Inequality in Congestion Games with Learning Agents

Who benefits from expanding transport networks? While designed to improve mobility, such interventions can also create inequality. We show that disparities arise not only from the structure of the network itself but also from differences in how commuters adapt to it. We model commuters as reinforcement learning agents who adapt their travel choices at different learning rates, reflecting unequal access to resources and information. We introduce the Price of Learning (PoL), a measure of inefficiency during learning. We analyze both a variation of the Braess Paradox original network and an abstraction of the Amsterdam metro network. Our simulations show that expansions can simultaneously increase efficiency and amplify inequality, especially when faster learners benefit from new routes before others adapt. We highlight that transport policies must account not only for equilibrium outcomes but also for the heterogeneous ways that commuters adapt.