Deep reinforcement learning for quantum multiparameter estimation

Abstract

Estimation of physical quantities is at the core of most scientific research and the use of quantum devices promises to enhance its performances. In real scenarios, it is fundamental to consider that the resources are limited and Bayesian adaptive estimation represents a powerful approach to efficiently allocate, during the estimation process, all the available resources. However, this framework relies on the precise knowledge of the system model, retrieved with a fine calibration that often results computationally and experimentally demanding. Here, we introduce a model-free and deep learning-based approach to efficiently implement realistic Bayesian quantum metrology tasks accomplishing all the relevant challenges, without relying on any a-priori knowledge on the system. To overcome this need, a neural network is trained directly on experimental data to learn the multiparameter Bayesian update. Then, the system is set at its optimal working point through feedbacks provided by a reinforcement learning algorithm trained to reconstruct and enhance experiment heuristics of the investigated quantum sensor. Notably, we prove experimentally the achievement of higher estimation performances than standard methods, demonstrating the strength of the combination of these two black-box algorithms on an integrated photonic circuit. This work represents an important step towards fully artificial intelligence-based quantum metrology.

References in corpus (6)

• Experimental realization of sub-shot-noise quantum imaging
• Quantum Metrology for Gravitational Wave Astronomy
• Robust Online Hamiltonian Learning
• Femtosecond laser micromachining for integrated quantum photonics
• Control-enhanced multiparameter quantum estimation
• Non-classical interference in integrated 3D multiports

Cited by in corpus (19)

• Entanglement-enhanced quantum metrology: from standard quantum limit to Heisenberg limit
• Review: Quantum Metrology and Sensing with Many-Body Systems
• Experimental property-reconstruction in a photonic quantum extreme learning machine
• Variational quantum algorithm for experimental photonic multiparameter estimation
• Real-time adaptive estimation of decoherence timescales for a single qubit
• Benchmarking Bayesian quantum estimation
• Quantum reservoir computing for photonic entanglement witnessing
• Optimizing quantum-enhanced Bayesian multiparameter estimation of phase and noise in practical sensors
• Exact Quantum Fisher Matrix Results for Distributed Phases Using Multiphoton Polarization Greenberger Horne Zeilinger States
• A micro-opto-mechanical glass interferometer for megahertz modulation of optical signals
• Framework for Learning and Control in the Classical and Quantum Domains
• Applications of model-aware reinforcement learning in Bayesian quantum metrology
• Model-aware reinforcement learning for high-performance Bayesian experimental design in quantum metrology
• Distributed multi-parameter quantum metrology with a superconducting quantum network
• Quantum multiphase estimation
• Reinforcement Learning for Optimal Control of Spin Magnetometers
• Principles of quantum functional testing
• Memory-enhanced quantum extreme learning machines for characterizing non-Markovian dynamics
• Quantum-Inspired Multi Agent Reinforcement Learning for Exploration Exploitation Optimization in UAV-Assisted 6G Network Deployment