Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access

TL;DR

This paper introduces a policy for multi-user multi-armed bandits in uncoordinated spectrum access, accounting for user-specific rewards and no communication, achieving logarithmic regret.

Contribution

It proposes a novel policy for multi-user MABs with user-dependent rewards in uncoordinated environments, ensuring efficient spectrum access.

Findings

Achieves $O(\log T)$ regret in the considered setting

Handles user-specific reward variations across channels

Applicable to uncoordinated spectrum access scenarios

Abstract

Multi-user multi-armed bandits have emerged as a good model for uncoordinated spectrum access problems. In this paper we consider the scenario where users cannot communicate with each other. In addition, the environment may appear differently to different users, ${i.e.}$, the mean rewards as observed by different users for the same channel may be different. With this setup, we present a policy that achieves a regret of $O (\log{T})$. This paper has been accepted at Asilomar Conference on Signals, Systems, and Computers 2019.