Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category •

Influence-Based Abstraction for Multiagent Systems

Frans A. Oliehoek, Stefan Witwicki, and Leslie P. Kaelbling. Influence-Based Abstraction for Multiagent Systems. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, pp. 1422–1428, July 2012.

Download

pdf [159.8kB]  

Abstract

This paper presents a theoretical advance by which factored POSGs can be decomposed into local models. We formalize the interface between such local models as the influence agents can exert on one another; and we prove that this interface is sufficient for decoupling them. The resulting influence-based abstraction substantially generalizes previous work on exploiting weakly-coupled agent interaction structures. Therein lie several important contributions. First, our general formulation sheds new light on the theoretical relationships among previous approaches, and promotes future empirical comparisons that could come by extending them beyond the more specific problem contexts for which they were developed. More importantly, the influence-based approaches that we generalize have shown promising improvements in the scalability of planning for more restrictive models. Thus, our theoretical result here serves as the foundation for practical algorithms that we anticipate will bring similar improvements to more general planning contexts, and also into other domains such as approximate planning, decision-making in adversarial domains, and online learning.

BibTeX Entry

@InProceedings{Oliehoek12AAAI_IBA,
    author =    {Frans A. Oliehoek and 
                 Stefan Witwicki and
                 Leslie P. Kaelbling},
    title =     {Influence-Based Abstraction for Multiagent Systems},
    booktitle = AAAI12,
    month =     jul,
    year =      2012,
    pages =     {1422--1428},
    abstract = 	 {
       This paper presents a theoretical advance by which factored
       POSGs can be decomposed into local models. We formalize the
       interface between such local models as the influence agents can
       exert on one another; and we prove that this interface is
       sufficient for decoupling them. The resulting influence-based
       abstraction substantially generalizes previous work on
       exploiting weakly-coupled agent interaction structures. Therein
       lie several important contributions. First, our general
       formulation sheds new light on the theoretical relationships
       among previous approaches, and promotes future empirical
       comparisons that could come by extending them beyond the more
       specific problem contexts for which they were developed. More
       importantly, the influence-based approaches that we generalize
       have shown promising improvements in the scalability of
       planning for more restrictive models. Thus, our theoretical
       result here serves as the foundation for practical algorithms
       that we anticipate will bring similar improvements to more
       general planning contexts, and also into other domains such as
       approximate planning, decision-making in adversarial domains,
       and online learning.
    }
}

Generated by bib2html.pl (written by Patrick Riley) on Wed Nov 06, 2013 16:37:07 UTC