The invention discloses a traffic signal control method and device based on a multi-agent reinforcement learning model. The method comprises the steps that respective traffic state data of multiple intersections in a target area are acquired, and the respective traffic state data of the multiple intersections comprise position data and speed data of vehicles in roads directly connected with the corresponding intersections; respectively inputting the respective traffic state data of the plurality of intersections into a plurality of pre-trained reinforcement learning models, and respectively outputting a plurality of traffic signal data by the plurality of reinforcement learning models, the plurality of traffic signal data being respectively used for controlling signal lamps of the plurality of intersections, and the plurality of reinforcement learning models select a plurality of traffic signal data from the plurality of action sets based on a Nash equilibrium strategy. The technical problem of poor traffic signal control effect caused by independent decision making of each reinforcement learning model when a plurality of reinforcement learning models are adopted to respectively control signals of a plurality of intersections is solved.
本发明公开了一种基于多智能体强化学习模型的交通信号控制方法和装置。其中,该方法包括:获取目标区域中多个路口各自的交通状态数据,其中,多个路口各自的交通状态数据包括与对应路口直接连接的道路中车辆的位置数据和速度数据;将多个路口各自的交通状态数据分别输入预先训练的多个强化学习模型,由多个强化学习模型分别输出多个交通信号数据,其中,多个交通信号数据分别用于控制多个路口的信号灯,多个强化学习模型基于纳什均衡策略分别从多个动作集合中选出多个交通信号数据。本发明解决了由于采用多个强化学习模型分别控制多个路口的信号时,每个强化学习模型做出决策较为独立,造成的交通信号控制的效果不佳的技术问题。
Traffic signal control method and device based on multi-agent reinforcement learning model
基于多智能体强化学习模型的交通信号控制方法和装置
2024-05-17
Patent
Electronic Resource
Chinese
Adaptive traffic signal control method based on multi-agent reinforcement learning
European Patent Office | 2021
|Traffic light signal control method based on multi-agent reinforcement learning
European Patent Office | 2022
|Traffic signal control method based on multi-agent deep reinforcement learning
European Patent Office | 2025
|Multi-agent reinforcement learning traffic signal control method based on strategy multiplexing
European Patent Office | 2024
|