EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Deep Reinforcement Learning Model to Solve the Stochastic Capacitated Vehicle Routing Problem with Service Times and Deadlines

Sergio Flavio Marroquín-Cano, Elías Neftalí Escobar-Gómez, Eduardo F. Morales, Elizeth Ramírez-Álvarez, Pedro Gasga-García, Eduardo Chandomí-Castellanos, J. Renán Velázquez-González, Julio Alberto Guzmán-Rabasa, José Roberto Bermúdez, Francisco Rodríguez-Sánchez

Mathematics · 22.09.2025 · 13 (18) · 3050

DOI: 10.3390/math13183050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 22.09.2025. Verfasst von Sergio Flavio Marroquín-Cano und 9 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle Routing Problems are central to logistics and operational research, arising in diverse contexts such as transportation planning, manufacturing systems, and military operations. While Deep Reinforcement Learning has been successfully applied to both deterministic and stochastic variants of Vehicle Routing Problems, existing approaches often neglect critical time-sensitive conditions. This work addresses the Stochastic Capacitated Vehicle Routing Problem with Service Times and Deadlines, a challenging formulation that is suited to model time routing conditions. The proposal, POMO-DC, integrates a novel dynamic context mechanism. At each decision step, this mechanism incorporates the vehicle’s cumulative travel time and delays—features absent in prior models—enabling the policy to adapt to changing conditions and avoid time violations. The model is evaluated on stochastic instances with 20, 30, and 50 customers and benchmarked against Google OR-Tools using multiple metaheuristics. Results show that POMO-DC reduces average delays by up to 88% (from 169.63 to 20.35 min for instances of 30 customers) and 75% (from 4352.43 to 1098.97 min for instances of 50 customers), while maintaining competitive travel times. These outcomes highlight the potential of Deep Reinforcement Learning-based frameworks to learn patterns from stochastic data and effectively manage time uncertainty in Vehicle Routing Problems.

Zitieren

APA

Marroquín-Cano, S. F., Escobar-Gómez, E. N., Morales, E. F., Ramírez-Álvarez, E., Gasga-García, P., Chandomí-Castellanos, E., Velázquez-González, J. R., Guzmán-Rabasa, J. A., Bermúdez, J. R., & Rodríguez-Sánchez, F. (2025). A Deep Reinforcement Learning Model to Solve the Stochastic Capacitated Vehicle Routing Problem with Service Times and Deadlines. Mathematics, 13(18), 3050. https://doi.org/10.3390/math13183050

Vancouver

Marroquín-Cano SF, Escobar-Gómez EN, Morales EF, Ramírez-Álvarez E, Gasga-García P, Chandomí-Castellanos E, et al. A Deep Reinforcement Learning Model to Solve the Stochastic Capacitated Vehicle Routing Problem with Service Times and Deadlines. Mathematics. 2025;13(18):3050. doi:10.3390/math13183050

BibTeX
@article{MarroqunCano2025,
  author = {Marroquín-Cano, Sergio Flavio and Escobar-Gómez, Elías Neftalí and Morales, Eduardo F. and Ramírez-Álvarez, Elizeth and Gasga-García, Pedro and Chandomí-Castellanos, Eduardo and Velázquez-González, J. Renán and Guzmán-Rabasa, Julio Alberto and Bermúdez, José Roberto and Rodríguez-Sánchez, Francisco},
  title = {A Deep Reinforcement Learning Model to Solve the Stochastic Capacitated Vehicle Routing Problem with Service Times and Deadlines},
  journal = {Mathematics},
  year = {2025},
  volume = {13},
  number = {18},
  pages = {3050},
  doi = {10.3390/math13183050}
}
Kostenlos starten →