Quantum Algorithm for Apprenticeship Learning

TL;DR

This paper introduces a quantum algorithm for apprenticeship learning that significantly speeds up the process compared to classical methods, with proven convergence and quadratic improvements in complexity.

Contribution

It presents the first quantum algorithm for apprenticeship learning via inverse reinforcement learning, demonstrating quadratic speedup over classical algorithms.

Findings

Quantum algorithm achieves quadratic speedup in per-iteration complexity.

Classical approximate apprenticeship learning algorithm with proven convergence.

Quantum approach extends classical methods with improved efficiency.

Abstract

Apprenticeship learning is a method commonly used to train artificial intelligence systems to perform tasks that are challenging to specify directly using traditional methods. Based on the work of Abbeel and Ng (ICML'04), we present a quantum algorithm for apprenticeship learning via inverse reinforcement learning. As an intermediate step, we give a classical approximate apprenticeship learning algorithm to demonstrate the speedup obtained by our quantum algorithm. We prove convergence guarantees on our classical approximate apprenticeship learning algorithm, which also extends to our quantum apprenticeship learning algorithm. We also show that, as compared to its classical counterpart, our quantum algorithm achieves an improvement in the per-iteration time complexity by a quadratic factor in the dimension of the feature vectors $k$ and the size of the action space $A$.