Research Article
Performance and Convergence of Multi-user Online Learning
@INPROCEEDINGS{10.1007/978-3-642-30373-9_23, author={Cem Tekin and Mingyan Liu}, title={Performance and Convergence of Multi-user Online Learning}, proceedings={Game Theory for Networks. 2nd International ICST Conference, GAMENETS 2011, Shanghai, China, April 16-18, 2011, Revised Selected Papers}, proceedings_a={GAMENETS}, year={2012}, month={10}, keywords={multi-user learning multi-armed bandits spectrum sharing congestion games}, doi={10.1007/978-3-642-30373-9_23} }- Cem Tekin
Mingyan Liu
Year: 2012
Performance and Convergence of Multi-user Online Learning
GAMENETS
Springer
DOI: 10.1007/978-3-642-30373-9_23
Abstract
We study the problem of allocating multiple users to a set of wireless channels in a decentralized manner when the channel qualities are time-varying and unknown to the users, and accessing the same channel by multiple users leads to reduced quality due to interference. In such a setting the users not only need to learn the inherent channel quality and at the same time the best allocations of users to channels so as to maximize the social welfare. Assuming that the users adopt a certain online learning algorithm, we investigate under what conditions the socially optimal allocation is achievable. In particular we examine the effect of different levels of knowledge the users may have and the amount of communications and cooperation. The general conclusion is that when the cooperation of users decreases and the uncertainty about channel payoffs increases it becomes harder to achieve the socially optimal allocation.