Deep reinforcement learning for efficient measurement of quantum devices

  title={Deep reinforcement learning for efficient measurement of quantum devices},
  author={Vu Nguyen and S. B. Orbell and Dominic T. Lennon and H. Moon and Florian Vigneau and Leon C. Camenzind and L. Yu and Dominik M. Zumb{\"u}hl and G. Andrew D. Briggs and Michael A. Osborne and D. Sejdinovic and Natalia Ares},
  journal={npj Quantum Information},
Deep reinforcement learning is an emerging machine-learning approach that can teach a computer to learn from their actions and rewards similar to the way humans learn from experience. It offers many advantages in automating decision processes to navigate large parameter spaces. This paper proposes an approach to the efficient measurement of quantum devices based on deep reinforcement learning. We focus on double quantum dot devices, demonstrating the fully automatic identification of specific… 
Robust and fast post-processing of single-shot spin qubit detection events with a neural network
A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter, which represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.
Miniaturizing neural networks for charge state autotuning in quantum dots
This paper develops extremely small feed-forward neural networks that can be used to detect charge-state transitions in QD stability diagrams and demonstrates that these neural networks can be trained on synthetic data produced by computer simulations, and robustly transferred to the task of tuning an experimental device into a desired charge state.
Machine learning as an enabler of qubit scalability
  • N. Ares
  • Physics
    Nature Reviews Materials
  • 2021
Intense efforts are underway to produce circuits that integrate a technologically relevant number of qubits. Although qubit control in most material systems is by now mature, device variability is
Confident Sinkhorn Allocation for Pseudo-Labeling
A Confident Sinkhorn Allocation (CSA) is proposed, which assigns labels to only samples with high confidence scores and learns the best label allocation via optimal transport and outperforms the current state-of-the-art in this practically important area.
This paper introduces two new innovations in PBT-style methods that employ trust-region based Bayesian Optimization, enabling full coverage of the high-dimensional mixed hyperparameter search space and shows that using a generational approach, they can also learn both architectures and hyperparameters jointly on-the-fly in a single training run.
Learning Coulomb Diamonds in Large Quantum Dot Arrays
An algorithm is introduced that is able to represent the facets of Coulomb diamonds in quantum dot arrays using the constant-interaction model, and relies only on one-dimensional raster scans to learn a model of the device using regularized maximum likelihood estimation.
Precise atom manipulation through deep reinforcement learning
Atomic-scale manipulation in scanning tunneling microscopy1 has enabled the creation of quantum states of matter based on artificial structures2–4 and extreme miniaturization of computational
Universal Statistical Simulator
This paper presents a quantum computer code for a Galton Board Simulator that is exponentially faster than a classical calculation and can be extended to a universal statistical simulator by removing pegs and altering the left-right ratio for each peg.
Identifying Pauli spin blockade using deep learning
Jonas Schuff1,∗, Dominic T. Lennon, Simon Geyer, David L. Craig, Federico Fedele, Florian Vigneau, Leon C. Camenzind, Andreas V. Kuhlmann, G. Andrew D. Briggs, Dominik M. Zumbühl, Dino Sejdinovic,
A Hybrid Quantum-Classical Algorithm for Robust Fitting
This work proposes a hybrid quantum-classical algorithm for robust fitting that solves a sequence of integer programs and terminates with a global solution or an error bound and represents a concrete application of quantum computing in computer vision.


Reinforcement Learning with Neural Networks for Quantum Feedback
This work shows how a network-based "agent" can discover complete quantum-error-correction strategies, protecting a collection of qubits against noise, and develops two ideas: two-stage learning with teacher/student networks and a reward quantifying the capability to recover the quantum information stored in a multi-qubit system.
Deep reinforcement learning for quantum Szilard engine optimization
This work uses deep reinforcement learning and Chopped Random Basis optimization, to solve an optimization problem based on the insertion of an off-center barrier in a quantum Szilard engine, and shows that using designed protocols for the time dependence of the barrier strength, an equal splitting of the wave function is achieved.
Universal Quantum Control through Deep Reinforcement Learning
A control framework is proposed and an analytic leakage bound is derived to simultaneously optimize the quantum gate-time and gate-fidelity against both leakage and stochastic control errors for a broad family of two-qubit-unitary gates important for quantum simulation of many-electron systems.
Generalizable control for quantum parameter estimation through reinforcement learning
It is demonstrated that reinforcement learning provides an efficient way to identify the controls that can be employed to improve the precision and is highly generalizable, namely the neural network trained under one particular value of the parameter can work for different values within a broad range.
Machine learning techniques for state recognition and auto-tuning in quantum dots
This work proposes a new paradigm for fully automated experimental initialization through a closed-loop system relying on machine learning and optimization techniques, and develops an approach based on convolutional neural networks which is able to “navigate” the huge space of parameters that characterize a complex, quantum system with neither human guidance nor reliance on a detailed description of the device.
Coherent transport of quantum states by deep reinforcement learning
Deep Reinforcement Learning is applied to control coherent transport of quantum states in arrays of quantum dots and it is demonstrated that DRL can solve the control problem in the absence of a known analytical solution even under disturbance conditions.
Open quantum system control based on reinforcement learning
Two modified algorithms based on the cutting-edge reinforcement learning methods for the flip from an initial state to a target one in a quantum spin system are proposed and it can be found that the efficiency of learning is greatly improved.
Efficiently measuring a quantum device using machine learning
This work presents measurements on a quantum dot device performed by a machine learning algorithm in real time, and shows that the algorithm outperforms standard grid scan techniques, reducing the number of measurements required and the measurement time by 3.7 times.
Deep reinforcement learning for quantum gate control
A dueling double deep Q-learning neural network is constructed to find out the optimized time dependence of controllable parameters to implement two typical quantum gates: a single-qu bit Hadamard gate and a two-qubit CNOT gate.
Reinforcement Learning in Different Phases of Quantum Control
This work implements cutting-edge Reinforcement Learning techniques and shows that their performance is comparable to optimal control methods in the task of finding short, high-fidelity driving protocol from an initial to a target state in non-integrable many-body quantum systems of interacting qubits.