Metraipolis › archive › dc_624bc29d12aa

Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking — arXiv:2608.13799

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13799
License (as archived)
CC0-1.0
Archived
2026-10-19T02:30:27.494Z
SHA-256 of the archived text
18646db4de63994769f2b42d8eb1cbaf714d216067bac8392c7f2a1cf3ab3169
Stable URL of this page
https://metraipolis.com/documento/dc_624bc29d12aa

How to cite

Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking — arXiv:2608.13799 — arXiv (en), https://arxiv.org/abs/2608.13799 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_624bc29d12aa (Metraipolis archive dc_624bc29d12aa, sha256 18646db4de63994769f2b42d8eb1cbaf714d216067bac8392c7f2a1cf3ab3169)
BibTeX
@misc{dc624bc29d12aa,
  title = {Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking — arXiv:2608.13799},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13799},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_624bc29d12aa; sha256 18646db4de63994769f2b42d8eb1cbaf714d216067bac8392c7f2a1cf3ab3169},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13799. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed requests and evolving vehicle states. Masked MLP and Transformer policies are trained through behavior cloning and proximal policy optimization. Deterministic feasibility masking prevents invalid vehicle--request assignments, while fixed-prefix/flexible-suffix route commitments protect completed, active, and near-term decisions and separately measure vehicle reassignment and resequencing. The learned policies are compared with dynamic insertion heuristics and time-limited rolling-horizon optimization. In a 20-scenario policy benchmark, all methods completed every request without invalid actions, but nearest feasible achieved the lowest mean objective and outperformed the learned policies in routing quality, waiting time, stability, makespan, and runtime. Across five independent training runs, PPO had little average effect on the MLP and improved the Transformer on average, although with greater seed variability. Under the common protocol, nearest feasible achieved the lowest combined objective and route disruption, whereas rolling horizon achieved the lowest waiting times and makespan at substantially higher computational cost. The learned policies retained millisecond-level decisions and transferred to instances with up to 80 requests without retraining, but did not outperform the strongest heuristic. No single method was best across routing efficiency, service responsiveness, stability, and online computation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13799 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:26:17.774Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).