A challenging application of artificial intelligence systems involves the scheduling of traffic signals in multi-intersection vehicular networks. This paper introduces a novel use of a multi-agent system and reinforcement learning (RL) framework to obtain an efficient traffic signal control policy. The latter is aimed at minimising the average delay, congestion and likelihood of intersection cross-blocking. A five-intersection traffic network has been studied in which each intersection is governed by an autonomous intelligent agent. Two types of agents, a central agent and an outbound agent, were employed. The outbound agents schedule traffic signals by following the longest-queue-first (LQF) algorithm, which has been proved to guarantee stability and fairness, and collaborate with the central agent by providing it local traffic statistics. The central agent learns a value function driven by its local and neighbours' traffic conditions. The novel methodology proposed here utilises the Q-Learning algorithm with a feedforward neural network for value function approximation. Experimental results clearly demonstrate the advantages of multi-agent RL-based control over LQF governed isolated single-intersection control, thus paving the way for efficient distributed traffic signal control in complex settings.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement learning-based multi-agent system for network traffic signal control


    Beteiligte:
    Arel, I. (Autor:in) / Liu, C. (Autor:in) / Urbanik, T. (Autor:in) / Kohls, A.G. (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2010


    Format / Umfang :

    8 Seiten, 24 Quellen




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Print


    Sprache :

    Englisch





    Traffic light signal control method based on multi-agent reinforcement learning

    ZHAO SHENGJIE / DENG HAO / CHEN ZHI | Europäisches Patentamt | 2022

    Freier Zugriff

    Adaptive traffic signal control method based on multi-agent reinforcement learning

    ZHANG CHENGWEI / JIN SHAN / ZHENG KANGJIE | Europäisches Patentamt | 2021

    Freier Zugriff


    Traffic signal lamp control method based on cooperative multi-agent reinforcement learning

    REN FUYUE / ZHAO XIAODONG / ZHANG FAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff