Publications

Sorted by DateClassified by Publication TypeClassified by Research Category

Safety Guarantees in Multi-agent Learning via Trapping Regions (Extended Abstract)

Aleksander Czechowski and Frans A. Oliehoek. Safety Guarantees in Multi-agent Learning via Trapping Regions (Extended Abstract). In Proceedings of the Twenty-Second International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2023.

Download

pdf [606.6kB]  

Abstract

One of the main challenges of multi-agent learning lies in establishing convergence of the algorithms, as, in general, a collection of individual, self-serving agents is not guaranteed to converge with their joint policy, when learning concurrently. This is in stark contrast to most single-agent environments, and sets a prohibitive barrier for deployment in practical applications, as it induces uncertainty in long term behavior of the system. In this work, we propose to apply the concept of trapping regions, known from qualitative theory of dynamical systems, to create safety sets in the joint strategy space for decentralized learning. Upon verification of the direction of learning dynamics, the resulting trajectories are guaranteed not to escape such sets, during the learning process. As a result, it is ensured, that despite the uncertainty over convergence of the applied algorithms, learning will never form hazardous joint strategy combinations.

BibTeX Entry

@inproceedings{Czechowski23AAMAS,
    author = {Czechowski, Aleksander and Oliehoek, Frans A.},
    title =     {Safety Guarantees in Multi-agent Learning via Trapping Regions (Extended Abstract)},
    booktitle = AAMAS23,
    year =      2023,
    month =     may,
    keywords =   {refereed},
    abstract =  {
        One of the main challenges of multi-agent learning lies in establishing
        convergence of the algorithms, as, in general, a collection of
        individual, self-serving agents is not guaranteed to converge with
        their joint policy, when learning concurrently. This is in stark
        contrast to most single-agent environments, and sets a prohibitive
        barrier for deployment in practical applications, as it induces
        uncertainty in long term behavior of the system.  In this work, we
        propose to apply the concept of trapping regions, known from
        qualitative theory of dynamical systems, to create safety sets in
        the joint strategy space for decentralized learning.  Upon
        verification of the direction of learning dynamics, the resulting
        trajectories are guaranteed not to escape such sets, during the
        learning process.  As a result, it is ensured, that despite the
        uncertainty over convergence of the applied algorithms, learning
        will never form hazardous joint strategy combinations.
    }
}

Generated by bib2html.pl (written by Patrick Riley) on Tue Dec 10, 2024 18:28:47 UTC