Salvato in:
Dettagli Bibliografici
Autori principali: Abouelrous, Abdo, Bliek, Laurens, Gabor, Adriana F., Wu, Yaoxin, Zhang, Yingqian
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.02383
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913997180108800
author Abouelrous, Abdo
Bliek, Laurens
Gabor, Adriana F.
Wu, Yaoxin
Zhang, Yingqian
author_facet Abouelrous, Abdo
Bliek, Laurens
Gabor, Adriana F.
Wu, Yaoxin
Zhang, Yingqian
contents In this paper, we address the problem of Column Generation (CG) using Reinforcement Learning (RL). Specifically, we use a RL model based on the attention-mechanism architecture to find the columns with most negative reduced cost in the Pricing Problem (PP). Unlike previous Machine Learning (ML) applications for CG, our model deploys an end-to-end mechanism as it independently solves the pricing problem without the help of any heuristic. We consider a variant of Vehicle Routing Problem (VRP) as a case study for our method. Through a set of experiments where our method is compared against a Dynamic Programming (DP)-based heuristic for solving the PP, we show that our method solves the linear relaxation up to a reasonable objective gap in significantly shorter running times.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02383
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing
Abouelrous, Abdo
Bliek, Laurens
Gabor, Adriana F.
Wu, Yaoxin
Zhang, Yingqian
Machine Learning
In this paper, we address the problem of Column Generation (CG) using Reinforcement Learning (RL). Specifically, we use a RL model based on the attention-mechanism architecture to find the columns with most negative reduced cost in the Pricing Problem (PP). Unlike previous Machine Learning (ML) applications for CG, our model deploys an end-to-end mechanism as it independently solves the pricing problem without the help of any heuristic. We consider a variant of Vehicle Routing Problem (VRP) as a case study for our method. Through a set of experiments where our method is compared against a Dynamic Programming (DP)-based heuristic for solving the PP, we show that our method solves the linear relaxation up to a reasonable objective gap in significantly shorter running times.
title Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing
topic Machine Learning
url https://arxiv.org/abs/2504.02383