 |
In December, ECE Ph.D. student Anup Menon was one of four student finalists for the best paper award at the 2013 IEEE Conference on Decision and Control in Florence, Italy.
His paper, ?A Distributed Learning Algorithm with Bit-valued Communications for Multi-agent Welfare Optimization,? was inspired by recent work on learning in repeated games. The paper describes an algorithm that helps individual agents in an engineered multi-agent system "learn" to pick actions that correspond to a system-level (global) desirable outcome (welfare optimal). The algorithm is model free and the agents change their actions only on the basis of their observed individual payoffs/utility. It's proved that convergence is guaranteed so long as the union of implicit communications (an agent observing a change in its utility due to a change in another agents' actions) and explicit communications satisfy certain connectivity properties.
An earlier version of the paper was one of five finalists for the best student paper award at the 2013 American Control Conference. Menon is advised by Professor John Baras (ECE/ISR).
Related Articles:
Work on RIS-aided mmWave beamforming named a ‘best paper’
ArtIAMAS receives third-year funding of up to $15.1M
Alum Sidiropoulos receives three IEEE Signal Processing Society awards
New ECE/ISR assistant professor wins award for dissertation
Kaiqing Zhang joins ECE and ISR as a joint appointment faculty member
Grad student Usman Fiaz wins Pelczar Award
Alum Dipankar Maity joins ECE faculty at University of North Carolina Charlotte
Nuno Martins, alum Shinkyu Park and Jeff Shamma lead tutorial session at IEEE CDC 2019
Ulukus, colleagues win Best Tutorial Paper Award
Ye, Barg win IEEE Data Storage Best Paper Award
January 8, 2014
|
