CNI Seminar Series

The Synergy Between Quality of Experience and Deep Reinforcement Learning for Uncoordinated Multi-Agent Resource Allocation in Cognitive Radio Network

Professor Andres Kwasinski, Professor, Rochester Institute of Technology, USA

#279
Slides
Abstract

The paradigm of a cognitive radio is that of a wireless device capable of autonomously learning to derive from observations awareness of the wireless environment state and adapt its resource allocation accordingly. Reinforcement Learning (RL) offers a natural framework for realizing this paradigm, but it faces the challenge of long learning times when the operating scenario is one where the cognitive radios operate in a fully distributed and uncoordinated fashion. One approach to accelerate learning is for those cognitive radios that have already learned a representation of the environment and the results of its actions, to transfer their experience to those cognitive radios that are joining the network and have not learned yet. However, the experience learned by one cognitive radio may not be useful for another because they may each be carrying vastly different types of traffic. In this talk, I will discuss how representing the effect of resource allocation using certain Quality of Experience metrics makes the experience learned by one cognitive radio be agnostic to the traffic type and can be shared to other radios even if they are servicing traffic of a different type. For this to be possible, the Quality of Experience metric needs to measure the perceived quality for different traffic using the same scale. The result is that cognitive radios joining the network can learn faster experiencing a negligible loss in Quality of Experience.


Bio
Professor Andres Kwasinski, Professor, Rochester Institute of Technology, USA

Andres Kwasinski is a Professor and Director of the Ph.D. program in Electrical and Computer Engineering at the Rochester Institute of Technology, Rochester, NY, USA. He has co-authored more than 110 peer-reviewed publications and four books published by Cambridge University Press and Wiley. His research interests include cognitive radios and wireless networks, cross-layer techniques in wireless communications, and smart infrastructures and networking. He currently serves on the Senior Editorial Board of the IEEE Signal Processing Magazine, where he has also been Area Editor and Associate Editor. He has previously served as an Editor for IEEE Transactions on Wireless Communications and IEEE Wireless Communications Letters. He received the Diploma in Electrical Engineering from the Buenos Aires Institute of Technology, Argentina, and the M.Sc. and Ph.D. degrees in Electrical and Computer Engineering from the University of Maryland, College Park, USA. Dr. Kwasinski is a Senior Member of the IEEE.