P. R. Kumar
Texas A&M University
Title:Regret and Bandits
Abstract:We address the problem of achieving low "regret" in bandit problems.
We exhibit a policy that often appears to outperform Thompson Sampling,
apparently regarded currently as the best learning scheme.
[Joint work with Ping-Chun Hsieh and Xi Liu].
P. R. Kumar obtained his B.Tech. degree in Electrical Engineering (Electronics) from I.I.T. Madras in 1973, and the M.S. and D.Sc. degrees in Systems Science and Mathematics from Washington University, St. Louis in 1975 and 1977, respectively. From 1977-84, he was a faculty member in the Department of Mathematics at the University of Maryland Baltimore County. From 1985-2011, he was a faculty member in the Department of Electrical and Computer Engineering and the Coordinated Science Laboratory at the University of Illinois. Currently he is at Texas A&M University where he is a University Distinguished Professor, Regents Professor, and holds the College of Engineering Chair in Computer Engineering.