Multi-player Multi-Armed Bandits with non-zero rewards on collisions for uncoordinated spectrum access

10/21/2019
by   Akshayaa Magesh, et al.
0

In this paper, we study the uncoordinated spectrum access problem using the multi-player multi-armed bandits framework. We consider a model where there is no central control and the users cannot communicate with each other. The environment may appear differently to different users, i.e., the mean rewards as seen by different users for a particular channel may be different. Additionally, in case of a collision, we allow for the colliding users to receive non-zero rewards. With this setup, we present a policy that achieves expected regret of order O(log^2+δT) for some δ > 0.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2019

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

Multi-user multi-armed bandits have emerged as a good model for uncoordi...
research
07/02/2018

Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access

A stochastic multi-user multi-armed bandit framework is used to develop ...
research
01/12/2021

Dynamic Spectrum Access using Stochastic Multi-User Bandits

A stochastic multi-user multi-armed bandit framework is used to develop ...
research
12/13/2021

Stochastic differential equations for limiting description of UCB rule for Gaussian multi-armed bandits

We consider the upper confidence bound strategy for Gaussian multi-armed...
research
04/28/2022

Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms Applications

Multi-player multi-armed bandits (MMAB) study how decentralized players ...
research
10/08/2017

Using the Value of Information to Explore Stochastic, Discrete Multi-Armed Bandits

In this paper, we propose an information-theoretic exploration strategy ...
research
03/06/2020

Distributed Learning in Ad-Hoc Networks: A Multi-player Multi-armed Bandit Framework

Next-generation networks are expected to be ultra-dense with a very high...

Please sign up or login with your details

Forgot password? Click here to reset