Vehicle Routing Problems (VRPs) play an important role in industry for managing and optimizing operations for fleets of vehicles. Our project aims to incorporate new objectives that pertain to social and environmental sustainability together with classical productivity related ones. One key goal is for example to avoid contributing to congestions in the road network. To tackle these objectives, we use learning-based methods, since these have proven to be efficient, effective and broadly applicable. In previous work, we have explored new machine learning models to deal with the fundamental properties of the problems of interest (they can be multi-objective with path flexibility). Through this project, we aim to demonstrate the applicability of our approach in more realistic settings. More concretely, we aim to: 1) Apply our multigraph multi-objective VRP models to tackle realistic problems with multiple objectives in real road networks. 2) Develop new models that perform more robustly across distributions and VRP variants. 3) Continue the work to generalize to larger and larger instance sizes.