CSEE Seminar Series - Reinforcement Learning and its Applications in Self-reconfigurable Access Designs

  • Wed 24 Jan 18

    16:00 - 17:30

  • Colchester Campus


  • Event speaker

    Dr. Mahsa Derakhshani

  • Event type

    Lectures, talks and seminars
    CSEE Seminar Series

  • Event organiser

    Computer Science and Electronic Engineering, School of

  • Contact details

This research illustrates how reinforcement learning is conducive to more intelligent future wireless network designs. More precisely, future wireless networks must competently accommodate to strict quality-of-service (QoS) requirements of a massive number of connections by managing limited resources in real-time. These networks, therefore, need self-reconfigurable access designs that quickly adapt to the network status.

Such designs could be realized by employing suitable learning techniques in medium access design and radio resource management. Reinforcement learning is one such technique, as it is achieved through an ongoing trial-and-error interaction with a dynamic environment, managing a continuing trade-off between exploration and exploitation. In this talk, I will model some network design challenges as multi-armed bandit problems, introduce reinforcement learning algorithms, illustrate how such models apply to medium access designs in wireless communication networks, and discuss the performance evaluation criteria for these algorithms. 

Bio: Dr. Mahsa Derakhshani is a Lecturer (Assistant Professor) in Digital Communications with the Wolfson School of Mechanical, Electrical and Manufacturing Engineering, Loughborough University, UK. Prior to joining Lboro, she was an Honorary NSERC Postdoctoral Fellow with Department of Electrical and Electronic Engineering, Imperial College London (2015 to 2016), a Postdoctoral Research Fellow with the Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada and a Research Assistant with the Department of Electrical and Computer Engineering, McGill University (2013 to 2015). She received her Ph.D. in electrical engineering degree from McGill University, Montréal, Canada, in 2013. Her research interests include radio resource management for wireless networks, software-defined wireless networking, applications of convex optimization and game theory for communication systems, and spectrum sensing techniques in cognitive radio networks. Dr. Derakhshani has received several awards and fellowships including the John Bonsall Porter Prize, the McGill Engineering Doctoral Award, the Fonds de Recherche du Québec–Nature et Technologies (FRQNT) and Natural Sciences and Engineering Research Council of Canada (NSERC) Postdoctoral Fellowships. Currently, she serves as an Associate Editor of the IET Signal Processing Journal.