
Type of publication:  Inproceedings 
Entered by:  BvB 
Title  Optimal Control in Large Stochastic MultiAgent Systems 
Bibtex cite ID  
Booktitle  Proceedings of the 7th Annual Symposium on Adaptive and Learning Agents and MultiAgent Systems (ALAMAS 2007) 
Year published  2007 
Month  April 
Pages  910 
Location  23 April 2007, Maastricht, The Netherlands 
Keywords  stochastic optimal control,multiagent systems 
Abstract  We study optimal control in large stochastic multiagent systems in continuous space and time. We consider multiagent 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 field approximation to compute accurate approximations of the optimal controls. We conclude that near to optimal control in large stochastic multiagent systems is possible with this approach. 
Authors  
Topics
 =SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
=SEE OWN CLASSIFICATION=

BibTeX  BibTeX 
RIS  RIS 
Attachments  
Total mark:  5 

