Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions

Frans A. Oliehoek, Matthijs T. J. Spaan, and Stefan Witwicki. Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, pp. 1645–1651, July 2015.
[Please see the extended version for proofs.]

Download

pdf [391.5kB]  

Abstract

Nowadays, multiagent planning under uncertainty scales to tens or even hundreds of agents. However, current methods either are restricted to problems with factored value functions, or provide solutions without any guarantees on quality. Methods in the former category typically build on heuristic search using upper bounds on the value function. Unfortunately, no techniques exist to compute such upper bounds for problems with non-factored value functions, which would additionally allow for meaningful benchmarking of methods of the latter category. To mitigate this problem, this paper introduces a family of influence-optimistic upper bounds for factored Dec-POMDPs without factored value functions. We demonstrate how we can achieve firm quality guarantees for problems with hundreds of agents.

BibTeX Entry

@inproceedings{Oliehoek15IJCAI,
    author =    {Frans A. Oliehoek 
                 and Matthijs T. J. Spaan 
                 and Stefan Witwicki},
    title =     {Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions},
    booktitle = IJCAI15,
    year =      2015,
    month =     jul,
    pages =     {1645--1651},
    note =      {},
    wwwnote =   {[Please see the <a href="b2hd-Oliehoek15arxiv_UBs.html">extended version</a> for proofs.]},
    abstract = {
    Nowadays, multiagent planning under uncertainty scales to tens or even hundreds
    of agents. However, current methods either are restricted to problems with
    factored value functions, or provide solutions without any guarantees on
    quality. Methods in the former category typically build on heuristic search
    using upper bounds on the value function.  Unfortunately, no techniques
    exist to compute such upper bounds for problems with non-factored value
    functions, which would additionally allow for meaningful benchmarking of
    methods of the latter category.  To mitigate this problem, this paper
    introduces a family of influence-optimistic upper bounds for factored
    Dec-POMDPs without factored value functions.  We demonstrate how we can
    achieve firm quality guarantees for problems with hundreds of agents.
    }
}

Generated by bib2html.pl (written by Patrick Riley) on Sat Dec 09, 2017 12:30:44 UTC