D-CIS Publication Database

Publication

Type of publication:Inproceedings
Entered by:JOSM
TitleAn Introduction to stochastic control theory, path integrals and reinforcement learning
Bibtex cite ID
Booktitle Proceedings 9th Granada Seminar on Computational Physics: Computational and Mathematical Modeling of Cooperative Behavior in Neural Systems
Year published 2006
Month September
Location 11-15 September 2006, Granada, Spain
Keywords stochastic control theory,path integrals,reinforcement learning
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 efficiently 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.
Authors
Kappen, Hilbert J.
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
 
Total mark: 5