Abstract
Improved low-frequency sensitivity of gravitational wave observatories would unlock study of intermediate-mass black hole mergers and binary black hole eccentricity and provide early warnings for multimessenger 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- to 30-hertz band by over 30x and up to 100x in subbands, surpassing the design goal motivated by the quantum limit. These results highlight the potential of Deep Loop Shaping to improve current and future gravitational wave observatories and, more broadly, instrumentation and control systems.
| Original language | English |
|---|---|
| Pages (from-to) | 1012-1015 |
| Number of pages | 4 |
| Journal | Science |
| Volume | 389 |
| Issue number | 6764 |
| DOIs | |
| Publication status | Published - 4 Sept 2025 |
Bibliographical note
Correction (24 October 2025): Reference 16 was inadvertently removed during the review process; it was added backin, and all subsequent references were renumbered. Additionally, the date of experiment was listed incorrectly in themain text and supplementary materials, and one of the non-byline author affiliations in the supplementary materialswas accidentally duplicated; both of these errors were corrected.Fingerprint
Dive into the research topics of 'Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver