RouteFinder: Towards Foundation Models for Vehicle Routing Problems
This work addresses the problem of efficiently solving multiple VRP variants for logistics and optimization domains, representing an incremental advancement by unifying and improving upon existing learning methods.
The paper tackles the challenge of creating a foundation model for various Vehicle Routing Problem (VRP) variants by introducing RouteFinder, which outperforms recent state-of-the-art learning methods in experiments on 48 VRP variants.
This paper introduces RouteFinder, a comprehensive foundation model framework to tackle different Vehicle Routing Problem (VRP) variants. Our core idea is that a foundation model for VRPs should be able to represent variants by treating each as a subset of a generalized problem equipped with different attributes. We propose a unified VRP environment capable of efficiently handling any combination of these attributes. The RouteFinder model leverages a modern transformer-based encoder and global attribute embeddings to improve task representation. Additionally, we introduce two reinforcement learning techniques to enhance multi-task performance: mixed batch training, which enables training on different variants at once, and multi-variant reward normalization to balance different reward scales. Finally, we propose efficient adapter layers that enable fine-tuning for new variants with unseen attributes. Extensive experiments on 48 VRP variants show RouteFinder outperforms recent state-of-the-art learning methods. Our code is publicly available at https://github.com/ai4co/routefinder.