Fidelity-based Probabilistic Q-learning for Control of Quantum Systems

Abstract

The balance between exploration and exploitation is a key problem for reinforcement learning methods, especially for Q-learning. In this paper, a fidelity-based probabilistic Q-learning (FPQL) approach is presented to naturally solve this problem and applied for learning control of quantum systems. In this approach, fidelity is adopted to help direct the learning process and the probability of each action to be selected at a certain state is updated iteratively along with the learning process, which leads to a natural exploration strategy instead of a pointed one with configured parameters. A probabilistic Q-learning (PQL) algorithm is first presented to demonstrate the basic idea of probabilistic action selection. Then the FPQL algorithm is presented for learning control of quantum systems. Two examples (a spin- 1/2 system and a lamda-type atomic system) are demonstrated to test the performance of the FPQL algorithm. The results show that FPQL algorithms attain a better balance between exploration and exploitation, and can also avoid local optimal policies and accelerate the learning process.

13 pages, 16 figures

References in corpus (4)

• Quantum reinforcement learning
• Modeling and Control of Quantum Systems: An Introduction
• Robust Online Hamiltonian Learning
• Quantum fidelity and quantum phase transitions in matrix product states

Cited by in corpus (48)

• A high-bias, low-variance introduction to Machine Learning for physicists
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Artificial Intelligence and Machine Learning for Quantum Technologies
• Model-Free Quantum Control with Reinforcement Learning
• When does reinforcement learning stand out in quantum control? A comparative study on state preparation
• Geometric Speed Limit of Accessible Many-Body State Preparation
• Coherent Transport of Quantum States by Deep Reinforcement Learning
• Qutrit-inspired Fully Self-supervised Shallow Quantum Learning Network for Brain Tumor Segmentation
• Deep Reinforcement Learning for Quantum State Preparation with Weak Nonlinear Measurements
• Automatic spin-chain learning to explore the quantum speed limit
• Reinforcement learning for autonomous preparation of Floquet-engineered states: Inverting the quantum Kapitza oscillator
• Glassy Phase of Optimal Quantum Control
• Robust Learning Control Design for Quantum Unitary Transformations
• A Reinforcement Learning approach for Quantum State Engineering
• Realizing a deep reinforcement learning agent discovering real-time feedback control strategies for a quantum system
• Quantum Language Model with Entanglement Embedding for Question Answering
• Reinforcement Learning for Digital Quantum Simulation
• Improving the dynamics of quantum sensors with reinforcement learning
• Machine learning \& artificial intelligence in the quantum domain
• Classifying global state preparation via deep reinforcement learning
• Policy Gradient based Quantum Approximate Optimization Algorithm
• Broken symmetry in a two-qubit quantum control landscape
• Deep reinforcement learning for quantum Hamiltonian engineering
• Stochastic Estimation of Dynamical Variables
• A quantum system control method based on enhanced reinforcement learning
• Accurate phonon blockade detector composed of a quadratically coupled optomechanical system
• Learning Control of Quantum Systems
• Magnetic Field-Based Reward Shaping for Goal-Conditioned Reinforcement Learning
• Robust optimization for quantum reinforcement learning control using partial observations
• Machine Learning for Estimation and Control of Quantum Systems
• Prospects of reinforcement learning for the simultaneous damping of many mechanical modes
• Solving Rubik's Cube via Quantum Mechanics and Deep Reinforcement Learning
• Indoor UAV Navigation to a Rayleigh Fading Source Using Q-Learning
• Noise-Robust End-to-End Quantum Control using Deep Autoregressive Policy Networks
• Push-Pull Optimization of Quantum Controls
• Creation and manipulation of quantized vortices in Bose-Einstein condensates using reinforcement learning
• Designing high-fidelity multi-qubit gates for semiconductor quantum dots through deep reinforcement learning
• Simulating long-range hopping with periodically-driven superconducting qubits
• Reinforcement Learning vs. Gradient-Based Optimisation for Robust Energy Landscape Control of Spin-1/2 Quantum Networks
• Improving robustness of quantum feedback control with reinforcement learning
• Fast quantum gate design with deep reinforcement learning using real-time feedback on readout signals
• A Quantum States Preparation Method Based on Difference-Driven Reinforcement Learning
• Finding Quantum Critical Points with Neural-Network Quantum States
• Deep Reinforcement Learning with Quantum-inspired Experience Replay
• Learning a quantum computer's capability
• Binary Quantum Control Optimization with Uncertain Hamiltonians
• Geometrical versus time-series representation of data in quantum control learning
• Several recent developments in estimation and robust control of quantum systems