Imitation Learning as Cause-Effect Reasoning

Garrett E. Katz, Di-Wei Huang, Rodolphe J. Gentili, James A. Reggia

Abstract: We propose a framework for general-purpose imitation learning centered on cause-effect reasoning. Our approach infers a hierarchical representation of a demonstrator’s intentions, which can explain why they acted as they did. This enables rapid generalization of the observed actions to new situations. We employ a novel causal inference algorithm with formal guarantees and connections to automated planning. Our approach is implemented and validated empirically using a physical robot, which successfully generalizes skills involving bimanual manipulation of composite objects in 3D. These results suggest that cause-effect reasoning is an effective unifying principle for cognitive-level imitation learning.