Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances

TL;DR

This paper surveys recent advances in imitation learning enabled by deep learning, introduces a new taxonomy, and discusses methodological innovations, practical applications, and future research directions.

Contribution

It presents a novel taxonomy for imitation learning and critically reviews recent methodological and practical developments in the field.

Findings

Deep learning has expanded IL capabilities across domains.

New methodologies address challenges like generalization and covariate shift.

The survey highlights trends, strengths, and limitations of recent IL research.

Abstract

Imitation learning (IL) enables agents to acquire skills by observing and replicating the behavior of one or multiple experts. In recent years, advances in deep learning have significantly expanded the capabilities and scalability of imitation learning across a range of domains, where expert data can range from full state-action trajectories to partial observations or unlabeled sequences. Alongside this growth, novel approaches have emerged, with new methodologies being developed to address longstanding challenges such as generalization, covariate shift, and demonstration quality. In this survey, we review the latest advances in imitation learning research, highlighting recent trends, methodological innovations, and practical applications. We propose a novel taxonomy that is distinct from existing categorizations to better reflect the current state of the IL research stratum and its trends. Throughout the survey, we critically examine the strengths, limitations, and evaluation practices of representative works, and we outline key challenges and open directions for future research.