The invention discloses a multi-agent reinforcement learning traffic signal cooperative control method considering intersection heterogeneity, belongs to the field of urban traffic signal control, and particularly relates to a traffic signal cooperative control method. The invention aims to solve the problem of low passing efficiency of the existing intersection. The method comprises the steps of data acquisition; building and initializing a simulation platform; building and initializing a multi-agent deep reinforcement learning network; the traffic state of the intersection, the traffic state of the road network and the reward function output by the simulation platform serve as input of a multi-agent deep reinforcement learning network, individual action function values of all the intersections are output, actions are determined and fed back to the simulation platform, and the simulation platform outputs the traffic state of the intersection, the traffic state of the road network and the reward function again after delta t seconds; obtaining a trained multi-agent deep reinforcement learning network; and inputting the traffic state of the actual intersection into the network, outputting an individual action function value, and selecting an optimal action to be issued to the intersection.
考虑交叉口异质性的多智能体强化学习交通信号协同控制方法,本发明属于城市交通信号控制领域,具体涉及交通信号协同控制方法。本发明的目的是为了解决现有交叉口通行效率低的问题。过程为:数据采集;仿真平台搭建及初始化;多智能体深度强化学习网络搭建及初始化;将仿真平台输出的交叉口的交通状态、路网的交通状态、奖励函数作为多智能体深度强化学习网络的输入,输出各交叉口的个体动作函数值,确定动作反馈给仿真平台,仿真平台Δt秒后再次输出交叉口的交通状态、路网的交通状态、奖励函数;获得训练好的多智能体深度强化学习网络;将实际交叉口的交通状态输入网络,输出个体动作函数值,选择最优动作下发到交叉口。
Multi-agent reinforcement learning traffic signal cooperative control method considering intersection heterogeneity
考虑交叉口异质性的多智能体强化学习交通信号协同控制方法
2024-05-14
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Multi-intersection traffic signal cooperative control method
European Patent Office | 2023
|European Patent Office | 2025
|European Patent Office | 2024
|