A comprehensive analysis of agent factorization and learning algorithms in multiagent systems

Guardado en:
Detalles Bibliográficos
Publicado en:Autonomous Agents and Multi-Agent Systems vol. 38, no. 2 (Dec 2024), p. 27
Autor principal: Kallinteris, Andreas
Otros Autores: Orfanoudakis, Stavros, Chalkiadakis, Georgios
Publicado:
Springer Nature B.V.
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3254231876
003 UK-CbPIL
022 |a 1387-2532 
022 |a 1573-7454 
024 7 |a 10.1007/s10458-024-09662-9  |2 doi 
035 |a 3254231876 
045 2 |b d20241201  |b d20241231 
100 1 |a Kallinteris, Andreas  |u Technical University of Crete, School of ECE, Chania, Greece (GRID:grid.6809.7) (ISNI:0000 0004 0622 3117) 
245 1 |a A comprehensive analysis of agent factorization and learning algorithms in multiagent systems 
260 |b Springer Nature B.V.  |c Dec 2024 
513 |a Journal Article 
520 3 |a In multiagent systems, agent factorization denotes the process of segmenting the state-action space of the environment into distinct components, each corresponding to an individual agent, and subsequently determining the interactions among these agents. Effective agent factorization significantly influences the system performance of real-world industrial applications. In this work, we try to assess the performance impact of agent factorization when using different learning algorithms in multiagent coordination settings; and thus discover the source of performance quality of the multiagent solution derived by combining different factorizations with different learning algorithms. To this end, we evaluate twelve different agent factorization instances—or agent definitions—in the warehouse traffic management domain, comparing the training performance of (primarily) three learning algorithms suitable for learning coordinated multiagent policies: the Evolutionary Strategies (ES), the Canonical Evolutionary Strategies (CES), and a genetic algorithm (CCEA) previously used in a similar setting. Our results demonstrate that the performance of different learning algorithms is affected in different ways by alternative agent definitions. Given this, we can conclude that many important multiagent coordination problems can eventually be solved more efficiently by a suitable agent factorization combined with an appropriate choice of a learning algorithm. Moreover, our work shows that ES and CES are effective learning algorithms for the warehouse traffic management domain, while, interestingly, celebrated policy gradient methods do not fare well in this complex real-world problem setting. As such, our work offers insights into the intrinsic properties of the learning algorithms that make them well-suited for this problem domain. More broadly, our work demonstrates the need to identify appropriate agent definitions-multiagent learning algorithm pairings in order to solve specific complex problems effectively, and provides insights into the general characteristics that such pairings must possess to address broad classes of multiagent learning and coordination problems. 
653 |a Robots 
653 |a Design 
653 |a Industrial applications 
653 |a Multiagent systems 
653 |a Genetic algorithms 
653 |a Coordination 
653 |a Machine learning 
653 |a Warehouses 
653 |a Factorization 
700 1 |a Orfanoudakis, Stavros  |u Technical University of Crete, School of ECE, Chania, Greece (GRID:grid.6809.7) (ISNI:0000 0004 0622 3117); Delft University of Technology, Intelligent Electrical Power Grids (IEPG) Group, Delft, The Netherlands (GRID:grid.5292.c) (ISNI:0000 0001 2097 4740) 
700 1 |a Chalkiadakis, Georgios  |u Technical University of Crete, School of ECE, Chania, Greece (GRID:grid.6809.7) (ISNI:0000 0004 0622 3117) 
773 0 |t Autonomous Agents and Multi-Agent Systems  |g vol. 38, no. 2 (Dec 2024), p. 27 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3254231876/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3254231876/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3254231876/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch