Extreme Spin Squeezing from Deep Reinforcement Learning

TL;DR

This paper demonstrates how deep reinforcement learning can discover efficient pulse sequences to achieve near-extreme spin squeezing at the Heisenberg limit using one-axis twisting interactions, with minimal pulses and practical timescales.

Contribution

It introduces a DRL-based method to find universal pulse rules for nearly extreme spin squeezing, surpassing traditional OAT limitations with minimal control complexity.

Findings

Only 6 pulse pairs needed for up to 10^4 particles.

Time to reach extreme SS comparable to optimal OAT squeezing time.

DRL discovers size-independent universal control rules.

Abstract

Spin squeezing (SS) is a recognized resource for realizing measurement precision beyond the standard quantum limit $\propto 1/\sqrt{N}$. The rudimentary one-axis twisting (OAT) interaction can facilitate SS and has been realized in diverse experiments, but it cannot achieve extreme SS for precision at Heisenberg limit $\propto 1/{N}$. Aided by deep reinforcement learning (DRL), we discover size-independent universal rules for realizing nearly extreme SS with OAT interaction using merely a handful of rotation pulses. More specifically, only 6 pairs of pulses are required for up to $10^4$ particles, while the time taken to reach extreme SS remains on the same order of the optimal OAT squeezing time, which makes our scheme viable for experiments that reported OAT squeezing. This study highlights the potential of DRL for controlled quantum dynamics.