In this context, we present a teacher-student framework that can distill the black-box (teacher) model into a student model with minimal accuracy loss.

Much of the work in online learning focuses on the study of sublinear upper bounds on the regret.

Human explanation (e.g., in terms of feature importance) has been recently used

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks.

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.