arXiv 2605.267762026-05-26cs.LGcs.AI

面向泛化的混合专家车辆路径问题模型

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

State Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology（自主智能无人系统国家重点实验室，北京理工大学）；School of AI, Beijing Institute of Technology（北京理工大学人工智能学院）

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

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出基于混合专家架构的残差细化专家与实例级门控机制（R2E-IG），通过模块化策略网络和动态权重适应训练，提升车辆路径问题在分布偏移下的泛化能力。

摘要：

近年来，深度强化学习（DRL）在车辆路径问题（VRPs）上取得了显著进展。然而，现有的基于DRL的方法通常是在均匀分布生成的实例上训练的，这限制了它们在真实世界分布偏移下的性能。在本文中，我们旨在开发一个面向泛化的模型，该模型将策略网络划分为多个模块，并在推理过程中自适应地重组模块以形成特定策略。具体来说，我们提出了具有实例级门控的残差细化专家（R2E-IG）以改进跨分布泛化。我们的贡献有三方面：（1）我们引入了一种残差细化专家（R2E）架构，通过残差细化增强专家表达能力；（2）我们设计了一种实例级门控机制，学习分布感知的实例表示并将输入路由到合适的模块；（3）我们提出了一种配备动态权重适应（DWA）的混合分布训练机制，该机制动态地重新加权来自不同分布的训练数据，以强调更具信息量的数据。大量实验表明，R2E-IG在合成和基准数据集的分布内和分布外实例上均取得了与最先进基线相竞争的性能。此外，R2E-IG是通用的，可以轻松集成到现有的基于DRL的方法中，以进一步提高性能。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。