000585442 001__ 585442
000585442 005__ 20250715170756.0
000585442 0247_ $$2doi$$a10.1038/s41598-024-66263-y
000585442 0247_ $$2datacite_doi$$a10.3204/PUBDB-2023-03590
000585442 0247_ $$2altmetric$$aaltmetric:165275955
000585442 0247_ $$2pmid$$apmid:38977749
000585442 0247_ $$2WOS$$aWOS:001271178000014
000585442 0247_ $$2openalex$$aopenalex:W4400411751
000585442 037__ $$aPUBDB-2023-03590
000585442 041__ $$aEnglish
000585442 082__ $$a600
000585442 1001_ $$0P:(DE-H253)PIP1095111$$aKaiser, Jan$$b0$$eCorresponding author
000585442 245__ $$aReinforcement learning-trained optimisers and Bayesian optimisation for online particle accelerator tuning
000585442 260__ $$a[London]$$bMacmillan Publishers Limited, part of Springer Nature$$c2024
000585442 3367_ $$2DRIVER$$aarticle
000585442 3367_ $$2DataCite$$aOutput Types/Journal article
000585442 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1727778840_1369329
000585442 3367_ $$2BibTeX$$aARTICLE
000585442 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000585442 3367_ $$00$$2EndNote$$aJournal Article
000585442 520__ $$aOnline tuning of particle accelerators is a complex optimisation problem that continues to require manual intervention by experienced human operators. Autonomous tuning is a rapidly expanding field of research, where learning-based methods like Bayesian optimisation (BO) hold great promise in improving plant performance and reducing tuning times. At the same time, reinforcement learning (RL) is a capable method of learning intelligent controllers, and recent work shows that RL can also be used to train domain-specialised optimisers in so-called reinforcement learning-trained optimisation (RLO). In parallel efforts, both algorithms have found successful adoption in particle accelerator tuning. Here we present a comparative case study, assessing the performance of both algorithms while providing a nuanced analysis of the merits and the practical challenges involved in deploying them to real-world facilities. Our results will help practitioners choose a suitable learning-based tuning algorithm for their tuning tasks, accelerating the adoption of autonomous tuning algorithms, ultimately improving the availability of particle accelerators and pushing their operational limits.
000585442 536__ $$0G:(DE-HGF)POF4-621$$a621 - Accelerator Research and Development (POF4-621)$$cPOF4-621$$fPOF IV$$x0
000585442 536__ $$0G:(DE-HGF)2020_InternLabs-0011$$aInternLabs-0011 - HIR3X - Helmholtz International Laboratory on Reliability, Repetition, Results at the most advanced X-ray Sources (2020_InternLabs-0011)$$c2020_InternLabs-0011$$x1
000585442 536__ $$0G:(DE-HGF)2020_ZT-I-PF-5-6$$aZT-I-PF-5-6 - Autonomous Accelerator (AA) (2020_ZT-I-PF-5-6)$$c2020_ZT-I-PF-5-6$$x2
000585442 542__ $$2Crossref$$i2024-07-08$$uhttps://creativecommons.org/licenses/by/4.0
000585442 542__ $$2Crossref$$i2024-07-08$$uhttps://creativecommons.org/licenses/by/4.0
000585442 588__ $$aDataset connected to CrossRef, Journals: bib-pubdb1.desy.de
000585442 693__ $$0EXP:(DE-H253)ARES-20200101$$1EXP:(DE-H253)SINBAD-20200101$$5EXP:(DE-H253)ARES-20200101$$aSINBAD$$eAccelerator Research Experiment at SINBAD$$x0
000585442 7001_ $$0P:(DE-H253)PIP1093707$$aXu, Chenran$$b1
000585442 7001_ $$0P:(DE-H253)PIP1087213$$aEichler, Annika$$b2
000585442 7001_ $$0P:(DE-H253)PIP1093488$$aSantamaria Garcia, Andrea$$b3
000585442 7001_ $$0P:(DE-H253)PIP1014315$$aStein, Oliver$$b4
000585442 7001_ $$0P:(DE-H253)PIP1089305$$aBruendermann, Erik$$b5
000585442 7001_ $$0P:(DE-H253)PIP1030512$$aKuropka, Willi$$b6
000585442 7001_ $$0P:(DE-H253)PIP1021528$$aDinter, Hannes$$b7
000585442 7001_ $$0P:(DE-H253)PIP1014786$$aMayet, Frank$$b8
000585442 7001_ $$0P:(DE-H253)PIP1019775$$aVinatier, Thomas$$b9
000585442 7001_ $$0P:(DE-H253)PIP1080380$$aBurkart, Florian$$b10
000585442 7001_ $$0P:(DE-H253)PIP1000212$$aSchlarb, Holger$$b11
000585442 77318 $$2Crossref$$3journal-article$$a10.1038/s41598-024-66263-y$$bSpringer Science and Business Media LLC$$d2024-07-08$$n1$$p15733$$tScientific Reports$$v14$$x2045-2322$$y2024
000585442 773__ $$0PERI:(DE-600)2615211-3$$a10.1038/s41598-024-66263-y$$gVol. 14, no. 1, p. 15733$$n1$$p15733$$tScientific reports$$v14$$x2045-2322$$y2024
000585442 8564_ $$uhttps://www.nature.com/articles/s41598-024-66263-y
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/Article%20Approval%20Service.pdf
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/HTML-Approval_of_scientific_publication.html
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/PDF-Approval_of_scientific_publication.pdf
