3. Reinforcement Learning for Sustainable Route Choice in Urban Mobility

Choosing the best route through a city is challenging because traffic conditions change continuously. Reinforcement learning (RL) provides a way for an agent to learn effective route-selection strategies by interacting with a simulated transport network. This project will investigate whether an RL-based approach can learn to select routes that reduce travel time and congestion compared with conventional shortest-path and travel-time-based approaches. The project will evaluate the learned strategy under different traffic demand conditions and investigate how well it adapts when traffic patterns change.