000607018 001__ 607018
000607018 005__ 20250221092211.0
000607018 020__ $$a978-3-95450-247-9
000607018 0247_ $$2doi$$a10.18429/JACOW-IPAC2024-TUPS60
000607018 0247_ $$2datacite_doi$$a10.3204/PUBDB-2024-01723
000607018 037__ $$aPUBDB-2024-01723
000607018 041__ $$aEnglish
000607018 1001_ $$0P:(DE-HGF)0$$aHirlaender, Simon$$b0$$eCorresponding author
000607018 1112_ $$a15th International Particle Accelerator Conference$$cNashville$$d2024-05-19 - 2024-05-24$$gIPAC'24$$wUSA
000607018 245__ $$aTowards few-shot reinforcement learning in particle accelerator control
000607018 260__ $$aGeneva, Switzerland$$bJACoW Publishing$$c2024
000607018 29510 $$a[Ebook] 15th International Particle Accelerator Conference, Nashville, Tennessee : May 19-24, 2024, Nashville, Tennessee, USA : proceedings / Pilat, Fulvia ; Andrian, Ivan , [Geneva] : JACoW Publishing, [2024],
000607018 300__ $$a1804 - 1807
000607018 3367_ $$2ORCID$$aCONFERENCE_PAPER
000607018 3367_ $$033$$2EndNote$$aConference Paper
000607018 3367_ $$2BibTeX$$aINPROCEEDINGS
000607018 3367_ $$2DRIVER$$aconferenceObject
000607018 3367_ $$2DataCite$$aOutput Types/Conference Paper
000607018 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1726213868_4150639
000607018 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000607018 500__ $$aLiteraturangaben;
000607018 520__ $$aThis paper addresses the automation of particle accelerator control through reinforcement learning (RL). It highlights the potential to increase reliable performance, especially in light of new diagnostic tools and the increasingly complex variable schedules of specific accelerators. We focus on the physics simulation of the AWAKE electron line, an ideal platform for performing in-depth studies that allow a clear distinction between the problem and the performance of different algorithmic approaches for accurate analysis. The main challenges are the lack of realistic simulations and partially observable environments. We show how effective results can be achieved through meta-reinforcement learning, where an agent is trained to quickly adapt to specific real-world scenarios based on prior training in a simulated environment with variable unknowns. When suitable simulations are lacking or too costly, a model-based method using Gaussian processes is used for direct training in a few shots only. The work opens new avenues for implementing control automation in particle accelerators, significantly increasing their efficiency and adaptability.
000607018 536__ $$0G:(DE-HGF)POF4-621$$a621 - Accelerator Research and Development (POF4-621)$$cPOF4-621$$fPOF IV$$x0
000607018 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
000607018 588__ $$aDataset connected to DataCite
000607018 650_7 $$2Other$$aAccelerator Physics
000607018 650_7 $$2Other$$amc6-beam-instrumentation-controls-feedback-and-operational-aspects - MC6: Beam Instrumentation, Controls, Feedback, and Operational Aspects
000607018 650_7 $$2Other$$aMC6.D13 - MC6.D13 Machine Learning
000607018 693__ $$0EXP:(DE-H253)ARES-20200101$$1EXP:(DE-H253)SINBAD-20200101$$5EXP:(DE-H253)ARES-20200101$$aSINBAD$$eAccelerator Research Experiment at SINBAD$$x0
000607018 7001_ $$0P:(DE-HGF)0$$aPochaba, Sabrina$$b1
000607018 7001_ $$0P:(DE-HGF)0$$aLamminger, Lukas$$b2
000607018 7001_ $$0P:(DE-H253)PIP1095111$$aKaiser, Jan$$b3
000607018 7001_ $$0P:(DE-H253)PIP1093707$$aXu, Chenran$$b4
000607018 7001_ $$0P:(DE-H253)PIP1093488$$aSantamaria Garcia, Andrea$$b5
000607018 7001_ $$0P:(DE-HGF)0$$aScomparin, Luca$$b6
000607018 773__ $$a10.18429/JACOW-IPAC2024-TUPS60
000607018 8564_ $$uhttps://accelconf.web.cern.ch/ipac2024/doi/jacow-ipac2024-tups60/index.html
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/HTML-Approval_of_scientific_publication.html
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/PDF-Approval_of_scientific_publication.pdf
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/Main%20Document.pdf$$yOpenAccess$$zStatID:(DE-HGF)0510
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/Publisher%27s%20PDF.pdf$$yRestricted$$zStatID:(DE-HGF)0599
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/Main%20Document.pdf?subformat=pdfa$$xpdfa$$yOpenAccess$$zStatID:(DE-HGF)0510
000607018 8564_ $$uhttps://bib-pubdb1.desy.de/record/607018/files/Publisher%27s%20PDF.pdf?subformat=pdfa$$xpdfa$$yRestricted$$zStatID:(DE-HGF)0599
000607018 909CO $$ooai:bib-pubdb1.desy.de:607018$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000607018 9101_ $$0I:(DE-588b)2008985-5$$6P:(DE-H253)PIP1095111$$aDeutsches Elektronen-Synchrotron$$b3$$kDESY
000607018 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1093707$$aExternal Institute$$b4$$kExtern
000607018 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1093488$$aExternal Institute$$b5$$kExtern
000607018 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
000607018 9141_ $$y2024
000607018 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000607018 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000607018 9201_ $$0I:(DE-H253)MSK-20120731$$kMSK$$lStrahlkontrollen$$x0
000607018 9201_ $$0I:(DE-H253)KIT-20130928$$kKIT$$lexterne Institute im Bereich Photon Science$$x1
000607018 9201_ $$0I:(DE-H253)CERN-20181204$$kCERN$$lCERN$$x2
000607018 980__ $$acontrib
000607018 980__ $$aVDB
000607018 980__ $$aUNRESTRICTED
000607018 980__ $$acontb
000607018 980__ $$aI:(DE-H253)MSK-20120731
000607018 980__ $$aI:(DE-H253)KIT-20130928
000607018 980__ $$aI:(DE-H253)CERN-20181204
000607018 9801_ $$aFullTexts