In recent years, there has been a growing trend towards using deep reinforcement learning (DRL) to solve the NP-hard vehicle routing problems (VRPs). While much success has been achieved, most of the previous studies solely focused on single-depot VRPs, which became less effective in handling more practical scenarios, such as multi-depot VRPs. Although there are many preprocessing measures, such as natural decomposition, those scenarios are still more challenging to optimize. To resolve this issue, we propose the multi-depot multi-type attention (MD-MTA) to solve the multi-depot VRP (MDVRP) and multi-depot open VRP (MDOVRP), respectively. We design a multi-type attention in the network to combine different types of embeddings and the state of the environment at each step, so as to accurately select the next node to visit and construct the route. We introduce a depot rotation augmentation to enhance solution decoding. Results show that it performs favorably against various representative traditional baselines and DRL-based baselines.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Type Attention for Solving Multi-Depot Vehicle Routing Problems


    Contributors:
    Li, Jinqi (author) / Tian Dai, Bing (author) / Niu, Yunyun (author) / Xiao, Jianhua (author) / Wu, Yaoxin (author)

    Published in:

    Publication date :

    2024-11-01


    Size :

    11145528 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    On Solving the Multi-depot Vehicle Routing Problem

    Tlili, Takwa / Krichen, Saoussen / Drira, Ghofrane et al. | Springer Verlag | 2015


    Five years of multi-depot vehicle routing problems

    Nuwan Jayarathna / Jayantha Lanel / Z.A.M.S. Juman | DOAJ | 2020

    Free access


    Solving Multi-Agent Routing Problems Using Deep Attention Mechanisms

    Bono, Guillaume / Dibangoye, Jilles S. / Simonin, Olivier et al. | IEEE | 2021