The invention belongs to the technical field of intelligent traffic control, particularly discloses a multi-intersection traffic signal lamp fairness control method based on multi-agent reinforcement learning, designs a novel fairness measurement index, provides a fairness perception multi-agent reinforcement learning method, and can improve the traffic signal lamp fairness control efficiency on the premise of ensuring that the model performance is not affected. A relatively fair action decision is provided; an anti-factual data enhancement module is provided, expansion of a data set is realized based on existing interaction data by utilizing an anti-factual thought, the diversity of the interaction data is enriched, and then the training sample efficiency is improved in a task in which interaction data collection is limited; an auxiliary self-supervised representation learning task is designed, self-supervised representation learning loss is constructed through a natural sequential relationship between states, introduction of additional training loss is beneficial to state information feature extraction, and the model training sample efficiency is improved.

    本发明属于智能交通控制技术领域,具体公开了基于多智能体强化学习的多路口交通信号灯公平控制方法,设计了一种新型的公平性度量指标,并提出了一种公平性感知的多智能体强化学习方法,可以在确保模型性能不受影响的前提下,提供相对公平的动作决策;提出了反事实数据增强的模块,通过利用反事实思想,基于已有的交互数据实现数据集的扩展,有利于丰富交互数据的多样性,进而在交互数据收集受限的任务中提高训练样本效率;设计了辅助自监督表示学习任务,通过状态之间天然的时序关系构建自监督表示学习损失,额外训练损失的引入有利于状态信息特征提取,提升模型训练样本效率。


    Access

    Download


    Export, share and cite



    Title :

    Multi-intersection traffic signal lamp fair control method based on multi-agent reinforcement learning


    Additional title:

    基于多智能体强化学习的多路口交通信号灯公平控制方法


    Contributors:
    DU XINQI (author) / CHEN HECHANG (author) / CHANG YI (author) / XING YONGHENG (author) / ZHANG SINUO (author)

    Publication date :

    2024-07-05


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen




    Multi-agent reinforcement learning method for fair adaptive traffic signal control

    ZHANG CHENGWEI / FANG WANQING / ZHAO XINTIAN | European Patent Office | 2023

    Free access

    Multi-agent reinforcement learning-based multi-traffic signal lamp control method and system

    WANG CHENG / FANG YIPENG / WANG XINYI et al. | European Patent Office | 2024

    Free access

    Multi-agent reinforcement learning traffic signal cooperative control method considering intersection heterogeneity

    BIE YIMING / JI YUTING / JI JINHUA et al. | European Patent Office | 2024

    Free access

    Traffic signal control method based on multi-agent reinforcement learning and intersection importance

    ZHANG CHENGWEI / LIU WANTING / WANG QICHAO et al. | European Patent Office | 2025

    Free access