Stochastic Learning in Potential Games: Communication and Payoff-Based Approaches

TL;DR

This paper explores stochastic learning algorithms for potential games, focusing on communication-based and payoff-based methods, to ensure convergence to local maxima in multi-agent systems with different information access levels.

Contribution

It introduces novel stochastic algorithms for potential game learning under two information settings, extending convergence guarantees to non-convex optimization scenarios.

Findings

Algorithms converge to local maxima of the potential function.

Effective in systems with limited information exchange.

Applicable to non-convex optimization problems.

Abstract

Game theory serves as a powerful tool for distributed optimization in multi-agent systems in different applications. In this paper we consider multi-agent systems that can be modeled by means of potential games whose potential function coincides with a global objective function to be maximized. In this approach, the agents correspond to the strategic decision makers and the optimization problem is equivalent to the problem of learning a potential function maximizer in the designed game. The paper deals with two different information settings in the system. Firstly, we consider systems, where agents have the access to the gradient of their utility functions. However, they do not possess the full information about the joint actions. Thus, to be able to move along the gradient toward a local optimum, they need to exchange the information with their neighbors by means of communication. The second setting refers to a payoff-based approach to learning potential function maximizers. Here, we assume that at each iteration agents can only observe their own played actions and experienced payoffs. In both cases, the paper studies unconstrained non-convex optimization with a differentiable objective function. To develop the corresponding algorithms guaranteeing convergence to a local maximum of the potential function in the game, we utilize the idea of the well-known Robbins-Monro procedure based on the theory of stochastic approximation.