Colloquium
10/14/2009 02:00 pm
CoRE B (Room 305)

Of sheep, wolves and reinforcement learning

Michael Kaisers, Maastricht University, Netherlands

Faculty Host: Michael Littman

Abstract

What happens when you isolate a number of wolves and sheep on an island, and what does their co-evolution have to do with learning? Recently, an interesting connection has been established, allowing to interpret learning as an evolution of ideas in the mind.

This talk will outline my research interests and give an overview over my specific perspective on reinforcement learning.

Bio

Michael Kaisers graduated from Maastricht with a B. Sc. in Knowledge Engineering in 2007, and a M. Sc. in Artificial Intelligence in 2008. In both cases, he earned the honor summa cum laude, additionally abbreviating his three-years bachelor program to two years, and complementing his master program by an extra-curricular four-month research visit to Simon Parsons at Brooklyn College, New York City.

The Netherlands Organization for Scientific Research (NWO) selected him and 47 other candidates in a nationwide competition to be awarded a TopTalent 2008 grant for a Ph. D. program of four years. In September 2008, he commenced his position at Eindhoven University of Technology. Since August 2009, the project is continued at Maastricht University.

Print Login