Hierarchical traffic signal optimization using reinforcement learning and traffic prediction with long-short term memory

Multi-agent systems can be used for modelling large-scale distributed systems in real world applications. In intelligent transportation system (ITS), many interacting entities influence the performance of the system. As part of ITS, traffic signal control can be modelled using a multi-agent system. In this paper, a hierarchical multi-agent system including two levels is employed to control traffic signals. Each traffic signal is controlled by an agent that sits in the physical level, i.e., in the first level. For the other levels, the traffic network is divided into a number of regions, each controlled by a region controller agent. The first level agents utilize reinforcement learning to find the best policy, while they send their local information to the above level agents. The local information is used to train a long short-term memory (LSTM) neural network for traffic status prediction. The agents in the above level can control the traffic signals by finding the best joint policy using the predicted traffic information. Experimental results show the effectiveness of the proposed method in a traffic network including 16 intersections.