Quantum circuit optimization with deep reinforcement learning

Abstract

A central aspect for operating future quantum computers is quantum circuit optimization, i.e., the search for efficient realizations of quantum algorithms given the device capabilities. In recent years, powerful approaches have been developed which focus on optimizing the high-level circuit structure. However, these approaches do not consider and thus cannot optimize for the hardware details of the quantum architecture, which is especially important for near-term devices. To address this point, we present an approach to quantum circuit optimization based on reinforcement learning. We demonstrate how an agent, realized by a deep convolutional neural network, can autonomously learn generic strategies to optimize arbitrary circuits on a specific architecture, where the optimization target can be chosen freely by the user. We demonstrate the feasibility of this approach by training agents on 12-qubit random circuits, where we find on average a depth reduction by 27% and a gate count reduction by 15%. We examine the extrapolation to larger circuits than used for training, and envision how this approach can be utilized for near-term quantum devices.

arXiv comment10 pages, 5 figures; keywords: quantum computing, quantum circuit optimization, machine learning, reinforcement learning, deep reinforcement learning

References in corpus (14)

• Playing Atari with Deep Reinforcement Learning
• Quantum Mechanics helps in searching for a needle in a haystack
• The theory of variational hybrid quantum-classical algorithms
• A Quantum Approximate Optimization Algorithm
• Active learning machine learns to create new quantum experiments
• Polynomial-time T-depth Optimization of Clifford+T circuits via Matroid Partitioning
• A Neural Decoder for Topological Codes
• Chip Placement with Deep Reinforcement Learning
• Reducing T-count with the ZX-calculus
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Deep Neural Network Probabilistic Decoder for Stabilizer Codes
• Learning in Quantum Control: High-Dimensional Global Optimization for Noisy Quantum Dynamics
• Decoding Molecular Graph Embeddings with Reinforcement Learning
• QVECTOR: an algorithm for device-tailored quantum error correction

Cited by in corpus (25)

• Deep Reinforcement Learning for Quantum State Preparation with Weak Nonlinear Measurements
• Pulse-level noisy quantum circuits with QuTiP
• Reinforcement learning for optimization of variational quantum circuit architectures
• Quantum Embedding Search for Quantum Machine Learning
• Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks
• Compiler Optimization for Quantum Computing Using Reinforcement Learning
• Artificial Intelligence for Quantum Computing
• Quantum Architecture Search via Deep Reinforcement Learning
• On Joint Learning for Solving Placement and Routing in Chip Design
• Quantum imaginary time evolution steered by reinforcement learning
• Operationally meaningful representations of physical systems in neural networks
• MQT Predictor: Automatic Device Selection with Device-Specific Circuit Compilation for Quantum Computing
• Qibolab: an open-source hybrid quantum operating system
• Hybrid discrete-continuous compilation of trapped-ion quantum circuits with deep reinforcement learning
• Reinforcement learning-based architecture search for quantum machine learning
• Enhancing variational quantum state diagonalization using reinforcement learning techniques
• Optimizing ZX-Diagrams with Deep Reinforcement Learning
• Unitary Synthesis of Clifford+T Circuits with Reinforcement Learning
• Wasserstein Complexity of Quantum Circuits
• Quantum Circuit Optimization through Iteratively Pre-Conditioned Gradient Descent
• SWAP Test for an Arbitrary Number of Quantum States
• Using machine learning for quantum annealing accuracy prediction
• Artificial intelligence for representing and characterizing quantum systems
• Introducing Reduced-Width QNNs, an AI-inspired Ansatz Design Pattern
• Optimizing Quantum Variational Circuits with Deep Reinforcement Learning