Demand Acceptance using Reinforcement Learning for Dynamic Vehicle Routing Problem with Emission Quota

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Najar, Farid, Barth, Dominique, Strozecki, Yann
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912965689606144
author Najar, Farid
Barth, Dominique
Strozecki, Yann
author_facet Najar, Farid
Barth, Dominique
Strozecki, Yann
contents This paper introduces and formalizes the Dynamic and Stochastic Vehicle Routing Problem with Emission Quota (DS-QVRP-RR), a novel routing problems that integrates dynamic demand acceptance and routing with a global emission constraint. A key contribution is a two-layer optimization framework designed to facilitate anticipatory rejections of demands and generation of new routes. To solve this, we develop hybrid algorithms that combine reinforcement learning with combinatorial optimization techniques. We present a comprehensive computational study that compares our approach against traditional methods. Our findings demonstrate the relevance of our approach for different types of inputs, even when the horizon of the problem is uncertain.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13279
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Demand Acceptance using Reinforcement Learning for Dynamic Vehicle Routing Problem with Emission Quota
Najar, Farid
Barth, Dominique
Strozecki, Yann
Machine Learning
Artificial Intelligence
This paper introduces and formalizes the Dynamic and Stochastic Vehicle Routing Problem with Emission Quota (DS-QVRP-RR), a novel routing problems that integrates dynamic demand acceptance and routing with a global emission constraint. A key contribution is a two-layer optimization framework designed to facilitate anticipatory rejections of demands and generation of new routes. To solve this, we develop hybrid algorithms that combine reinforcement learning with combinatorial optimization techniques. We present a comprehensive computational study that compares our approach against traditional methods. Our findings demonstrate the relevance of our approach for different types of inputs, even when the horizon of the problem is uncertain.
title Demand Acceptance using Reinforcement Learning for Dynamic Vehicle Routing Problem with Emission Quota
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.13279