What is ‘multi’ in multi-agent learning?

Learning in multi-agent environments constitutes a research and application area whose importance is broadly acknowledged in artificial intelligence. Although there is a rapidly growing body of literature on multi-agent learning, almost nothing is known about the intrinsic nature of and requirements for this kind of learning. This observation is the starting point of this chapter which aims at providing a more general characterization of multi-agent learning. This is done in an interdisciplinary way from two different perspectives: the perspective of single-agent learning (the ‘machine learning perspective’) and the perspective of human-human collaborative learning (the ‘psychological perspective’). The former leads to a ‘positive’ characterization: three types of learning mechanisms multiplication, division, and interaction are identified and illustrated that can occur in multi-agent but not in single-agent settings. The latter leads to a ‘negative’ characterization: several cognitive processes like conflict resolution, mutual regulation, and explanation are identified and discussed that are most essential to human-human collaborative learning, but have been largely ignored so far in the available multi-agent learning approaches. Misunderstanding among humans is identified as a major source of these processes, and its important role in the context of multiagent systems is stressed. This chapter also offers a brief guide to agents and multi-agent systems as studied in artificial intelligence, and suggests directions for future research on multi-agent learning.