Optimizing Quantum Variational Circuits with Deep Reinforcement Learning

TL;DR

This paper explores using deep reinforcement learning to improve the optimization of quantum variational circuits, especially in noisy conditions, outperforming traditional gradient-based methods.

Contribution

It demonstrates that reinforcement learning can effectively augment quantum circuit optimization, addressing hardware imperfections and complex search spaces.

Findings

Reinforcement learning outperforms gradient descent in noisy environments.

RL-augmented optimizers achieve better convergence in quantum variational circuits.

Code and pretrained models are publicly available for replication.

Abstract

Quantum Machine Learning (QML) is considered to be one of the most promising applications of near term quantum devices. However, the optimization of quantum machine learning models presents numerous challenges arising from the imperfections of hardware and the fundamental obstacles in navigating an exponentially scaling Hilbert space. In this work, we evaluate the potential of contemporary methods in deep reinforcement learning to augment gradient based optimization routines in quantum variational circuits. We find that reinforcement learning augmented optimizers consistently outperform gradient descent in noisy environments. All code and pretrained weights are available to replicate the results or deploy the models at: https://github.com/lockwo/rl_qvc_opt.