Multi-user lax communications: a multi-armed bandit approach

TL;DR

This paper addresses a multi-user multi-armed bandit problem inspired by cognitive radio networks, proposing a distributed learning algorithm to achieve stable channel allocations with minimal communication, backed by theoretical guarantees and experiments.

Contribution

It introduces a novel distributed algorithm for multi-user MABs that ensures convergence to stable configurations without central control or extensive communication.

Findings

The algorithm converges to stable channel allocations.

Performance is comparable or superior to existing algorithms.

The approach is validated through experiments inspired by real networks.

Abstract

Inspired by cognitive radio networks, we consider a setting where multiple users share several channels modeled as a multi-user multi-armed bandit (MAB) problem. The characteristics of each channel are unknown and are different for each user. Each user can choose between the channels, but her success depends on the particular channel chosen as well as on the selections of other users: if two users select the same channel their messages collide and none of them manages to send any data. Our setting is fully distributed, so there is no central control. As in many communication systems, the users cannot set up a direct communication protocol, so information exchange must be limited to a minimum. We develop an algorithm for learning a stable configuration for the multi-user MAB problem. We further offer both convergence guarantees and experiments inspired by real communication networks, including comparison to state-of-the-art algorithms.