Applying Reinforcement Learning to Optimize Traffic Light Cycles
This work addresses traffic congestion for urban planners and drivers, but it is incremental as it applies an existing method to a specific domain.
The paper tackled the problem of manual traffic light optimization by applying reinforcement learning to optimize cycles in real-time, resulting in a 44.16% decrease in average emergency stops.
Manual optimization of traffic light cycles is a complex and time-consuming task, necessitating the development of automated solutions. In this paper, we propose the application of reinforcement learning to optimize traffic light cycles in real-time. We present a case study using the Simulation Urban Mobility simulator to train a Deep Q-Network algorithm. The experimental results showed 44.16% decrease in the average number of Emergency stops, showing the potential of our approach to reduce traffic congestion and improve traffic flow. Furthermore, we discuss avenues for future research and enhancements to the reinforcement learning model.