Journal Article

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

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

2023

Overview

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. Real-time feedback control of quantum systems without relying on a description of the system itself is usually challenging. Here, the authors exploit deep reinforcement learning to realise feedback control for initialisation of a superconducting qubit on a submicrosecond timescale.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 639/766/483/2802 / 639/766/483/481 / Control systems / Deep learning / Feedback / Feedback control / Field programmable gate arrays / Humanities and Social Sciences / Latency / Learning / multidisciplinary / Neural networks / Quantum theory / Qubits (quantum computing) / Real time / Reinforcement / Science / Science (multidisciplinary) / Superconductivity