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/Article%20Approval%20Service.pdf?subformat=pdfa$$xpdfa
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/Publishers%20PDF.pdf$$yOpenAccess
000585442 8564_ $$uhttps://bib-pubdb1.desy.de/record/585442/files/Publishers%20PDF.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000585442 8767_ $$92024-07-08$$a52909833$$d2024-07-08$$eAPC$$jDEAL$$lSpringerNature$$v6.31$$zEinzelnachweis Rechnung SN-2024-01442-b
000585442 8767_ $$92024-07-08$$d2024-07-08$$ePayment fee$$jDEAL$$lSpringerNature$$v0.35$$zMPDL Gebühr
000585442 8767_ $$92024-07-08$$a52909833$$d2024-07-08$$eAPC$$jStorniert$$lSpringerNature$$zDFG OAPK (Projekt)
000585442 8767_ $$92024-07-08$$a52909833$$d2024-07-08$$eAPC$$jZahlung erfolgt$$lSpringerNature$$zDFG OAPK (Projekt)
000585442 909CO $$ooai:bib-pubdb1.desy.de:585442$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1095111$$aDeutsches Elektronen-Synchrotron$$b0$$kDESY
000585442 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1093707$$aExternal Institute$$b1$$kExtern
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1087213$$aDeutsches Elektronen-Synchrotron$$b2$$kDESY
000585442 9101_ $$0I:(DE-588)1043621512$$6P:(DE-H253)PIP1087213$$aEuropean XFEL$$b2$$kXFEL.EU
000585442 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1093488$$aExternal Institute$$b3$$kExtern
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1014315$$aDeutsches Elektronen-Synchrotron$$b4$$kDESY
000585442 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1089305$$aExternal Institute$$b5$$kExtern
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1030512$$aDeutsches Elektronen-Synchrotron$$b6$$kDESY
000585442 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1030512$$aExternal Institute$$b6$$kExtern
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1021528$$aDeutsches Elektronen-Synchrotron$$b7$$kDESY
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1014786$$aDeutsches Elektronen-Synchrotron$$b8$$kDESY
000585442 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1014786$$aExternal Institute$$b8$$kExtern
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1019775$$aDeutsches Elektronen-Synchrotron$$b9$$kDESY
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1080380$$aDeutsches Elektronen-Synchrotron$$b10$$kDESY
000585442 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1000212$$aDeutsches Elektronen-Synchrotron$$b11$$kDESY
000585442 9131_ $$0G:(DE-HGF)POF4-621$$1G:(DE-HGF)POF4-620$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lMaterie und Technologie$$vAccelerator Research and Development$$x0
000585442 9141_ $$y2024
000585442 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000585442 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2023-08-24
000585442 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2023-08-24
000585442 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2023-08-24
000585442 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2023-08-24
000585442 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000585442 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2023-08-24
000585442 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSCI REP-UK : 2022$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-07-29T15:28:26Z
000585442 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-07-29T15:28:26Z
000585442 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-07-29T15:28:26Z
000585442 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18
000585442 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-18
000585442 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
000585442 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
000585442 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
000585442 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
000585442 915pc $$0PC:(DE-HGF)0113$$2APC$$aDEAL: Springer Nature 2020
000585442 9201_ $$0I:(DE-H253)MSK-20120731$$kMSK$$lStrahlkontrollen$$x0
000585442 9201_ $$0I:(DE-H253)MPY1-20170908$$kMPY1$$lBeschleunigerphysik Fachgruppe MPY1$$x1
000585442 9201_ $$0I:(DE-H253)KIT-20130928$$kKIT$$lexterne Institute im Bereich Photon Science$$x2
000585442 980__ $$ajournal
000585442 980__ $$aVDB
000585442 980__ $$aI:(DE-H253)MSK-20120731
000585442 980__ $$aI:(DE-H253)MPY1-20170908
000585442 980__ $$aI:(DE-H253)KIT-20130928
000585442 980__ $$aAPC
000585442 980__ $$aUNRESTRICTED
000585442 9801_ $$aAPC
000585442 9801_ $$aFullTexts
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1201/9780429434358$$uHuang, X. Beam-based correction and optimization for accelerators (Taylor & Francis, 2020).
