Urban Traffic Control Based on Pre-Adapted Reinforcement Learning
Urban traffic control is one of the appropriate research grounds in various artificial intelligence fields such as multiagent systems and learning methods. Dynamism, continuous changes of states, and the necessity to give prompt response are among the specific characteristics of the environment in a traffic control system. Proposing an appropriate and flexible strategy to meet the existing requirements is always a major challenge in the traffic control field. In this paper, the authors have proposed an efficient method to control urban traffic using multiagent systems and a kind of reinforcement learning augmented by an auxiliary pre-learning stage.