Optimalisasi Arus Lalulintas Perkotaan Menggunakan Reinforcement Learning

Muhammad Al Fatih
Ahmad Tazkiarni Ramadhan
Nikri Aria Pratama
Ahmad Aqil
Aries Saifudin

Journal of Research and Publication Innovation
Vol 2 No 3 (2024): JULY

This study aims to optimize urban traffic flow using a reinforcement learning approach. With rapid urban population growth, traffic issues become increasingly urgent to address to improve transportation efficiency and reduce congestion. In this research, we collect traffic data from a specific urban area and apply a reinforcement learning model to develop a system that can learn traffic patterns and make optimal decisions for traffic management. We conduct testing of the system using simulations and in real-world environments to evaluate its performance. The analysis results indicate that this approach is effective in enhancing traffic flow and reducing congestion in the studied urban area. Potential implications of this research include improving urban transportation efficiency and enhancing the quality of life for city residents.