Abstract In a ride-hailing system, an optimal relocation of vacant vehicles can significantly reduce fleet idling time and balance the supply–demand distribution, enhancing system efficiency and promoting driver satisfaction and retention. Model-free deep reinforcement learning (DRL) has been shown to dynamically learn the relocating policy by actively interacting with the intrinsic dynamics in large-scale ride-hailing systems. However, the issues of sparse reward signals and unbalanced demand and supply distribution place critical barriers in developing effective DRL models. Conventional exploration strategy (e.g., the ϵ -greedy) may barely work under such an environment because of dithering in low-demand regions distant from high-revenue regions. This study proposes the deep relocating option policy (DROP) that supervises vehicle agents to escape from oversupply areas and effectively relocate to potentially underserved areas. We propose to learn the Laplacian embedding of a time-expanded relocation graph, as an approximation representation of the system relocation policy. The embedding generates task-agnostic signals, which in combination with task-dependent signals, constitute the pseudo-reward function for generating DROPs. We present a hierarchical learning framework that trains a high-level relocation policy and a set of low-level DROPs. We note that DROP is a general method and can be incorporated into existing model-free RL advances for further improvements in ride-hailing applications. The effectiveness of our approach is demonstrated using a custom-built high-fidelity simulator with real-world trip record data. We report that DROP significantly improves baseline value and policy iteration algorithms and can effectively resolve the dithering issue in low-demand areas.

    Highlights Hierarchical reinforcement learning framework for relocating empty vehicles. Learning deep relocation option policy using past relocation records. High-fidelity simulator with real-world trip data as training environment. Comprehensive experiments and ablation study.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning


    Beteiligte:
    Qian, Xinwu (Autor:in) / Guo, Shuocheng (Autor:in) / Aggarwal, Vaneet (Autor:in)


    Erscheinungsdatum :

    2022-10-06




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Real-world ride-hailing vehicle repositioning using deep reinforcement learning

    Jiao, Yan / Tang, Xiaocheng / Qin, Zhiwei (Tony) et al. | Elsevier | 2021


    Strategic driver repositioning in ride-hailing networks with dual sourcing

    Dong, Tingting / Luo, Qi / Xu, Zhengtian et al. | Elsevier | 2023



    A novel repositioning approach and analysis for dynamic ride-hailing problems

    Christian Ackermann / Julia Rieck | DOAJ | 2023

    Freier Zugriff

    SYSTEMS AND METHODS FOR REPOSITIONING VEHICLES IN A RIDE-HAILING PLATFORM

    LI SHUAIJI / TANG XIAOCHENG / QIN ZHIWEI | Europäisches Patentamt | 2022

    Freier Zugriff