D-CIS Publication Database

Publication

Type of publication:Article
Entered by:JOSM
TitleOptimal and Approximate Q-value Functions for Decentralized POMDPs
Bibtex cite ID
Journal Journal of Artificial Intelligence Research
Year published 2008
Volume 32
Pages 289-353
ISSN 1076-9757
Keywords optimal approximate,Q-value functions,decentralized POMDPs
Abstract
Planning in single-agent models like MDPs and POMDPs can be carried out by resorting to Q-value functions: a (near-) optimal Q-value function is computed in a recursive manner by dynamic programming, and then a policy is extracted from this value function. In this paper we study whether similar Q-value functions can be defined in decentralized POMDP models (Dec-POMDPs), what the cost of computing such value functions is, and how policies can be extracted from such value functions. Using the framework of Bayesian games, we argue that searching for the optimal Q-value function may be as costly as exhaustive policy search. Then we analyze various approximate Q-value functions that allow efficient computation. Finally, we describe a family of algorithms for extracting policies from such Q-value functions.
Authors
Oliehoek, Frans
Spaan, Matthijs T. J.
Vlassis, Nikos
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
 
Total mark: 5