"Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings"

This repository contains the LaTeX code of a research poster written by Lilian Besson and Remi Bonnefoi, entitled "Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings".


Setting up the future Internet of Things (IoT) networks will require to support more and more communicating devices. We prove that intelligent devices in unlicensed bands can use Multi-Armed Bandit (MAB) learning algorithms to improve resource exploitation. We evaluate the performance of two classical MAB learning algorithms, UCB1 and Thomson Sampling, to handle the decentralized decision-making of Spectrum Access, applied to IoT networks; as well as learning performance with a growing number of intelligent end-devices.

We show that using learning algorithms does help to fit more devices in such networks, even when all end-devices are intelligent and are dynamically changing channel. In the studied scenario, stochastic MAB learning provides a up to 16% gain in term of successful transmission probabilities, and has near optimal performance even in non-stationary and non-i.i.d. settings with a majority of intelligent devices.

Key words:

  • Internet of Things,
  • Multi-Armed Bandits,
  • Reinforcement Learning,
  • Cognitive Radio,
  • Non-Stationary Bandits.

Poster_JdD__Remi_Bonnefoi_and_Lilian_Besson__IoT_slotted.en.pdf as a PNG image


This poster is based on an article sent to the CrownCom 2017 conference on May 2017.

We presented this article to the CrownCom 2017 conference in September 2017. These slides (also in 4:3) were used to present the article at the conference.

We got the Best Paper Award for our article during the CrownCom 2017 conference!

Icons license

Some SVG or EPS icons used for the poster were obtained freely from the website (wifi-signal, old-typical-phone, smartphone), under the Creative Commons 3.0 License.


This poster was done for the PhD Student Day 2017, at IETR.

©, 2017, Rémi Bonnefoi & Lilian Besson (IETR, CentraleSupélec, SCEE Team).

<center><a title="Our poster as a PNG image, or a A0 PDF" href=""><img width="700px" src="Poster_JdDRemi_Bonnefoi_and_Lilian_BessonIoT_slotted.en.png" alt="Poster_JdDRemi_Bonnefoi_and_Lilian_BessonIoT_slotted.en.pdf"></a></center>

I (Lilian Besson) have started my PhD in October 2016, and this is a part of my on going research in 2017.

📜 License ?

This project is publicly published, under the terms of the MIT Licensed (file LICENSE).

Published Maintenance Ask Me Anything ! Analytics

ForTheBadge uses-badges ForTheBadge uses-git

made-with-latex ForTheBadge built-with-science