Balancing Efficiency and Fairness in Traffic Light Control through Deep Reinforcement Learning
2026-05-11 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how to make traffic lights smarter by using a kind of computer learning called deep reinforcement learning. Their system not only helps cars move better but also makes sure that pedestrians get fair crossing times. Unlike older systems that mostly focused on cars, this approach adjusts in real-time based on how many people and vehicles need to cross. Tests showed it reduces traffic jams while being fair to everyone. This work aims to improve how cities manage traffic in a smarter and more balanced way.
urban traffic congestiontraffic light controldeep reinforcement learningvehicular trafficpedestrian trafficreal-time demandsmart citiestraffic managementadaptive systems
Authors
Matteo Cederle, Giacomo Scatto, Gian Antonio Susto
Abstract
Urban traffic congestion presents a significant challenge for modern cities, which impacts mobility and sustainability. Traditional traffic light control systems often fail to adapt to dynamic conditions, leading to inefficiencies. This paper proposes a novel deep reinforcement learning agent for traffic light control that addresses this limitation by explicitly integrating fairness considerations for both vehicular and pedestrian traffic. Unlike prior work, our approach dynamically balances these flows based on real-time demand, moving beyond systems focused solely on vehicles. Experimental results demonstrate that our agent effectively reduces congestion while ensuring equitable service for both the categories of road users. This research contributes to a practical and adaptable solution for intelligent traffic management within the framework of smart cities, paving the way for more efficient and inclusive urban mobility.