Inhalt des Dokuments
Kappen, Radboud University Nijmegen,
|Wednesday, February 13, 2013, 1.30 - 2.30 p.m.,
Faculty meeting room – MAR 6.004, Building Marchstraße
Stochastic optimal control theory provides a principled answer to the problem of computing an optimal sequence of actions to reach a goal in the presence of uncertainty. The solution is based on dynamic programming and known as the Bellman equation. However, the actual computation is typically very costly and scales exponentially in the dimension of the problem. Recently, it was shown that a quite large class of non-linear control problems could be solved using an alternative approach using a diffusion process. The optimal control can be represented as a path integral, an expectation over future trajectories. This solution can be computed much more efficiently, using MCMC or other approximate inference methods. In this talk, I will introduce the theory in the context of a learning to control an unknown plant.
Bert Kappen studied particle physics in Groningen, the Netherlands and completed his PhD in 1987 at the Rockefeller University in New York. Since 1997 he is a Professor at the laboratory for biophysics at the University of Nijmegen. His group is involved in research on machine learning (stochastic processes, learning algorithms, probabilistic reasoning and several applications in collaboration with industry) and computational neuroscience. His research was awarded in 1997 the prestigious national PIONIER research subsidy. He co-founded in 1998 the company Smart Research, which sells prediction software based on neural networks. He has developed a medical diagnostic expert system called Promedas, which assists doctors to make accurate diagnosis of patients.