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 and stochastic optimization methods such as neuroevolution.

Current research efforts include best-match methods for reinforcement learning, multi-task reinforcement learning, balancing exploration and exploitation in information retrieval, neuroevolutionary helicopter control, analyzing novelty search, and optimally and approximately solving Dec-POMDPs. To find out more about my research, check out my research page or see my publication list.

News

March 2012: Our article Balancing Exploration and Exploitation in Listwise and Pairwise Online Learning to Rank for Information Retrieval was accepted for publication in the journal Information Retrieval.

January 2012: Maarten de Rijke and I have been awarded a Free Competition grant by the NWO (Dutch national science foundation) for a 4-year project entitled Modeling and Learning from Implicit Feedback in Information Retrieval.

December 2011: Our paper V-MAX: Tempered Optimism for Better PAC Reinforcement Learning was accepted for publication in AAMAS-12.

September 2011: Our article Neuroevolutionary Reinforcement Learning for Generalized Control of Simulated Helicopters was accepted for publication in the journal Evolutionary Intelligence.

July 2011: Our paper A Probabilistic Method for Inferring Preferences from Clicks was accepted for publication in CIKM-11.

July 2011: I have been awarded a Free Competition grant by the NWO (Dutch national science foundation) for a 4-year project entitled Decision-Theoretic Control for Network Capacity Allocation Problems.