Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts

About

In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based methods are typically trained on instances generated from a uniform distribution, which limits their performance under real-world distribution shifts. In this paper, we aim to develop a generalization-oriented model that partitions the policy network into multiple modules and adaptively recombines modules to form specific policies during inference. Specifically, we propose Residual Refined Experts with Instance-level Gating (R2E-IG) to improve cross-distribution generalization. Our contributions are threefold: (1) We introduce a Residual Refined Expert (R2E) architecture that enhance expert expressiveness via residual refinement; (2) We design an instance-level gating mechanism that learns distribution-aware instance representations and routes inputs to suitable modules; (3) We propose a mixed-distribution training mechanism equipped with Dynamic Weight Adaption (DWA), which dynamically reweights training data from different distributions to emphasize more informative ones. Extensive experiments show that R2E-IG achieves competitive performance against state-of-the-art baselines on both in-distribution and out-of-distribution instances across synthetic and benchmark datasets. Moreover, R2E-IG is generic and can be easily integrated into existing DRL-based methods to further improve performance.

Changhao Miao, Yuntian Zhang, Tongyu Wu, Fang Deng, Chen Chen• 2026

Related benchmarks

TaskDatasetResultRank
Capacitated Vehicle Routing ProblemCVRP N=100
Objective Value15.6268
87
Capacitated Vehicle Routing ProblemCVRP 20
Objective Value6.0801
43
Capacitated Vehicle Routing ProblemExpansion CVRP20
Objective Value5.3767
18
Capacitated Vehicle Routing ProblemExplosion CVRP100
Objective Value12.3139
18
Capacitated Vehicle Routing ProblemExpansion CVRP50
Objective Value8.2284
9
Capacitated Vehicle Routing ProblemExpansion CVRP100
Objective Value11.4175
9
Capacitated Vehicle Routing ProblemExplosion CVRP50
Objective Value8.8002
9
Capacitated Vehicle Routing ProblemGrid CVRP50
Objective Value10.4649
9
Capacitated Vehicle Routing ProblemImplosion CVRP50
Objective Value10.3022
9
Traveling Salesman ProblemExpansion TSP 50
Objective Value4.3897
9
Showing 10 of 26 rows

Other info

Follow for update