000585442 999C5 $$1WF Bergan$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.22.054601$$tPhys. Rev. Acceler. Beams$$uBergan, W. F. et al. Online storage ring optimization using dimension-reduction and genetic algorithms. Phys. Rev. Acceler. Beams 22, 054601. https://doi.org/10.1103/PhysRevAccelBeams.22.054601 (2019).$$v22$$y2019
000585442 999C5 $$1X Huang$$2Crossref$$9-- missing cx lookup --$$a10.1016/j.nima.2013.05.046$$p77 -$$tNucl. Instrum. Methods Phys. Res., Sect. A$$uHuang, X., Corbett, J., Safranek, J. & Wu, J. An algorithm for online optimization of accelerators. Nucl. Instrum. Methods Phys. Res., Sect. A 726, 77–83. https://doi.org/10.1016/j.nima.2013.05.046 (2013).$$v726$$y2013
000585442 999C5 $$2Crossref$$uBellman, R. Dynamic Programming (Princeton University Press, 1957).
000585442 999C5 $$2Crossref$$uRoussel, R. et al. Bayesian optimization algorithms for accelerator physics (2024). arXiv:2312.05667.
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.124.124801$$uDuris, J. et al. Bayesian Optimization of a Free-Electron Laser. Phys. Rev. Lett.124 (2020).
000585442 999C5 $$2Crossref$$uHanuka, A. et al. Online tuning and light source control using a physics-informed Gaussian process. In Proceedings of the 33rd Conference on Neural Information Processing Systems (2019).
000585442 999C5 $$1S Jalas$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.126.104801$$p1 -$$tPhys. Rev. Lett.$$uJalas, S. et al. Bayesian optimization of a laser-plasma accelerator. Phys. Rev. Lett. 126, 1. https://doi.org/10.1103/PhysRevLett.126.104801 (2021).$$v126$$y2021
000585442 999C5 $$1R Roussel$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.24.062801$$tPhys. Rev. Accel. Beams$$uRoussel, R., Hanuka, A. & Edelen, A. Multiobjective bayesian optimization for online accelerator tuning. Phys. Rev. Accel. Beams 24, 062801. https://doi.org/10.1103/PhysRevAccelBeams.24.062801 (2021).$$v24$$y2021
000585442 999C5 $$1C Xu$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.26.034601$$tPhys. Rev. Accel. Beams$$uXu, C. et al. Bayesian optimization of the beam injection process into a storage ring. Phys. Rev. Accel. Beams 26, 034601. https://doi.org/10.1103/PhysRevAccelBeams.26.034601 (2023).$$v26$$y2023
000585442 999C5 $$2Crossref$$uMcIntire, M., Cope, T., Ermon, S. & Ratner, D. Bayesian Optimization of FEL Performance at LCLS. In Proceedings of the 7th International Particle Accelerator Conference (2016).
000585442 999C5 $$1T Boltz$$2Crossref$$uBoltz, T. et al. Feedback design for control of the micro-bunching instability based on reinforcement learning. In CERN Yellow Reports: Conference Proceedings 9, 227–227 (2020).$$y2020
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.24.104601$$uSt. John, J. et al. Real-time artificial intelligence for accelerator control: A study at the Fermilab Booster. Phys. Rev. Acceler. Beams 24, 104601 (2021).
