交通出行过程中,诱导信息的发布与出行路径的选择是两个相互联系相互影响的决策过程,基于此建立了诱导-出行信号博弈模型,并依据其信号均衡将路网分成了不同的等级.为验证均衡解的合理性,提出了一种基于完全但不完美信息动态博弈的虚拟行动学习模型并应用于此问题,收到了很好的学习仿真效果,最后给出了相应的收敛性定理及其证明. In the process of traffic travel, the information release and travel route selection are two decision-making processes which influence each other. Based on this, a game model of travel-departure signal is established, and the road network is divided into different levels according to its signal balance. In order to verify the rationality of the equilibrium solution, a virtual action learning model based on complete but imperfect information dynamic game is proposed and applied to this problem, and a good learning simulation result is obtained. Finally, the corresponding convergence theorem Its proof.