论文部分内容阅读
交通控制系统是一个复杂的巨系统,传统的建模和控制方式难以获得较好的控制效果。文章针对区域协调控制中难以建立精确数学模型的特点,引入了强化学习,提出了基于强化学习的无模型区域协调控制算法。采用微观交通仿真软件对算法进行了仿真实验,与Webster定时控制进行对比,实验结果表明:强化学习算法取得较好的效果。
Traffic control system is a complex giant system, the traditional modeling and control method is difficult to get better control effect. In this paper, aiming at the characteristics that it is difficult to establish an accurate mathematical model in regional coordinated control, this paper introduces intensive learning and proposes a model-free coordinated control algorithm based on reinforcement learning. The simulation experiment is carried out by using the micro-traffic simulation software and compared with the Webster timing control. The experimental results show that the reinforcement learning algorithm achieves good results.