic graph theory, nonsmooth analysis, set-valued dynamical systems, and game theory.