Cooperative multi-agent reinforcement learning models (CMRLM) for intelligent traffic control

Abstract

Traffic crisis often happen because of traffic burden by the large number automobiles on the path. Increasing transportation move and decreasing the average waiting time of each vehicle are the aims of cooperative intelligent traffic control system. Each signal wishes to catch better travel move. During the course, signals form a strategy of cooperation in addition to restriction for neighboring signals to exploit their individual benefit. A superior traffic signal scheduling strategy is used to resolve the difficulty. The several parameters may influence the traffic control model. So it is hard to learn the best possible result. Traffic light controllers are not expert to study from previous results. Due to this, they are unable to include the uncertain transformation of traffic flow. Reinforcement learning algorithm based traffic control model used to get fine timing rules by properly defining real-time parameters of the real traffic scenario. The projected real-time traffic control optimization prototype is able to continue with the traffic signal scheduling rules successfully. The model expands traffic value of the vehicle, which consists of delay time, the number of vehicles stopped at a signal, and the newly arriving vehicles to learn and set up the optimal actions. The experimentation outcome illustrates a major enhancement in traffic control, demonstrating the projected model is competent of making possible real-time dynamic traffic control.