My paper on Double Q-learning was accepted at NIPS.
I am currently employed as project member at CWI (the Centrum Wiskunde & Informatica, which translates to the center for mathematics and computer science). I have nearly finished my dissertation on reinforcement learning at the University of Utrecht. I have conducted my Ph.D. research mainly under supervision of Marco Wiering.
My main research interests and the topic of my dissertation are in the field of reinforcement learning. My other research interests include machine learning in a broader sense, classification, evolutionary strategies and statistical learning.
Hado van Hasselt (2010). "Double Q-learning". To be published in Advances in Neural Information Processing Systems 23 (NIPS 2010), Vancouver, British Columbia, Canada.
Joost Westra, Hado van Hasselt, Frank Dignum and Virginia Dignum (2009). "Adaptive Serious Games Using Agent Organizations". In F.P.M. Dignum, J.M. Bradshaw, BG Silverman & W..A. Doesburg (Eds.), Agents for Games and Simulations, pp. 206-220. Berlin / Heidelberg: Springer.
Marco Wiering and Hado van Hasselt (2008). "Ensemble Algorithms in Reinforcement Learning". In: IEEE Transactions, SMC Part B, special issue on Adaptive Dynamic Programming and Reinforcement Learning in Feedback Control. August 2008. pp. 930-936.
Joost Westra, Hado van Hasselt, Virginia Dignum and Frank Dignum (2008). "On-line Adapting Games Using Agent Organizations". Proceedings of IEEE Symposium on Computational Intelligence and Games (CIG 2008), Perth, Australia, 2008.
Hado van Hasselt and Marco Wiering (2007). "Reinforcement Learning in Continuous Action Spaces". Proceedings of IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL 2007), Honolulu, HI, USA, pp. 272-279, 2007.