Imperial College London
Portrait Picture

ProfessorDenizGunduz

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor in Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6218d.gunduz Website

 
 
//

Assistant

 

Ms Joan O'Brien +44 (0)20 7594 6316

 
//

Location

 

1016Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Tung:2021:10.1109/JSAC.2021.3087248,
author = {Tung, T-Y and Kobus, S and Roig, JP and Gunduz, D},
doi = {10.1109/JSAC.2021.3087248},
journal = {IEEE Journal on Selected Areas in Communications},
pages = {2590--2603},
title = {Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels},
url = {http://dx.doi.org/10.1109/JSAC.2021.3087248},
volume = {39},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We propose a novel formulation of the “effectivenessproblem” in communications, put forth by Shannon and Weaverin their seminal work “The Mathematical Theory of Communication”, by considering multiple agents communicating overa noisy channel in order to achieve better coordination andcooperation in a multi-agent reinforcement learning (MARL)framework. Specifically, we consider a multi-agent partiallyobservable Markov decision process (MA-POMDP), in which theagents, in addition to interacting with the environment, can alsocommunicate with each other over a noisy communication channel. The noisy communication channel is considered explicitlyas part of the dynamics of the environment, and the messageeach agent sends is part of the action that the agent can take.As a result, the agents learn not only to collaborate with eachother but also to communicate “effectively” over a noisy channel.This framework generalizes both the traditional communicationproblem, where the main goal is to convey a message reliably overa noisy channel, and the “learning to communicate” frameworkthat has received recent attention in the MARL literature, wherethe underlying communication channels are assumed to be errorfree. We show via examples that the joint policy learned using theproposed framework is superior to that where the communicationis considered separately from the underlying MA-POMDP. Thisis a very powerful framework, which has many real worldapplications, from autonomous vehicle planning to drone swarmcontrol, and opens up the rich toolbox of deep reinforcementlearning for the design of multi-user communication systems.
AU  - Tung,T-Y
AU  - Kobus,S
AU  - Roig,JP
AU  - Gunduz,D
DO  - 10.1109/JSAC.2021.3087248
EP  - 2603
PY  - 2021///
SN  - 0733-8716
SP  - 2590
TI  - Effective Communications: A Joint Learning and Communication Framework for Multi-Agent Reinforcement Learning Over Noisy Channels
T2  - IEEE Journal on Selected Areas in Communications
UR  - http://dx.doi.org/10.1109/JSAC.2021.3087248
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000673624000024&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/9466501
UR  - http://hdl.handle.net/10044/1/92931
VL  - 39
ER  -
Download