Neural Deconstruction Search for Vehicle Routing Problems
Keywords: neural combinatorial optimization; vehicle routing problem; reinforcement learning; neural deconstruction
TL;DR: We introduce an iterative search framework in which solutions are deconstructed by a neural policy.
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.
Primary Area: reinforcement learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7980
Loading