000585442 999C5 $$1T Chen$$2Crossref$$uChen, T. et al. Learning to optimize: A primer and a benchmark. J. Mach. Learn. Res. 23, 1–59 (2022).$$y2022
000585442 999C5 $$2Crossref$$uLi, K. & Malik, J. Learning to optimize. In International Conference on Learning Representations (2017).
000585442 999C5 $$2Crossref$$uLi, K. & Malik, J. Learning to optimize neural nets (2017). Preprint available at arXiv:1703.00441.
000585442 999C5 $$2Crossref$$uAndrychowicz, M. et al. Learning to learn by gradient descent by gradient descent. In Proceedings of the 30th Conference on Neural Information Processing Systems (NIPS 2016) (2016).
000585442 999C5 $$1V Kain$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.23.124801$$tPhys. Rev. Acceler. Beams$$uKain, V. et al. Sample-efficient reinforcement learning for CERN accelerator control. Phys. Rev. Acceler. Beams 23, 124801. https://doi.org/10.1103/PhysRevAccelBeams.23.124801 (2020).$$v23$$y2020
000585442 999C5 $$2Crossref$$uKaiser, J., Stein, O. & Eichler, A. Learning-based optimisation of particle accelerators under partial observability without real-world training. In Chaudhuri, K. et al. (eds.) Proceedings of the 39th International Conference on Machine Learning, vol. 162 of Proceedings of Machine Learning Research, 10575–10585 (PMLR, 2022).
000585442 999C5 $$2Crossref$$uPang, X., Thulasidasan, S. & Rybarcyk, L. Autonomous control of a particle accelerator using deep reinforcement learning. In Proceedings of the Machine Learning for Engineering Modeling, Simulation, and Design Workshop at Neural Information Processing Systems 2020 (2020).
000585442 999C5 $$1E Meier$$2Crossref$$9-- missing cx lookup --$$a10.1016/j.nima.2009.09.048$$p629 -$$tNucl. Instrum. Methods Phys. Res., Sect. A$$uMeier, E., Biedron, S., LeBlanc, G., Morgan, M. & Wu, J. Electron beam energy and bunch length feed forward control studies using an artificial neural network at the linac coherent light source. Nucl. Instrum. Methods Phys. Res., Sect. A 610, 629–635. https://doi.org/10.1016/j.nima.2009.09.048 (2009).$$v610$$y2009
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1109/TNS.2016.2543203$$uEdelen, A. L. et al. Neural networks for modeling and control of particle accelerators. IEEE Trans. Nuclear Sci. 63, 878–897. https://doi.org/10.1109/TNS.2016.2543203 (2016). Basically model predictive control accompanied by a nice literature overview.
000585442 999C5 $$1A Scheinker$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.121.044801$$tPhys. Rev. Lett.$$uScheinker, A., Edelen, A., Bohler, D., Emma, C. & Lutman, A. Demonstration of model-independent control of the longitudinal phase space of electron beams in the linac-coherent light source with femtosecond resolution. Phys. Rev. Lett. 121, 044801. https://doi.org/10.1103/PhysRevLett.121.044801 (2018).$$v121$$y2018
000585442 999C5 $$1J Degrave$$2Crossref$$9-- missing cx lookup --$$a10.1038/s41586-021-04301-9$$p414 -$$tNature$$uDegrave, J. et al. Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602, 414–419. https://doi.org/10.1038/s41586-021-04301-9 (2022).$$v602$$y2022
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1088/1741-4326/ac121b$$uSeo, J. et al. Feedforward beta control in the KSTAR tokamak by deep reinforcement learning. Nuclear Fusion 61. https://doi.org/10.1088/1741-4326/ac121b (2021).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1088/1741-4326/ac79be$$uSeo, J. et al. Development of an operation trajectory design algorithm for control of multiple 0D parameters using deep reinforcement learning in KSTAR. Nuclear Fusion 62. https://doi.org/10.1088/1741-4326/ac79be (2022).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.3390/app10093207$$uGuerra-Ramos, D., Trujillo-Sevilla, J. & Rodríguez-Ramos, J. M. Towards piston fine tuning of segmented mirrors through reinforcement learning. Appl. Sci. (Switzerland)10. https://doi.org/10.3390/app10093207 (2020).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1051/0004-6361/202243311$$uNousiainen, J. et al. Toward on-sky adaptive optics control using reinforcement learning: Model-based policy optimization for adaptive optics. Astron. Astrophysi. 664. https://doi.org/10.1051/0004-6361/202243311 (2022).
