Wireless service providers learn to compete using shared spectrum
Learning Market Competition in Shared Spectrum: A Multi-Agent Reinforcement Learning Approach
Computer Science and Game Theory
Summary
Wireless companies share a common range of airwaves to offer services, but the demand from customers is not always known in advance. The authors look at how these companies can use a type of machine learning called multi-agent reinforcement learning to figure out customer demand over time and decide how to compete either by setting prices or by controlling the number of customers served. They also study whether these learning companies might end up acting like a team and avoid competition, which could affect market fairness. Their work helps explain how learning and competition interact in wireless markets that share limited spectrum.
What this means in practice
- •For wireless network operators: Improve pricing and service strategies by adapting to unknown customer demand in shared spectrum environments.
- •For telecommunications regulators: Monitor and design policies that anticipate potential collusion among learning-based competitors in shared wireless markets.
Authors
Qixuan Zai, Randall Berry
Abstract
This paper investigates market competition among wireless service providers (SPs) that serve customers using shared spectrum. Prior work has analyzed such markets through models of competition with congestible resources, capturing both the congestion-sensitive nature of wireless spectrum and the effects of spectrum sharing on service quality. These models typically assume that the market demand function is known, enabling SPs to optimize pricing or quantity decisions under either Bertrand or Cournot competition. In contrast, we consider a setting in which the demand function is initially unknown and must be learned over time. We model this learning process using multi-agent reinforcement learning (MARL), allowing competing SPs to learn market dynamics while adapting their competitive strategies. Although MARL has shown strong performance in a variety of economic settings, recent work has demonstrated that it can also give rise to tacit collusion among self-interested agents. We therefore examine whether similar collusive behavior emerges in shared-spectrum markets and how its prevalence depends on the mode of competition (price versus quantity) and the choice of MARL algorithm. Our results provide insight into the interaction between learning dynamics, market structure, and spectrum sharing, with implications for both wireless market design and the deployment of learning-enabled decision-making systems.