Analysis and Design of Information Dynamics and Information Dissemination To Realize Optimal Management of Transportation

我们一直在关注控制交通网络系统行为的信息服务的理想模式。该问题的难点在于最优交通分配并不总是满足每个驾驶员的最小出行时间。因此，本研究试图确定如何调和这两种相互冲突的观点。大多数先前的研究强调驾驶员的决策过程来解决这个悖论。我们特别研究了信息服务方面，以使交通流量令人满意。首先，我们采用强化学习框架来获得解决悖论的策略。其次，通过实验给出了实现理想交通流的信息分配准则。

We have been concerned with the desirable mode of information services to control the behavior of a transportation network system. The difficulty of this problem is that optimal traffic assignment is not always satisfied with minimal travel time of each driver. Consequently, this study is an attempt to ascertain how to reconcile these two conflicting viewpoints. Most previous studies emphasized the driver's decision making processes to resolve this paradox. We specifically examined the information services side to make traffic flow desirable. First, we adopt a reinforcement learning framework to acquire a strategy for solving the paradox. Secondly, we show the criteria of information distribution to realize a desirable traffic flow through some experimentation.