PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An introduction to stochastic control theory, path integrals and reinforcement learning
Bert Kappen
In: AIP, 11-15 September 2006, Spain.

Abstract

Abstract. Control theory is a mathematical description of how to act optimally to gain future rewards. In this paper I give an introduction to deterministic and stochastic control theory and I give an overview of the possible application of control theory to the modeling of animal behavior and learning. I discuss a class of non-linear stochastic control problems that can be efciently solved using a path integral or by MC sampling. In this control formalism the central concept of cost-to-go becomes a free energy and methods and concepts from statistical physics can be readily applied. Keywords: Stochastic optimal control, path integral control, reinforcement learning PACS: 05.45.-a 02.50.-r 45.80.+r

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:4876
Deposited By:Bert Kappen
Deposited On:24 March 2009