Free energy-based reinforcement learning using a quantum processor
Machine Learning
2017-06-02 v1 Artificial Intelligence
Neural and Evolutionary Computing
Optimization and Control
Quantum Physics
Abstract
Recent theoretical and experimental results suggest the possibility of using current and near-future quantum hardware in challenging sampling tasks. In this paper, we introduce free energy-based reinforcement learning (FERL) as an application of quantum hardware. We propose a method for processing a quantum annealer's measured qubit spin configurations in approximating the free energy of a quantum Boltzmann machine (QBM). We then apply this method to perform reinforcement learning on the grid-world problem using the D-Wave 2000Q quantum annealer. The experimental results show that our technique is a promising method for harnessing the power of quantum sampling in reinforcement learning tasks.
Cite
@article{arxiv.1706.00074,
title = {Free energy-based reinforcement learning using a quantum processor},
author = {Anna Levit and Daniel Crawford and Navid Ghadermarzy and Jaspreet S. Oberoi and Ehsan Zahedinejad and Pooya Ronagh},
journal= {arXiv preprint arXiv:1706.00074},
year = {2017}
}