In many cities worldwide, urban centers serve as transportation bottlenecks, increasing travel times for all road users, regardless of whether their destinations are within or outside the city center. Various strategies have been proposed to mitigate traffic congestion, including the implementation of physical barriers to restrict access, congestion pricing during peak hours, and entrance fees for vehicles entering the city center.
In this study, we propose a solution based on homogeneous control of traffic flow within the city center. Specifically, we aim to dynamically regulate access by measuring the current state of the transportation system and determining optimal adjustments to improve overall travel times. To achieve this, we employ reinforcement learning to optimize a control parameter governing the opening and closing of barriers at city center entry points.
The proposed controller is implemented using a reinforcement learning agent based on the Proximal Policy Optimization (PPO) algorithm. The objective is to learn an optimal policy for managing access restrictions, thereby reducing congestion and improving traffic efficiency within the urban core.