Training agents for unknown logistics problems

verfasst von: Elisa Schmid, Matthias Becker
Abstract: A methodology on how to prepare agents to succeed on a priori unknown logistics problems is presented. The training of the agents is and can only be executed using a small number of test problems that are taken out of a broad class of generalized logistics problems. The developed agents are then evaluated on unknown instances of the problem class. This work has been developed in the context of last year’s AbstractSwarm Multi-Agent Logistics Competition. The most successful algorithms are presented, and additionally, all participating algorithms are discussed with respect to the features of the algorithms that contribute to their success. As a result, we conclude that such a broad variety of a priori unknown logistics problems can be solved efficiently if multiple different good working approaches are used, instead of trying to find one optimal algorithm. For the used test problems this method can undercut, trivial as well as non-trivial implementations, for example, algorithms based on machine learning.
Organisationseinheit(en): Fachgebiet Mensch-Computer-Interaktion
Typ: Aufsatz in Konferenzband
Seiten: 243-246
Anzahl der Seiten: 4
Publikationsdatum: 24.07.2023
Publikationsstatus: Veröffentlicht
Peer-reviewed: Ja
ASJC Scopus Sachgebiete: Software, Theoretische Informatik und Mathematik, Angewandte Informatik
Elektronische Version(en): https://doi.org/10.1145/3583133.3590724 (Zugang: Geschlossen)

BibTeX

@inproceedings{c982fb906404492f811165ca6657335b,
title = "Training agents for unknown logistics problems",
abstract = "A methodology on how to prepare agents to succeed on a priori unknown logistics problems is presented. The training of the agents is and can only be executed using a small number of test problems that are taken out of a broad class of generalized logistics problems. The developed agents are then evaluated on unknown instances of the problem class. This work has been developed in the context of last year{\textquoteright}s AbstractSwarm Multi-Agent Logistics Competition. The most successful algorithms are presented, and additionally, all participating algorithms are discussed with respect to the features of the algorithms that contribute to their success. As a result, we conclude that such a broad variety of a priori unknown logistics problems can be solved efficiently if multiple different good working approaches are used, instead of trying to find one optimal algorithm. For the used test problems this method can undercut, trivial as well as non-trivial implementations, for example, algorithms based on machine learning.",
keywords = "agent learning, competition, unknown logistics problems",
author = "Elisa Schmid and Matthias Becker",
year = "2023",
month = jul,
day = "24",
doi = "10.1145/3583133.3590724",
language = "English",
pages = "243--246",
booktitle = "GECCO '23 Companion",
publisher = "Association for Computing Machinery, Inc",
note = "2023 Genetic and Evolutionary Computation Conference Companion : GECCO 2023 ; Conference date: 15-07-2023 Through 19-07-2023",
}