Multi-user Communication Networks: A Coordinated Multi-armed Bandit Approach
This addresses resource sharing in communication networks for multiple users, offering a novel coordination method with broad applicability but incremental improvements over existing bandit techniques.
The paper tackles the problem of multi-user communication networks by developing a coordinated multi-armed bandit approach that learns unknown network characteristics and minimizes coordination overhead, achieving convergence to stable resource allocations with analytic guarantees and outperforming state-of-the-art methods in experiments.
Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other users while keeping coordination overhead to a minimum. The proposed solution combines Multi-Armed Bandit learning with a lightweight signalling-based coordination scheme, and ensures convergence to a stable allocation of resources. Our work considers single-user level algorithms for two scenarios: an unknown fixed number of users, and a dynamic number of users. Analytic performance guarantees, proving convergence to stable marriage configurations, are presented for both setups. The algorithms are designed based on a system-wide perspective, rather than focusing on single user welfare. Thus, maximal resource utilization is ensured. An extensive experimental analysis covers convergence to a stable configuration as well as reward maximization. Experiments are carried out over a wide range of setups, demonstrating the advantages of our approach over existing state-of-the-art methods.