Optimally Teaching a Linear Behavior Cloning Agent
Abstract
We study optimal teaching of Linear Behavior Cloning (LBC) learners. In this setup, the teacher can select which states to demonstrate to an LBC learner. The learner maintains a version space of infinite linear hypotheses consistent with the demonstration. The goal of the teacher is to teach a realizable target policy to the learner using minimum number of state demonstrations. This number is known as the Teaching Dimension(TD). We present a teaching algorithm called ``Teach using Iterative Elimination(TIE)" that achieves instance optimal TD. However, we also show that finding optimal teaching set computationally is NP-hard. We further provide an approximation algorithm that guarantees an approximation ratio of on the teaching dimension. Finally, we provide experimental results to validate the efficiency and effectiveness of our algorithm.
Keywords
Cite
@article{arxiv.2311.15399,
title = {Optimally Teaching a Linear Behavior Cloning Agent},
author = {Shubham Kumar Bharti and Stephen Wright and Adish Singla and Xiaojin Zhu},
journal= {arXiv preprint arXiv:2311.15399},
year = {2023}
}