用强化学习提升引力波探测器低频灵敏度，突破噪声瓶颈
Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping
- 用频域奖励的强化学习优化控制回路，消除镜面稳定噪声
- 10-30Hz频段降噪超30倍，部分频段达100倍，超量子极限设计目标
- 适用于现有及未来引力波探测器，也推广至精密仪器控制
提升引力波观测器的低频灵敏度，可开启对中等质量黑洞并合、双黑洞轨道偏心率的研究，并为双中子星并合提供多信使观测预警。当前镜面稳定控制引入有害噪声，是灵敏度提升的主要障碍。本文通过深度回路整形（Deep Loop Shaping）方法，利用频域奖励的强化学习消除了该噪声。在利文斯顿激光干涉仪（LLO）上验证了该方法的有效性：10–30Hz频段控制噪声降低超过30倍，子频段最高达100倍，超越由量子极限驱动的设计目标。结果表明，深度回路整形具有显著提升现有与未来引力波探测器性能的潜力，更广泛适用于精密仪器与控制系统。
原文摘要 · Abstract (English)
Improved low-frequency sensitivity of gravitational wave observatories would unlock study of intermediate-mass black hole mergers, binary black hole eccentricity, and provide early warnings for multi-messenger observations of binary neutron star mergers. Today's mirror stabilization control injects harmful noise, constituting a major obstacle to sensitivity improvements. We eliminated this noise through Deep Loop Shaping, a reinforcement learning method using frequency domain rewards. We proved our methodology on the LIGO Livingston Observatory (LLO). Our controller reduced control noise in the 10--30Hz band by over 30x, and up to 100x in sub-bands surpassing the design goal motivated by the quantum limit. These results highlight the potential of Deep Loop Shaping to improve current and future GW observatories, and more broadly instrumentation and control systems.
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。