Traffic Signal Control Using Reinforcement Learning

Proposing an appropriate and dynamic strategy to meet the existing requirements is an important aspect in traffic control system. Continuous changes of states and the necessity to respond quickly are the specific characteristics of the environment in a traffic control system. To achieve an existing requirements Reinforcement Learning i.e. Q learning algorithm have been developed that is closely related to methods of dynamic programming which quickly respond to the actual conditions found in the environment and also learn about them. In this approach, some statistical traffic data is used and then computing appropriate values of the traffic parameters. The simulation result shows that Q learning algorithm is able to manage the traffic signals efficiently in both under saturation and over saturation.