000585442 999C5 $$1S Yatawatta$$2Crossref$$9-- missing cx lookup --$$a10.1093/mnras/stab1401$$p2141 -$$tMon. Not. R. Astron. Soc.$$uYatawatta, S. & Avruch, I. M. Deep reinforcement learning for smart calibration of radio telescopes. Mon. Not. R. Astron. Soc. 505, 2141–2150. https://doi.org/10.1093/mnras/stab1401 (2021).$$v505$$y2021
000585442 999C5 $$1Z Zhou$$2Crossref$$9-- missing cx lookup --$$a10.1021/acscentsci.7b00492$$p1337 -$$tACS Cent. Sci.$$uZhou, Z., Li, X. & Zare, R. N. Optimizing chemical reactions with deep reinforcement learning. ACS Cent. Sci. 3, 1337–1344. https://doi.org/10.1021/acscentsci.7b00492 (2017).$$v3$$y2017
000585442 999C5 $$1JR Deneault$$2Crossref$$9-- missing cx lookup --$$a10.1557/s43577-021-00051-1$$p566 -$$tMRS Bull.$$uDeneault, J. R. et al. Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer. MRS Bull. 46, 566–575. https://doi.org/10.1557/s43577-021-00051-1 (2021).$$v46$$y2021
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1109/ECC.2016.7810598$$uAbdelrahman, H., Berkenkamp, F., Poland, J. & Krause, A. Bayesian optimization for maximum power point tracking in photovoltaic power plants. In 2016 European Control Conference (ECC), 2078–2083, https://doi.org/10.1109/ECC.2016.7810598 (Institute of Electrical and Electronics Engineers Inc., 2016).
000585442 999C5 $$1Y Xiong$$2Crossref$$9-- missing cx lookup --$$a10.2514/1.T5774$$p37 -$$tJ. Thermophys. Heat Transfer$$uXiong, Y., Guo, L., Huang, Y. & Chen, L. Intelligent thermal control strategy based on reinforcement learning for space telescope. J. Thermophys. Heat Transfer 34, 37–44. https://doi.org/10.2514/1.T5774 (2020).$$v34$$y2020
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1115/1.4051072$$uXiong, Y., Guo, L. & Tian, D. Application of deep reinforcement learning to thermal control of space telescope. J. Thermal Sci. Eng. Appl. 14. https://doi.org/10.1115/1.4051072 (2022).
000585442 999C5 $$1A Baheri$$2Crossref$$9-- missing cx lookup --$$a10.1016/j.conengprac.2017.09.007$$p131 -$$tControl. Eng. Pract.$$uBaheri, A., Bin-Karim, S., Bafandeh, A. & Vermillion, C. Real-time control using Bayesian optimization: A case study in airborne wind energy systems. Control. Eng. Pract. 69, 131–140. https://doi.org/10.1016/j.conengprac.2017.09.007 (2017).$$v69$$y2017
000585442 999C5 $$1L Maggi$$2Crossref$$9-- missing cx lookup --$$a10.1109/JSAC.2021.3078490$$p1858 -$$tIEEE J. Sel. Areas Commun.$$uMaggi, L., Valcarce, A. & Hoydis, J. Bayesian optimization for radio resource management: Open loop power control. IEEE J. Sel. Areas Commun. 39, 1858–1871. https://doi.org/10.1109/JSAC.2021.3078490 (2021).$$v39$$y2021
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1145/3408308.3427986$$uDing, X., Du, W. & Cerpa, A. E. MB2C: Model-based deep reinforcement learning for multi-zone building control. In BuildSys 2020 - Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 50–59, https://doi.org/10.1145/3408308.3427986 (Association for Computing Machinery, Inc, 2020).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1016/j.egyai.2022.100202$$uNweye, K., Liu, B., Stone, P. & Nagy, Z. Real-world challenges for multi-agent reinforcement learning in grid-interactive buildings. Energy AI 10. https://doi.org/10.1016/j.egyai.2022.100202 (2022).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.3390/instruments5030028$$uPanofski, E. et al. Commissioning results and electron beam characterization with the S-band photoinjector at SINBAD-ARES. Instruments 5 (2021).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/JACoW-LINAC2022-THPOJO01$$uBurkart, F. et al. The ARES Linac at DESY. In Proceedings of the 31st International Linear Accelerator Conference (LINAC’22), no. 31 in International Linear Accelerator Conference, 691–694, https://doi.org/10.18429/JACoW-LINAC2022-THPOJO01 (JACoW Publishing, Geneva, Switzerland, 2022).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.7551/mitpress/3206.001.0001$$uRasmussen, C. E. & Williams, C. K. I. Gaussian Processes for Machine Learning (The MIT Press, 2005).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1093/comjnl/7.4.308$$uNelder, J. A. & Mead, R. A simplex method for function minimization. Comput. J. 7 (1965).
