An Invitation to Imitation

Abstract

Imitation learning is the study of algorithms that attempt to improve performance by mimicking a teacher’s decisions and behaviors. Such techniques promise to enable effective “programming by demonstration” to automate tasks, such as driving, that people can demonstrate but find difficult to hand program. This work represents a summary from a very personal perspective of research on computationally effective methods for learning to imitate behavior. I intend it to serve two audiences: to engage machine learning experts in the challenges of imitation learning and the interesting theoretical and practical distinctions with more familiar frameworks like statistical supervised learning theory; and equally, to make the frameworks and tools available for imitation learning more broadly appreciated by roboticists and experts in applied artificial intelligence.