Optimizing Quantum Variational Circuits with Deep Reinforcement Learning

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.

References in corpus (34)

• Adam: A Method for Stochastic Optimization
• Continuous control with deep reinforcement learning
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Soft Actor-Critic Algorithms and Applications
• A Quantum Approximate Optimization Algorithm
• Strong quantum computational advantage using a superconducting quantum processor
• Evaluating analytic gradients on quantum hardware
• Dota 2 with Large Scale Deep Reinforcement Learning
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks
• Deep Reinforcement Learning that Matters
• PennyLane: Automatic differentiation of hybrid quantum-classical computations
• Diagnosing Barren Plateaus with Tools from Quantum Optimal Control
• Unsupervised Machine Learning on a Hybrid Quantum Computer
• Resolving catastrophic error bursts from cosmic rays in large arrays of superconducting qubits
• Estimating the gradient and higher-order derivatives on quantum hardware
• Leveraging Secondary Storage to Simulate Deep 54-qubit Sycamore Circuits
• Experimental Deep Reinforcement Learning for Error-Robust Gateset Design on a Superconducting Quantum Computer
• q-means: A quantum algorithm for unsupervised machine learning
• Classical Simulation of Quantum Supremacy Circuits
• Space, time, parallelism and noise requirements for reliable quantum computing
• Quantum circuit optimization with deep reinforcement learning
• Simulating the Sycamore quantum supremacy circuits
• Policy Gradient based Quantum Approximate Optimization Algorithm
• Maximum Entropy RL (Provably) Solves Some Robust RL Problems
• FLIP: A flexible initializer for arbitrarily-sized parametrized quantum circuits
• Deep reinforcement learning for robust quantum optimization
• Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks