Graph Q-Learning for Combinatorial Optimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dax, Victoria M., Li, Jiachen, Leahy, Kevin, Kochenderfer, Mykel J.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910294197927936
author Dax, Victoria M.
Li, Jiachen
Leahy, Kevin
Kochenderfer, Mykel J.
author_facet Dax, Victoria M.
Li, Jiachen
Leahy, Kevin
Kochenderfer, Mykel J.
contents Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data. In this paper, we propose and demonstrate that GNNs can be applied to solve Combinatorial Optimization (CO) problems. CO concerns optimizing a function over a discrete solution space that is often intractably large. To learn to solve CO problems, we formulate the optimization process as a sequential decision making problem, where the return is related to how close the candidate solution is to optimality. We use a GNN to learn a policy to iteratively build increasingly promising candidate solutions. We present preliminary evidence that GNNs trained through Q-Learning can solve CO problems with performance approaching state-of-the-art heuristic-based solvers, using only a fraction of the parameters and training time.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05610
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graph Q-Learning for Combinatorial Optimization
Dax, Victoria M.
Li, Jiachen
Leahy, Kevin
Kochenderfer, Mykel J.
Machine Learning
Artificial Intelligence
Graph-structured data is ubiquitous throughout natural and social sciences, and Graph Neural Networks (GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data. In this paper, we propose and demonstrate that GNNs can be applied to solve Combinatorial Optimization (CO) problems. CO concerns optimizing a function over a discrete solution space that is often intractably large. To learn to solve CO problems, we formulate the optimization process as a sequential decision making problem, where the return is related to how close the candidate solution is to optimality. We use a GNN to learn a policy to iteratively build increasingly promising candidate solutions. We present preliminary evidence that GNNs trained through Q-Learning can solve CO problems with performance approaching state-of-the-art heuristic-based solvers, using only a fraction of the parameters and training time.
title Graph Q-Learning for Combinatorial Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.05610