Paper Info
Title
An investigation into mathematical programming for finite horizon decentralized POMDPs
Abstract
Decentralized planning in uncertain environments is a complex task generally dealt with by using a decision-theoretic approach, mainly through the framework of Decentralized Partially Observable Markov Decision Processes (DEC-POMDPs). Although DEC-POMDPS are a general and powerful modeling tool, solving them is a task with an overwhelming complexity that can be doubly exponential. In this paper, we study an alternate formulation of DEC-POMDPs relying on a sequence-form representation of policies. From this formulation, we show how to derive Mixed Integer Linear Programming (MILP) problems that, once solved, give exact optimal solutions to the DEC-POMDPs. We show that these MILPs can be derived either by using some combinatorial characteristics of the optimal solutions of the DEC-POMDPs or by using concepts borrowed from game theory. Through an experimental validation on classical test problems from the DEC-POMDP literature, we compare our approach to existing algorithms. Results show that mathematical programming outperforms dynamic programming but is less efficient than forward search, except for some particular problems. The main contributions of this work are the use of mathematical programming for DEC-POMDPs and a better understanding of DEC-POMDPs and of their solutions. Besides, we argue that our alternate representation of DEC-POMDPs could be helpful for designing novel algorithms looking for approximate solutions to DEC-POMDPs.
Year
DOI
Venue
2014
10.1613/jair.2915
Journal of Artificial Intelligence Research
Keywords
DocType
Volume
decentralized pomdps,optimal solution,alternate representation,mathematical programming,exact optimal solution,alternate formulation,complex task,decentralized planning,decentralized partially observable markov,decision-theoretic approach,dynamic programming,finite horizon,markov decision process,artificial intelligence,multiagent systems,decision theory,artificial intelligent,game theory
Journal
abs/1401.3831
Issue
ISSN
Citations 
1
Journal Of Artificial Intelligence Research, Volume 37, pages 329-396, 2010
14
PageRank 
References 
Authors
0.63
37
2
Name
Order
Citations
PageRank
Raghav Aras1353.32
Alain Dutech28611.37