Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access
This addresses spectrum allocation for wireless networks, but it is incremental as it builds on existing bandit models with user-dependent rewards.
The paper tackles the problem of uncoordinated spectrum access in multi-user multi-armed bandits where users cannot communicate and perceive different rewards for the same channels, presenting a policy that achieves O(log T) regret.
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.