Abstract
Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here, we propose a information-theoretic formalization of bounded rational decision-making where information processing is modelled as changes in the information state that can be quantified by differences in the so-called free energy. By optimizing a free energy, bounded rational decision-makers trade off expected utility gains and information-processing costs measured by the relative entropy. As a result, the bounded rational decision-making problem can be rephrased in terms of well-known variational principles from statistical physics. In the limit when computational costs are ignored, the maximum expected utility principle is recovered.

Bio
Pedro A. Ortega is postdoctoral researcher in the GRASP Robotics Lab at the University of Pennsylvania, working with Prof. Daniel D. Lee. His research focuses on the mathematical foundations of artificial intelligence, machine learning, and cybernetics. His work includes the application of information-theoretic and statistical mechanical ideas to sequential decision-making, which has led to contributions in novel bounded rationality models and recasting adaptive control as a causal inference problem. He obtained his PhD in Engineering from the University of Cambridge (Prof. Zoubin Ghahramani), and he has been a post-doctoral fellow in the Department of Engineering at Cambridge (Prof. Simon Godsill), at the Max Planck Institute for Biological Cybernetics/Intelligent Systems (Daniel A. Braun), and at the Hebrew University in Jerusalem (Prof. Naftali Tishby).