Efficient and Robust Entanglement Generation with Deep Reinforcement Learning for Quantum Metrology

TL;DR

This paper introduces a deep reinforcement learning-based method to optimize pulse sequences for rapid entanglement generation in quantum metrology, achieving Heisenberg-limited precision and robustness against atom number variations.

Contribution

It presents a novel DRL approach to optimize entanglement generation, outperforming traditional methods in speed and robustness for quantum measurement applications.

Findings

Achieves Heisenberg-limited scaling in measurement precision.

Pulse sequences along two axes improve robustness against atom number deviations.

The method is efficient and feasible for current experimental setups.

Abstract

Quantum metrology exploits quantum resources and strategies to improve measurement precision of unknown parameters. One crucial issue is how to prepare a quantum entangled state suitable for high-precision measurement beyond the standard quantum limit. Here, we propose a scheme to find optimal pulse sequence to accelerate the one-axis twisting dynamics for entanglement generation with the aid of deep reinforcement learning (DRL). We consider the pulse train as a sequence of $\pi/2$ pulses along one axis or two orthogonal axes, and the operation is determined by maximizing the quantum Fisher information using DRL. Within a limited evolution time, the ultimate precision bounds of the prepared entangled states follow the Heisenberg-limited scalings. These states can also be used as the input states for Ramsey interferometry and the final measurement precisions still follow the Heisenberg-limited scalings. While the pulse train along only one axis is more simple and efficient, the scheme using pulse sequence along two orthogonal axes show better robustness against atom number deviation. Our protocol with DRL is efficient and easy to be implemented in state-of-the-art experiments.