IT-Forum: On Optimal Solutions in Decentralized Control (Team) Problems

On Optimal Solutions in Decentralized Control (Team) Problems
Friday, January 30, 2015 - 1:00pm to Saturday, January 31, 2015 - 1:55pm
Packard 202
Abhishek Gupta (USC)
Abstract / Description: 

Recently, there has been a lot of work on decentralized control (team) problems -- problems in which multiple agents having different information act, perhaps in a dynamic environment, to minimize a common objective function. Such scenarios naturally occur, for example, in large-scale control systems, communication systems, organizations, and networks. However, very few team problems were known to admit optimal solutions.

In this talk, we discuss some recent results on this topic and show that a class of dynamic LQG teams with no observation sharing information structures admit team-optimal solutions. This result provides the first unified proof of existence of optimal solutions in several different classes of stochastic teams, including the celebrated Witsenhausen's counterexample, the Gaussian test channel, the Gaussian relay channel and their non-scalar extensions.

Abhishek Gupta is currently a postdoc at University of Southern California. He recently completed his PhD in Aerospace Engineering department from UIUC. He completed his B.Tech. in Aerospace Engineering from IIT Bombay, MS in Aerospace Engineering from UIUC and MS in Applied Mathematics from UIUC in 2009, 2011 and 2012, respectively. His research lies at the intersection of stochastic control theory, optimization, game theory, and information theory. He has received Kenneth Lee Herrick Memorial Award 2014 for outstanding research and academic performance from Aerospace Engineering Department at UIUC, Mavis Future Faculty Fellowship in 2012-2013 from the College of Engineering at UIUC, and Narotam Sekhsaria Excellence in Undergraduate award in 2009 for excellent all-round performance during undergraduate studies.