Spring 2013 GRASP Seminar: Pedro Ortega, Max Planck Institute for Intelligent Systems and Biological Cybernetics, "Adaptive Coding of Actions and Observations"

Abstract: The application of expected utility theory to construct adaptive agents is both computationally intractable and statistically questionable. To overcome these difficulties, agents need the ability to delay the choice of the optimal policy to a later stage when they have learned more about the environment. How should agents do this optimally? An information-theoretic answer to this question is given by the Bayesian control rule - the solution to the adaptive coding problem when there are not only observations but also actions. We review the central ideas behind the Bayesian control rule.

Presenter's biography

Pedro A. Ortega is currently postdoctoral fellow at the Max Planck Institute for Intelligent Systems and Biological Cybernetics working on the foundations of autonomous agency. He grew up in Zürich, Switzerland and then moved to Santiago, Chile, where he graduated in 2005 as a Computer Engineer from the University of Chile. In 2011, he obtained his PhD in Engineering from the University of Cambridge under the supervision of Zoubin Ghahramani.