I am an assistant professor at the Informatics Institute at the University of Amsterdam, in the Intelligent Autonomous Systems group.  My research is primarily focused on single- and multi-agent decision-theoretic planning and learning, especially reinforcement learning, though I am also interested in stochastic optimization methods such as neuroevolution.

Current research efforts include comparing disparate approaches to reinforcement learning, developing more rigorous frameworks for empirical evaluations, improving the scalability of multiagent planning, and applying learning methods to traffic management, helicopter control, and data filtering in high energy physics.  To find out more about my research, check out my research page, see my publication list, or watch this (somewhat outdated) video.

News

January 2010: A book based on my PhD thesis will be published in Springer’s Studies in Computational Intelligence series.

November 2009: Our work on traffic control and representation switching appears in the forthcoming book Interactive Collaborative Information Systems from Springer.

August 2009: Michael Littman and I are editing a special issue of the Machine Learning Journal on Empirical Evaluations in Reinforcement Learning.

June 2009: Our article “Critical Factors in the Empirical Performance of Temporal Difference and Evolutionary Methods for Reinforcement Learning” was accepted for publication in the journal Autonomous Agents and Multi-Agent Systems.

May 2009: Our work on data analysis in high energy physics will be reported in articles in Engineering Applications of Artificial Intelligence and in Physical Review Letters.