Fair Transport Network Design using Multi-Agent Reinforcement Learning

Transportation systems fundamentally impact human well-being, productivity, and sustainability. It is thus crucial to address the disproportional benefits that their design can lead to. In my research, I explore the trade-off between efficiency and fairness in transport network design. I argue that Multi-Agent Reinforcement Learning frameworks can be used to study the dynamics of mobility and simulate the impact of transportation network design on alleviating urban inequalities.