PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Optimal control in large stochastic multi-agent systems.
Bart Broek, Wim Wiegerinck and Bert Kappen
In: Alamas, 2-3 April 2007, The netherlands.


Abstract. We study optimal control in large stochastic multi-agent systems in continuous space and time. We consider multi-agent systems where agents have independent dynamics with additive noise and control. The goal is to minimize the joint cost, which consists of a state dependent term and a term quadratic in the control. The system is described by a mathematical model, and an explicit solution is given. We focus on large systems where agents have to distribute themselves over a number of targets with minimal cost. In such a setting the optimal control problem is equivalent to a graphical model inference problem. Exact inference will be intractable, and we use the mean eld approximation to compute accurate approximations of the optimal controls. We conclude that near to optimal control in large stochastic multi-agent systems is possible with this approach.

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:4883
Deposited By:Bert Kappen
Deposited On:24 March 2009