arXiv:2210.16715

Realizing a deep reinforcement learning agent discovering real-time feedback control strategies for a quantum system

Kevin Reuer, Jonas Landgraf, Thomas Fösel, James O’Sullivan, Liberto Beltrán, Abdulkadir Akın, Graham J. Norris, Ants Remm, Michael Kerschbaum, Jean-Claude Besse, Florian Marquardt, Andreas J. Wallraff, Christopher Eichler

Published Oct 30, 2022• 3 citations

arXiv HTML PDF

Abstract

To realize the full potential of quantum technologies, finding good strategies to control quantum information processing devices in real time becomes increasingly important. Usually these strategies require a precise understanding of the device itself, which is generally not available. Model-free reinforcement learning circumvents this need by discovering control strategies from scratch without relying on an accurate description of the quantum system. Furthermore, important tasks like state preparation, gate teleportation and error correction need feedback at time scales much shorter than the coherence time, which for superconducting circuits is in the microsecond range. Developing and training a deep reinforcement learning agent able to operate in this real-time feedback regime has been an open challenge. Here, we have implemented such an agent in the form of a latency-optimized deep neural network on a field-programmable gate array (FPGA). We demonstrate its use to efficiently initialize a superconducting qubit into a target state. To train the agent, we use model-free reinforcement learning that is based solely on measurement data. We study the agent's performance for strong and weak measurements, and for three-level readout, and compare with simple strategies based on thresholding. This demonstration motivates further research towards adoption of reinforcement learning for real-time feedback control of quantum devices and more generally any physical system requiring learnable low-latency feedback control.

DOI: 10.3929/ethz-b-000641511

Related papers

Realizing a deep reinforcement learning agent for real-time quantum feedback

Kevin Reuer, Jonas Landgraf, Thomas Fösel +10 more

Realizing the full potential of quantum technologies requires precise real-time control on time scales much shorter than the coherence time. Model-free reinforcement learning promises to discover efficient feedback strategies from scratch without relying on a description of the quantum system. However, developing and training a reinforcement learning agent able to operate in real-time using feedback has been an open challenge. Here, we have implemented such an agent for a single qubit as a sub-microsecond-latency neural network on a field-programmable gate array (FPGA). We demonstrate its use to efficiently initialize a superconducting qubit and train the agent based solely on measurements. Our work is a first step towards adoption of reinforcement learning for the control of quantum devices and more generally any physical device requiring low-latency feedback.

Nature CommunicationsNov 6, 202354 citations

Fast Quantum Gate Design with Deep Reinforcement Learning Using Real-Time Feedback on Readout Signals

Emily Wright, Rogério de Sousa

The design of high-fidelity quantum gates is difficult because it requires the optimization of two competing effects, namely maximizing gate speed and minimizing leakage out of the qubit subspace. We propose a deep reinforcement learning algorithm that uses two agents to address the speed and leakage challenges simultaneously. The first agent constructs the qubit in-phase control pulse using a policy learned from rewards that compensate short gate times. The rewards are obtained at intermediate time steps throughout the construction of a full-length pulse, allowing the agent to explore the landscape of shorter pulses. The second agent determines an out-of-phase pulse to target leakage. Both agents are trained on real-time data from noisy hardware, thus providing model-free gate design that adapts to unpredictable hardware noise. To reduce the effect of measurement classification errors, the agents are trained directly on the readout signal from probing the qubit. We present proof-of-concept experiments by designing X and square root of X gates of various durations on IBM hardware. After just 200 training iterations, our algorithm is able to construct novel control pulses up to two times faster than the default IBM gates, while matching their performance in terms of state fidelity and leakage rate. As the length of our custom control pulses increases, they begin to outperform the default gates. Improvements to the speed and fidelity of gate operations open the way for higher circuit depth in quantum simulation, quantum chemistry and other algorithms on near-term and future quantum devices.

arXiv:2305.01169IEEE International Conference on Quantum Computing and Engineering (QCE)Sep 17, 20234 citations

