% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Kaiser:585442,
author = {Kaiser, Jan and Xu, Chenran and Eichler, Annika and
Santamaria Garcia, Andrea and Stein, Oliver and
Bruendermann, Erik and Kuropka, Willi and Dinter, Hannes and
Mayet, Frank and Vinatier, Thomas and Burkart, Florian and
Schlarb, Holger},
title = {{R}einforcement learning-trained optimisers and {B}ayesian
optimisation for online particle accelerator tuning},
journal = {Scientific reports},
volume = {14},
number = {1},
issn = {2045-2322},
address = {[London]},
publisher = {Macmillan Publishers Limited, part of Springer Nature},
reportid = {PUBDB-2023-03590},
pages = {15733},
year = {2024},
abstract = {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.},
cin = {MSK / MPY1 / KIT},
ddc = {600},
cid = {I:(DE-H253)MSK-20120731 / I:(DE-H253)MPY1-20170908 /
I:(DE-H253)KIT-20130928},
pnm = {621 - Accelerator Research and Development (POF4-621) /
InternLabs-0011 - HIR3X - Helmholtz International Laboratory
on Reliability, Repetition, Results at the most advanced
X-ray Sources $(2020_InternLabs-0011)$ / ZT-I-PF-5-6 -
Autonomous Accelerator (AA) $(2020_ZT-I-PF-5-6)$},
pid = {G:(DE-HGF)POF4-621 / $G:(DE-HGF)2020_InternLabs-0011$ /
$G:(DE-HGF)2020_ZT-I-PF-5-6$},
experiment = {EXP:(DE-H253)ARES-20200101},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:38977749},
UT = {WOS:001271178000014},
doi = {10.1038/s41598-024-66263-y},
url = {https://bib-pubdb1.desy.de/record/585442},
}