Agent-Based Route Planning with Deep Q Learning

Solving traffic congestion is one of the most important and complex problems, as it causes chaos in metropolitans, especially during rush hours. Traditional methods that continue to be used have proven to be inadequate, and as a result, the developing technology has affected all areas as well as the solutions to the traffic control problem. Intelligent Transportation Systems have emerged with the development of artificial intelligence and communication technologies. This study aims to reduce time in traffic by using an agent-based route planning method with deep Q learning. An agent which acts as a taxi in the generated traffic flow is also used to demonstrate the efficiency of the proposed method in taxi service. It is aimed to be able to comprehend the actions to be implemented in order to complete the given task in an effective way with deep Q learning, considering criteria such as travel time and waiting time for passengers as performance criteria in different scenarios.