000585442 999C5 $$1A Scheinker$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevSTAB.16.102803$$tPhys. Rev. ST Accel. Beams$$uScheinker, A., Pang, X. & Rybarcyk, L. Model-independent particle accelerator tuning. Phys. Rev. ST Accel. Beams 16, 102803. https://doi.org/10.1103/PhysRevSTAB.16.102803 (2013).$$v16$$y2013
000585442 999C5 $$2Crossref$$uHwang, K. et al. Prior-mean-assisted bayesian optimization application on frib front-end tunning (2022). arXiv:2211.06400.
000585442 999C5 $$2Crossref$$uBoltz, T. et al. More sample-efficient tuning of particle accelerators with bayesian optimization and prior mean models (2024). arXiv:2403.03225.
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.27.054601$$uKaiser, J., Xu, C., Eichler, A. & Santamaria Garcia, A. Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations. Phys. Rev. Acceler. Beams (2024).
000585442 999C5 $$2Crossref$$uDulac-Arnold, G., Mankowitz, D. & Hester, T. Challenges of real-world reinforcement learning. In Proceedings of the 36th International Conference on Machine Learning (2019).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1109/IROS.2017.8202133$$uTobin, J. et al. Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 23–30. https://doi.org/10.1109/IROS.2017.8202133 (2017).
000585442 999C5 $$2Crossref$$uOpenAI et al. Solving Rubik’s cube with a robot hand (2019). Preprint available at arXiv:1910.07113.
000585442 999C5 $$1R Roussel$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevLett.128.204801$$tPhys. Rev. Lett.$$uRoussel, R. et al. Differentiable preisach modeling for characterization and optimization of particle accelerator systems with hysteresis. Phys. Rev. Lett. 128, 204801. https://doi.org/10.1103/PhysRevLett.128.204801 (2022).$$v128$$y2022
000585442 999C5 $$1R Roussel$$2Crossref$$9-- missing cx lookup --$$a10.1038/s41467-021-25757-3$$p5612 -$$tNat. Commun.$$uRoussel, R. et al. Turn-key constrained parameter space exploration for particle accelerators using bayesian active learning. Nat. Commun. 12, 5612 (2021).$$v12$$y2021
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/JACoW-IPAC2023-THPL028$$uXu, C. et al. Bayesian optimization for SASE tuning at the European XFEL. In Proc. IPAC’23, no. 14 in IPAC’23 - 14th International Particle Accelerator Conference, 4483–4486, https://doi.org/10.18429/JACoW-IPAC2023-THPL028 (JACoW Publishing, Geneva, Switzerland, 2023).
000585442 999C5 $$1J Kirschner$$2Crossref$$9-- missing cx lookup --$$a10.1103/PhysRevAccelBeams.25.062802$$tPhys. Rev. Accel. Beams$$uKirschner, J. et al. Tuning particle accelerators with safety constraints using bayesian optimization. Phys. Rev. Accel. Beams 25, 062802. https://doi.org/10.1103/PhysRevAccelBeams.25.062802 (2022).$$v25$$y2022
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/JACoW-IPAC-2023-THPL029$$uXu, C. et al. Beam trajectory control with lattice-agnostic reinforcement learning. In Proc. IPAC’23, https://doi.org/10.18429/JACoW-IPAC-2023-THPL029 (2023).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/JACoW-IPAC2023-THPL038$$uHirlaender, S. et al. Ultra fast reinforcement learning demonstrated at cern awake. In Proc. IPAC’23, no. 14 in IPAC’23 - 14th International Particle Accelerator Conference, 4510–4513, https://doi.org/10.18429/JACoW-IPAC2023-THPL038 (JACoW Publishing, Geneva, Switzerland, 2023).
