Interpretable Apprenticeship Learning from Heterogeneous Decision-Making via Personalized Embeddings

Advances in learning from demonstration (LfD) have enabled intelligent agents to learn decision-making strategies through observation. However, humans exhibit heterogeneity in their decision-making criteria, leading to demonstrations with significant variability. We propose a personalized apprenticeship learning framework that automatically infers an interpretable representation of all human task demonstrators by extracting latent, human-specific decision-making criteria specified by an inferred, personalized embedding. We achieve near-perfect LfD accuracy in synthetic domains and 89.02% accuracy on a real-world planning domain, significantly outperforming state-of-the-art benchmarks. Further, a user study conduced to assess the interpretability of different types of decision-making models finds evidence that our methodology produces both interpretable (p < 0.04) and highly usable models (p < 0.05).