提出抗噪量子多臂老虎机算法，提升真实量子设备上的决策性能。
Towards Noise-Resilient Quantum Multi-Armed and Stochastic Linear Bandits
- 设计抗噪量子蒙特卡洛估计算法，增强噪声环境下奖励估计精度。
- 在多种量子噪声模型下，显著降低后悔值并提升估计准确率。
- 适合关注真实量子设备上强化学习应用的研究者。
量子多臂老虎机（MAB）和随机线性老虎机（SLB）近年来受到广泛关注，因其量子版本可实现相对于经典方法的平方根加速。然而，现有大多数量子MAB算法假设在无噪声电路上使用理想的量子蒙特卡洛（QMC）过程，忽略了当前含噪声中等规模量子（NISQ）设备中的噪声影响。本文研究了一种抗噪的量子蒙特卡洛算法，提升了在查询量子奖励预言机时的估计精度。基于该估计算法，提出了抗噪量子多臂老虎机（QMAB）和量子随机线性老虎机（QSLB）算法，在保持对经典方法优势的同时，增强了在噪声环境下的性能。实验表明，所提方法在多种量子噪声模型下均能提升QMAB的估计准确率并减少后悔值。
原文摘要 · Abstract (English)
Quantum multi-armed bandits (MAB) and stochastic linear bandits (SLB) have recently attracted significant attention, as their quantum counterparts can achieve quadratic speedups over classical MAB and SLB. However, most existing quantum MAB algorithms assume ideal quantum Monte Carlo (QMC) procedures on noise-free circuits, overlooking the impact of noise in current noisy intermediate-scale quantum (NISQ) devices. In this paper, we study a noise-robust QMC algorithm that improves estimation accuracy when querying quantum reward oracles. Building on this estimator, we propose noise-robust QMAB and QSLB algorithms that enhance performance in noisy environments while preserving the advantage over classical methods. Experiments show that our noise-robust approach improves QMAB estimation accuracy and reduces regret under several quantum noise models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。