Improving the dynamics of quantum sensors with reinforcement learning

Abstract

Recently proposed quantum-chaotic sensors achieve quantum enhancements in measurement precision by applying nonlinear control pulses to the dynamics of the quantum sensor while using classical initial states that are easy to prepare. Here, we use the cross-entropy method of reinforcement learning to optimize the strength and position of control pulses. Compared to the quantum-chaotic sensors with periodic control pulses in the presence of superradiant damping, we find that decoherence can be fought even better and measurement precision can be enhanced further by optimizing the control. In some examples, we find enhancements in sensitivity by more than an order of magnitude. By visualizing the evolution of the quantum state, the mechanism exploited by the reinforcement learning method is identified as a kind of spin-squeezing strategy that is adapted to the superradiant damping.

References in corpus (26)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learning phase transitions by confusion
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Reinforcement Learning in Different Phases of Quantum Control
• Active learning machine learns to create new quantum experiments
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Fidelity-based Probabilistic Q-learning for Control of Quantum Systems
• Constructing exact representations of quantum many-body systems with deep neural networks
• Quantum parameter estimation with optimal control
• Control-enhanced multiparameter quantum estimation
• An Efficient Algorithm for Optimizing Adaptive Quantum Metrology Processes
• Classicality of spin states
• Learning in Quantum Control: High-Dimensional Global Optimization for Noisy Quantum Dynamics
• Quantifying Quantumness and the Quest for Queens of Quantum
• Generalizable control for quantum parameter estimation through reinforcement learning
• Quantum error correction for the toric code using deep reinforcement learning
• Experimental Phase Estimation Enhanced By Machine Learning
• Quantum metrology with a quantum-chaotic sensor
• Differential Evolution for Many-Particle Adaptive Quantum Metrology
• Measurement-based adaptation protocol with quantum reinforcement learning
• NMR studies of quantum chaos in a two-qubit kicked top
• Characterization of decohering quantum systems: Machine learning approach
• WKB for a damped spin
• A quantum-chaotic cesium-vapor magnetometer

Cited by in corpus (30)

• Artificial Intelligence and Machine Learning for Quantum Technologies
• Learning Quantum Systems
• Model-Free Quantum Control with Reinforcement Learning
• Entanglement-enhanced quantum metrology: from standard quantum limit to Heisenberg limit
• Using deep learning to understand and mitigate the qubit noise environment
• Neural-Network Heuristics for Adaptive Bayesian Quantum Estimation
• Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks
• Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
• Sub-Quantum Fisher Information
• Generalizable control for multiparameter quantum metrology
• Deep reinforcement learning for quantum Hamiltonian engineering
• Efficient and Robust Entanglement Generation with Deep Reinforcement Learning for Quantum Metrology
• Demonstration of a programmable optical lattice atom interferometer
• Machine classification for probe based quantum thermometry
• Frequentist Parameter Estimation with Supervised Learning
• Detection of entangled states supported by reinforcement learning
• Neural-network-based parameter estimation for quantum detection
• Data-Centric Machine Learning in Quantum Information Science
• A Neural Network Assisted ${}^{171}$Yb${}^{+}$ Quantum Magnetometer
• Framework for Learning and Control in the Classical and Quantum Domains
• Model-aware reinforcement learning for high-performance Bayesian experimental design in quantum metrology
• Reinforcement Learning for Rotation Sensing with Ultracold Atoms in an Optical Lattice
• Applications of model-aware reinforcement learning in Bayesian quantum metrology
• Reinforcement Learning for Optimal Control of Spin Magnetometers
• Research progress of artificial intelligence empowered quantum communication and quantum sensing systems
• Quantum metrology with a non-linear kicked Mach-Zehnder interferometer
• Trade-off between Bagging and Boosting for quantum separability-entanglement classification
• Reinforcement-learning based matterwave interferometer in a shaken optical lattice
• Noise-Resilient Quantum Reinforcement Learning
• Fully differentiable optimization protocols for non-equilibrium steady states