Quantum Stream Learning

TL;DR

This paper introduces a deep reinforcement learning approach for quantum stream learning, enabling real-time decision-making and control of quantum systems under noise, with transfer learning for adaptability, advancing quantum technology applications.

Contribution

It presents a novel deep reinforcement learning framework for streaming quantum data, demonstrating adaptability to noise patterns and enhancing quantum control techniques.

Findings

Reinforcement learning effectively manages streaming quantum data.

The approach adapts to different quantum noise patterns via transfer learning.

Stream learning improves understanding of closed-loop quantum control.

Abstract

The exotic nature of quantum mechanics makes machine learning (ML) be different in the quantum realm compared to classical applications. ML can be used for knowledge discovery using information continuously extracted from a quantum system in a broad range of tasks. The model receives streaming quantum information for learning and decision-making, resulting in instant feedback on the quantum system. As a stream learning approach, we present a deep reinforcement learning on streaming data from a continuously measured qubit at the presence of detuning, dephasing, and relaxation. We also investigate how the agent adapts to another quantum noise pattern by transfer learning. Stream learning provides a better understanding of closed-loop quantum control, which may pave the way for advanced quantum technologies.