Simulation-Based Optimization of the 3Rs in Circular Construction Using Integrated Digital Twins and Multi-agent Reinforcement Learning

[EN] Achieving a circular construction industry requires reducing waste, reusing materials, and recycling resources (the 3Rs). However, traditional methods for implementing these goals mostly depend on static strategies that do not adapt to changes in demand or resource availability. This paper prop...

Descripción completa

Detalles Bibliográficos
Autores: Guzmán, Eduardo, Tobon, Sandra, Torres, Marta, Andres, B.|||0000-0002-7920-7711
Tipo de recurso: artículo
Fecha de publicación:2026
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::f8892753c630cc2f3ea9f35b6c6f8dd3
Acceso en línea:https://riunet.upv.es/handle/10251/235273
Access Level:acceso embargado
Palabra clave:Circular Economy
Construction waste management
Sustainability
Deep Q-network
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
Descripción
Sumario:[EN] Achieving a circular construction industry requires reducing waste, reusing materials, and recycling resources (the 3Rs). However, traditional methods for implementing these goals mostly depend on static strategies that do not adapt to changes in demand or resource availability. This paper proposes an approach that integrates Digital Twins (DTs) and Multi-Agent Reinforcement Learning (MARL) to optimize the 3Rs dynamically and collaboratively. The DTs continuously sim-ulate construction processes, enabling real-time monitoring of waste generation, costs, and energy consumption. Meanwhile, multiple agents learn actions, via deep reinforcement learning, that jointly minimize material waste while balanc-ing cost and carbon footprint targets. The synergy between MARL and DT is demonstrated through a simulated scenario inwhicheachagentspecializesindifferentinterventions(e.g.,recycling,scheduling,logistics).Resultsshowthatthisintegratedapproachoutperformsbaselinestrategies,nointervention(No-Op)andrandomactions,significantlyreducingaveragewasteandimprovingrecyclingrates.Theseresultshighlightthepotentialofintelligent,data-drivenframeworkstoadvancesustainabilityintheconstructionindustry,pavingthewayforlarge-scaleadoptionofcirculareconomyprinciples.