{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:43:53Z","timestamp":1782938633835,"version":"3.54.5"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.asoc.2026.115836","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:58:17Z","timestamp":1782431897000},"page":"115836","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Action-attentive deep reinforcement learning for autonomous alignment of beamlines"],"prefix":"10.1016","volume":"202","author":[{"given":"Siyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengran","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1127-8158","authenticated-orcid":false,"given":"Junbin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115836_bib0005","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115836_bib0010","series-title":"CERN Yellow Reports: Conference Proceedings","first-page":"227","article-title":"Feedback design for control of the micro-bunching instability based on reinforcement learning","volume":"vol. 9","author":"Boltz","year":"2020"},{"key":"10.1016\/j.asoc.2026.115836_bib0015","author":"Chen"},{"key":"10.1016\/j.asoc.2026.115836_bib0020","series-title":"MHS\u201995. Proceedings of the Sixth International Symposium on Micro Machine and Human Science","first-page":"39","article-title":"A new optimizer using particle swarm theory","author":"Eberhart","year":"1995"},{"key":"10.1016\/j.asoc.2026.115836_bib0025","doi-asserted-by":"crossref","unstructured":"G. Garc\u00eda, Synchrotron radiation: basics, methods and applications, 2016.","DOI":"10.1080\/0889311X.2016.1203913"},{"key":"10.1016\/j.asoc.2026.115836_bib0030","author":"Guo"},{"key":"10.1016\/j.asoc.2026.115836_bib0035","series-title":"Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence","author":"Holland","year":"1992"},{"key":"10.1016\/j.asoc.2026.115836_bib0040","first-page":"983","article-title":"Beam tuning at the FRIB front end using machine learning","volume":"22","author":"Hwang","year":"2022","journal-title":"Proc. IPAC"},{"key":"10.1016\/j.asoc.2026.115836_bib0045","author":"Kaiser"},{"issue":"2","key":"10.1016\/j.asoc.2026.115836_bib0050","doi-asserted-by":"crossref","DOI":"10.1107\/S1600577524000717","article-title":"Optimization of synchrotron radiation parameters using swarm intelligence and evolutionary algorithms","volume":"31","author":"Karaca","year":"2024","journal-title":"J. Synchrotron Radiat."},{"key":"10.1016\/j.asoc.2026.115836_bib0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.inffus.2022.03.003","article-title":"Exploration in deep reinforcement learning: a survey","volume":"85","author":"Ladosz","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.asoc.2026.115836_bib0060","author":"Lillicrap"},{"key":"10.1016\/j.asoc.2026.115836_bib0065","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1022628806385","article-title":"Self-improving reactive agents based on reinforcement learning, planning and teaching","volume":"8","author":"Lin","year":"1992","journal-title":"Mach. Learn."},{"key":"10.1016\/j.asoc.2026.115836_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2021.105400","article-title":"Reinforcement learning for combinatorial optimization: a survey","volume":"134","author":"Mazyavkina","year":"2021","journal-title":"Comput. Oper. Res."},{"key":"10.1016\/j.asoc.2026.115836_bib0075","series-title":"Proc. 3rd Int. Particle Accelerator Conf.(IPAC\u201912)","first-page":"2837","article-title":"Orbit correction studies using neural networks","author":"Meier","year":"2012"},{"key":"10.1016\/j.asoc.2026.115836_bib0080","author":"Mnih"},{"issue":"7540","key":"10.1016\/j.asoc.2026.115836_bib0085","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.asoc.2026.115836_bib0090","author":"Morris"},{"key":"10.1016\/j.asoc.2026.115836_bib0095","series-title":"Optical System Alignment, Tolerancing, and Verification XIV","first-page":"171","article-title":"On-the-fly optimization of synchrotron beamlines using machine learning","volume":"vol. 12222","author":"Morris","year":"2022"},{"key":"10.1016\/j.asoc.2026.115836_bib0100","author":"Nogueira"},{"issue":"5","key":"10.1016\/j.asoc.2026.115836_bib0105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3453160","article-title":"Hierarchical reinforcement learning: a comprehensive survey","volume":"54","author":"Pateria","year":"2021","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"10.1016\/j.asoc.2026.115836_bib0110","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"10.1016\/j.asoc.2026.115836_bib0115","article-title":"Exploration via hindsight goal generation","volume":"32","author":"Ren","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.asoc.2026.115836_bib0120","article-title":"Application of machine learning in orbital correction of storage ring","volume":"33","author":"Ruichun","year":"2021","journal-title":"High Power Laser Part. Beams"},{"key":"10.1016\/j.asoc.2026.115836_bib0125","author":"Schaul"},{"key":"10.1016\/j.asoc.2026.115836_bib0130","series-title":"Proc. of 17th Int. Conf. on Accelerator and Large Experimental Physics Control Systems (ICALEPCS\u201919)","first-page":"1426","article-title":"Orbit correction with machine learning techniques at the synchrotron light source DELTA","author":"Schirmer","year":"2019"},{"key":"10.1016\/j.asoc.2026.115836_bib0135","series-title":"International Conference on Machine Learning","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"Silver","year":"2014"},{"key":"10.1016\/j.asoc.2026.115836_bib0140","article-title":"Practical Bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.asoc.2026.115836_bib0145","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1008202821328","article-title":"Differential evolution\u2013a simple and efficient heuristic for global optimization over continuous spaces","volume":"11","author":"Storn","year":"1997","journal-title":"J. Glob. Optim."},{"key":"10.1016\/j.asoc.2026.115836_bib0150","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.asoc.2026.115836_bib0155","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1107\/S1600577515001861","article-title":"General method for automatic on-line beamline optimization based on genetic algorithm","volume":"22","author":"Xi","year":"2015","journal-title":"J. Synchrotron Radiat."},{"issue":"1","key":"10.1016\/j.asoc.2026.115836_bib0160","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1107\/S1600577516018117","article-title":"AI-BL1. 0: a program for automatic on-line beamline optimization using the evolutionary algorithm","volume":"24","author":"Xi","year":"2017","journal-title":"J. Synchrotron Radiat."},{"issue":"1","key":"10.1016\/j.asoc.2026.115836_bib0165","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1107\/S1600577522010050","article-title":"Multi-objective genetic algorithm for synchrotron radiation beamline optimization","volume":"30","author":"Zhang","year":"2023","journal-title":"J. Synchrotron Radiat."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012846?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626012846?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:49:19Z","timestamp":1782935359000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626012846"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":33,"alternative-id":["S1568494626012846"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115836","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Action-attentive deep reinforcement learning for autonomous alignment of beamlines","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115836","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115836"}}