Neural Deconstruction Search for Vehicle Routing Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911193490259968 |
|---|---|
| author | Hottung, André Wong-Chung, Paula Tierney, Kevin |
| author_facet | Hottung, André Wong-Chung, Paula Tierney, Kevin |
| contents | 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 matches or surpasses the performance of state-of-the-art operations research methods across three challenging vehicle routing problems of various problem sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03715 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural Deconstruction Search for Vehicle Routing Problems Hottung, André Wong-Chung, Paula Tierney, Kevin Artificial Intelligence Machine Learning 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 matches or surpasses the performance of state-of-the-art operations research methods across three challenging vehicle routing problems of various problem sizes. |
| title | Neural Deconstruction Search for Vehicle Routing Problems |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.03715 |