The complexity of systems studied in distributed artificial intelligence (DAI), such as multi-agent systems, often makes it extremely difficult or even impossible to correctly and completely specify their behavioral repertoires and dynamics. There is broad agreement that such systems should be equipped with the ability to learn in order to improve their future performance autonomously. The interdisciplinary cooperation of researchers from DAI and machine learning (ML) has established a new and very active area of research and development enjoying steadily increasing attention from both...