000585442 999C5 $$2Crossref$$uKrause, A. & Ong, C. Contextual Gaussian process bandit optimization. In Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F. & Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 24 (Curran Associates, Inc., 2011).
000585442 999C5 $$2Crossref$$uNyikosa, F. M., Osborne, M. A. & Roberts, S. J. Bayesian optimization for dynamic problems (2018). Preprint available at arXiv:1803.03432.
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/jacow-ipac2023-thpl007$$uKuklev, N., Sun, Y., Shang, H., Borland, M. & Fystro, G. I. Robust adaptive bayesian optimization. In Proc. IPAC’23, no. 14 in IPAC’23 - 14th International Particle Accelerator Conference, 4377–4380, https://doi.org/10.18429/jacow-ipac2023-thpl007 (JACoW Publishing, Geneva, Switzerland, 2023).
000585442 999C5 $$2Crossref$$uStein, O., Kaiser, J. & Eichler, A. Accelerating linear beam dynamics simulations for machine learning applications. In Proceedings of the 13th International Particle Accelerator Conference (2022).
000585442 999C5 $$2Crossref$$uKaiser, J. & Xu, C. Cheetah (2023).
000585442 999C5 $$2Crossref$$uBrockman, G. et al. OpenAI Gym (2016).
000585442 999C5 $$1M Towers$$2Crossref$$9-- missing cx lookup --$$a10.5281/zenodo.8127026$$tGymnasium$$uTowers, M. et al. Gymnasiumhttps://doi.org/10.5281/zenodo.8127026 (2023).$$y2023
000585442 999C5 $$2Crossref$$uFujimoto, S., van Hoof, H. & Meger, D. Addressing function approximation error in actor-critic methods (2018). Preprint available at arXiv:1802.09477v3.
000585442 999C5 $$2Crossref$$uRaffin, A. et al. Stable Baselines3 (2019).
000585442 999C5 $$2Crossref$$uBalandat, M. et al. BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization. In Advances in Neural Information Processing Systems 33 (2020).
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.1007/978-1-4615-7892-5$$uMatérn, B. Spatial Variation, vol. 36 (Springer New York, 1986), 2 edn.
000585442 999C5 $$1DR Jones$$2Crossref$$9-- missing cx lookup --$$a10.1023/A:1008306431147$$p455 -$$tJ. Global Optim.$$uJones, D. R., Schonlau, M. & Welch, W. J. Efficient global optimization of expensive black-box functions. J. Global Optim. 13, 455–492. https://doi.org/10.1023/A:1008306431147 (1998).$$v13$$y1998
000585442 999C5 $$2Crossref$$9-- missing cx lookup --$$a10.18429/jacow-ipac2023-thpl164$$uRoussel, R., Edelen, A., Bartnik, A. & Mayes, C. Xopt: A simplified framework for optimization of accelerator problems using advanced algorithms. In Proc. IPAC’23, no. 14 in IPAC’23 - 14th International Particle Accelerator Conference, 4796–4799, https://doi.org/10.18429/jacow-ipac2023-thpl164 (JACoW Publishing, Geneva, Switzerland, 2023).
000585442 999C5 $$2Crossref$$uFundamental Algorithms for Scientific Computing in Python. Virtanen, P. et al. SciPy 1.0. Nat. Methods17, 261–272 (2020).
000585442 999C5 $$1A Scheinker$$2Crossref$$9-- missing cx lookup --$$a10.1109/TCST.2021.3136133$$p2261 -$$tIEEE Trans. Control Syst. Technol.$$uScheinker, A., Huang, E.-C. & Taylor, C. Extremum seeking-based control system for particle accelerator beam loss minimization. IEEE Trans. Control Syst. Technol. 30, 2261–2268. https://doi.org/10.1109/TCST.2021.3136133 (2022).$$v30$$y2022