Neural Deconstruction Search for Vehicle Routing Problems
- URL: http://arxiv.org/abs/2501.03715v1
- Date: Tue, 07 Jan 2025 11:44:25 GMT
- Title: Neural Deconstruction Search for Vehicle Routing Problems
- Authors: André Hottung, Paula Wong-Chung, Kevin Tierney,
- Abstract summary: We introduce an iterative search framework where solutions are deconstructed by a neural policy.
Our approach surpasses the performance of state-of-the-art operations research methods across three challenging vehicle routing problems.
- Score: 6.6401567070583
- License:
- Abstract: Autoregressive construction approaches generate solutions to vehicle routing problems in a step-by-step fashion, leading to high-quality solutions that are nearing the performance achieved by handcrafted, operations research techniques. In this work, we challenge the conventional paradigm of sequential solution construction and introduce an iterative search framework where solutions are instead deconstructed by a neural policy. Throughout the search, the neural policy collaborates with a simple greedy insertion algorithm to rebuild the deconstructed solutions. Our approach surpasses the performance of state-of-the-art operations research methods across three challenging vehicle routing problems of various problem sizes.
Related papers
- A Multiagent Path Search Algorithm for Large-Scale Coalition Structure Generation [61.08720171136229]
Coalition structure generation is a fundamental computational problem in multiagent systems.
We develop SALDAE, a multiagent path finding algorithm for CSG that operates on a graph of coalition structures.
arXiv Detail & Related papers (2025-02-14T15:21:27Z) - An Efficient Learning-based Solver Comparable to Metaheuristics for the
Capacitated Arc Routing Problem [67.92544792239086]
We introduce an NN-based solver to significantly narrow the gap with advanced metaheuristics.
First, we propose direction-aware facilitating attention model (DaAM) to incorporate directionality into the embedding process.
Second, we design a supervised reinforcement learning scheme that involves supervised pre-training to establish a robust initial policy.
arXiv Detail & Related papers (2024-03-11T02:17:42Z) - The Algorithm Configuration Problem [0.8075866265341176]
This article focuses on optimizing parametrized algorithms for solving specific instances of decision/optimization problems.
We present a comprehensive framework that not only formalizes the Algorithm Configuration Problem, but also outlines different approaches for its resolution.
arXiv Detail & Related papers (2024-03-01T17:29:34Z) - Genetic Algorithms with Neural Cost Predictor for Solving Hierarchical Vehicle Routing Problems [20.684353068460375]
When vehicle routing decisions are intertwined with higher-level decisions, the resulting optimization problems pose significant challenges for computation.
We propose a novel deep-learning-based approach called Genetic Algorithm with Neural Cost Predictor (GANCP) to tackle the challenge.
In particular, our proposed neural network learns the objective values of the HGS-CVRP open-source package that solves capacitated vehicle routing problems.
arXiv Detail & Related papers (2023-10-22T02:46:37Z) - Large Neighborhood Search based on Neural Construction Heuristics [5.210197476419621]
We propose a learned construction based on neural networks as repair operator to solve the vehicle routing problem with time windows.
Our method uses graph neural networks to encode the problem and auto-regressively decodes a solution.
arXiv Detail & Related papers (2022-05-02T09:38:19Z) - An Overview and Experimental Study of Learning-based Optimization
Algorithms for Vehicle Routing Problem [49.04543375851723]
Vehicle routing problem (VRP) is a typical discrete optimization problem.
Many studies consider learning-based optimization algorithms to solve VRP.
This paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step approaches.
arXiv Detail & Related papers (2021-07-15T02:13:03Z) - A review of approaches to modeling applied vehicle routing problems [77.34726150561087]
We review the approaches for modeling vehicle routing problems.
We formulate several criteria for evaluating modeling methods.
We discuss several future research avenues in the field of modeling VRP domains.
arXiv Detail & Related papers (2021-05-23T14:50:14Z) - Deep Policy Dynamic Programming for Vehicle Routing Problems [89.96386273895985]
We propose Deep Policy Dynamic Programming (D PDP) to combine the strengths of learned neurals with those of dynamic programming algorithms.
D PDP prioritizes and restricts the DP state space using a policy derived from a deep neural network, which is trained to predict edges from example solutions.
We evaluate our framework on the travelling salesman problem (TSP) and the vehicle routing problem (VRP) and show that the neural policy improves the performance of (restricted) DP algorithms.
arXiv Detail & Related papers (2021-02-23T15:33:57Z) - Learning to Solve Vehicle Routing Problems with Time Windows through
Joint Attention [6.155158115218501]
We develop a policy model that is able to start and extend multiple routes concurrently by using attention on the joint action space of several tours.
In comprehensive experiments on three variants of the vehicle routing problem with time windows we show that our model called JAMPR works well for different problem sizes and outperforms the existing state-of-the-art constructive model.
arXiv Detail & Related papers (2020-06-16T12:08:10Z) - MineReduce: an approach based on data mining for problem size reduction [58.720142291102135]
This paper presents an approach named MineReduce, which uses mined patterns to perform problem size reduction.
We present an application of MineReduce to improve a for the heterogeneous fleet vehicle routing problem.
arXiv Detail & Related papers (2020-05-15T08:49:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.