Reinforcement Learning with Neural Networks for Quantum Feedback

Thomas Fösel, Petru Tighineanu, Talitha Weiss +1 more

Machine learning with artificial neural networks is revolutionizing science.The most advanced challenges require discovering answers autonomously.In the domain of reinforcement learning, control strategies are improved according to a reward function.The power of neural-network-based reinforcement learning has been highlighted by spectacular recent successes such as playing Go, but its benefits for physics are yet to be demonstrated.Here, we show how a network-based "agent" can discover complete quantum-error-correction strategies, protecting a collection of qubits against noise.These strategies require feedback adapted to measurement outcomes.Finding them from scratch without human guidance and tailored to different hardware resources is a formidable challenge due to the combinatorially large search space.To solve this challenge, we develop two ideas: two-stage learning with teacher and student networks and a reward quantifying the capability to recover the quantum information stored in a multiqubit system.Beyond its immediate impact on quantum computation, our work more generally demonstrates the promise of neural-network-based reinforcement learning in physics.

arXiv:1802.05267Physical Review XSep 27, 2018231 citations

Enhanced qubit readout via reinforcement learning

Aniket Chatterjee, Jonathan Schwinger, Yvonne Y. Gao

Measurement is an essential component of robust and practical quantum computation. For superconducting qubits, the measurement process involves the effective manipulation of the joint qubit-resonator dynamics, and it should ideally provide the highest quality for qubit state discrimination with the shortest readout pulse and resonator reset time. Here, we harness model-free reinforcement learning (RL), together with a tailored training environment, to achieve this multifaceted optimization task. Using the IBM quantum device, we demonstrate that the pulse obtained by the RL agent not only successfully achieves state-of-the-art performance, with an assignment error of ( 4.6 ± 0.4 ) × 10 − 3 , but also executes the readout and the subsequent resonator reset almost three times faster than the system’s default process. Furthermore, the learned waveforms are robust against realistic parameter drifts and follow an intuitive form, making them readily implementable on existing hardware with little computational overhead. Our results provide an effective readout strategy to boost the performance of superconducting quantum processors and demonstrate the value of RL in providing optimal and practical solutions for complex quantum information processing tasks.

arXiv:2412.04053Physical Review AppliedMay 22, 202510 citations

Quantum circuit optimization with deep reinforcement learning

Thomas Fösel, Murphy Yuezhen Niu, Florian Marquardt +1 more

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:2103.07585Mar 13, 202169 citations

Towards real-time control of a CartPole system on a quantum computer

Nguyen Truong Thu Ngo, Väinö Mehtola, Jerome Lenssen +4 more

Abstract The application of quantum reinforcement learning to real-time control systems faces significant challenges regarding hardware latency, noise susceptibility, and learning convergence. This work presents an end-to-end investigation of a minimal hybrid quantum–classical agent applied to the CartPole benchmark, addressing the gap between idealized simulation and execution on a physical superconducting quantum processing unit. We demonstrate that a single-qubit agent acts as an effective learning model, and its performance is functionally comparable to a classical actor-critic network even when the training of the hybrid agent is restricted to use parameter-shift for its quantum circuit component. To connect learning to deployment constraints, we map the inference-time trade-off between control-loop rate and measurement shot budget to provide guidance for an eventual real-time control demonstration. The resulting performance matrices show that both inference control frequency and shot count strongly affect balancing stability: higher inference frequencies consistently improve performance, and increasing the shot budget lowers the minimum inference frequency required to achieve near-maximal balancing. These results highlight the importance of finding an optimal medium between shot count and control frequency and developing circuits that are e.g. initial-state invariant. Lastly, we address the critical bottleneck of control latency on noisy intermediate-scale quantum hardware. By bypassing the standard high-level software stack and programming the Zurich Instruments readout electronics directly via command tables, we achieve more than an order-of-magnitude improvement in execution speed on the VTT Q5 processor. These results quantify some of the current boundaries of quantum-assisted control and provide a start for achieving the tens-of-hertz throughput required for real-time closed-loop control feedback.

Machine Learning Science and TechnologyJul 21, 20260 citations