Multi-Objective Reinforcement Learning (MORL) aims to learn a set of policies that optimize trade-offs between multiple, often conflicting objectives. MORL is computationally more complex than single-objective RL, particularly as the number of objectives increases. Additionally, when objectives involve the preferences of agents or groups, ensuring fairness is socially desirable. This paper introduces a principled algorithm that incorporates fairness into MORL while improving scalability to many-objective problems. We propose using Lorenz dominance to identify policies with equitable reward distributions and introduce {\lambda}-Lorenz dominance to enable flexible fairness preferences. We release a new, large-scale real-world transport planning environment and demonstrate that our method encourages the discovery of fair policies, showing improved scalability in two large cities (Xi'an and Amsterdam). Our methods outperform common multi-objective approaches, particularly in high-dimensional objective spaces.

Ghebreab has spent the last decade imparting that emphasis on interdisciplinarity to his students. 'Sometime around 2010, I decided to stop putting my energy into my own research and to invest it in the next generation instead. Questions I have dealt with in my teaching include: how does the brain process information? Where do we see pattern recognition reflected? And how does AI cope with pattern recognition and bias?