Taxis spend a large amount of time idle, searching for passengers. The routes vacant taxis should follow in order to minimize their idle times are hard to calculate; they depend on complex effects like passenger demand, traffic conditions, and inter-taxi competition. Here we explore if reinforcement learning (RL) can be used for this purpose. Using real-world data from three major cities, we show RL-taxis can indeed learn to minimize their idle times in different environments. In particular, a single RL-taxi competing with a population of regular taxis learns to out-perform its rivals.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Using reinforcement learning to minimize taxi idle times


    Contributors:

    Published in:

    Publication date :

    2022-06-15


    Size :

    12 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Estimating Taxi-out times with a reinforcement learning algorithm

    Balakrishna, Poornima / Ganesan, Rajesh / Sherry, Lance et al. | IEEE | 2008



    Drone taxi system using multi-agent reinforcement learning and drone taxi operation method using the same

    JOONGHEON KIM / YUN WON JOON / JAE HYUN KIM et al. | European Patent Office | 2022

    Free access

    Multiagent Reinforcement Learning-Based Taxi Predispatching Model to Balance Taxi Supply and Demand

    Yongjian Yang / Xintao Wang / Yuanbo Xu et al. | DOAJ | 2020

    Free access

    Reinforcement Learning for Engine Idle Speed Control

    Xue, Jinlin / Gao, Qiang / Ju, Weiping | Tema Archive | 2010