A complete framework for training and evaluating multi-agent reinforcement learning (MARL) systems for adaptive traffic signal control in realistic urban environments, using the SUMO microscopic ...
A simulation-based traffic light control system for a real Ho Chi Minh intersection, built with Python, PyTorch, and SUMO. A Deep Q-Network (DQN) agent learns to minimize vehicle queue lengths and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results