TY - JOUR
AU - Kaiser, Jan
AU - Xu, Chenran
AU - Eichler, Annika
AU - Santamaria Garcia, Andrea
AU - Stein, Oliver
AU - Bruendermann, Erik
AU - Kuropka, Willi
AU - Dinter, Hannes
AU - Mayet, Frank
AU - Vinatier, Thomas
AU - Burkart, Florian
AU - Schlarb, Holger
TI - Reinforcement learning-trained optimisers and Bayesian optimisation for online particle accelerator tuning
JO - Scientific reports
VL - 14
IS - 1
SN - 2045-2322
CY - [London]
PB - Macmillan Publishers Limited, part of Springer Nature
M1 - PUBDB-2023-03590
SP - 15733
PY - 2024
AB - Online tuning of particle accelerators is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods like Bayesian optimisation (BO) hold great promise in improving plant performance and reducing tuning times. At the same time, reinforcement learning (RL) is a capable method of learning intelligent controllers, and recent work shows that RL can also be used to train domain-specialised optimisers in so-called reinforcement learning-trained optimisation (RLO). In parallel efforts, both algorithms have found successful adoption in particle accelerator tuning. Here we present a comparative case study, assessing the performance of both algorithms while providing a nuanced analysis of the merits and the practical challenges involved in deploying them to real-world facilities. Our results will help practitioners choose a suitable learning-based tuning algorithm for their tuning tasks, accelerating the adoption of autonomous tuning algorithms, ultimately improving the availability of particle accelerators and pushing their operational limits.
LB - PUB:(DE-HGF)16
C6 - pmid:38977749
UR - <Go to ISI:>//WOS:001271178000014
DO - DOI:10.1038/s41598-024-66263-y
UR - https://bib-pubdb1.desy.de/record/585442
ER -