{"id":"https://openalex.org/W4417514342","doi":"https://doi.org/10.1088/2632-2153/ae2fa8","title":"Explainable physics-based constraints on reinforcement learning for accelerator optimization","display_name":"Explainable physics-based constraints on reinforcement learning for accelerator optimization","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W4417514342","doi":"https://doi.org/10.1088/2632-2153/ae2fa8"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ae2fa8","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2fa8","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ae2fa8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023643218","display_name":"Jonathan Colen","orcid":"https://orcid.org/0000-0003-4162-0276"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Colen","raw_affiliation_strings":["Joint Institute on Advanced Computing for Environmental Studies, Old Dominion University, Norfolk, VA 23539, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-4162-0276","affiliations":[{"raw_affiliation_string":"Joint Institute on Advanced Computing for Environmental Studies, Old Dominion University, Norfolk, VA 23539, United States of America","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002582478","display_name":"Malachi Schram","orcid":"https://orcid.org/0000-0002-3475-2871"},"institutions":[{"id":"https://openalex.org/I29801172","display_name":"Thomas Jefferson National Accelerator Facility","ror":"https://ror.org/02vwzrd76","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I29801172","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malachi Schram","raw_affiliation_strings":["Computer Science Department, Old Dominion University, Norfolk, VA 23539, United States of America","Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America","Joint Institute on Advanced Computing for Environmental Studies, Old Dominion University, Norfolk, VA 23539, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3475-2871","affiliations":[{"raw_affiliation_string":"Computer Science Department, Old Dominion University, Norfolk, VA 23539, United States of America","institution_ids":["https://openalex.org/I81365321"]},{"raw_affiliation_string":"Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America","institution_ids":["https://openalex.org/I29801172"]},{"raw_affiliation_string":"Joint Institute on Advanced Computing for Environmental Studies, Old Dominion University, Norfolk, VA 23539, United States of America","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043233932","display_name":"Kishansingh Rajput","orcid":"https://orcid.org/0000-0002-4430-9937"},"institutions":[{"id":"https://openalex.org/I29801172","display_name":"Thomas Jefferson National Accelerator Facility","ror":"https://ror.org/02vwzrd76","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I29801172","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishansingh Rajput","raw_affiliation_strings":["Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America","Department of Computer Science, University of Houston, Houston, TX 77204, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America","institution_ids":["https://openalex.org/I29801172"]},{"raw_affiliation_string":"Department of Computer Science, University of Houston, Houston, TX 77204, United States of America","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114658139","display_name":"Armen Kasparian","orcid":null},"institutions":[{"id":"https://openalex.org/I29801172","display_name":"Thomas Jefferson National Accelerator Facility","ror":"https://ror.org/02vwzrd76","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I29801172","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Armen Kasparian","raw_affiliation_strings":["Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science Department, Thomas Jefferson National Accelerator Facility, Newport News, VA 23606, United States of America","institution_ids":["https://openalex.org/I29801172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14468293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"1","first_page":"015005","last_page":"015005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.21289999783039093,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.21289999783039093,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.09510000050067902,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.06279999762773514,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8159000277519226},{"id":"https://openalex.org/keywords/surrogate-model","display_name":"Surrogate model","score":0.4934999942779541},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46639999747276306},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.42260000109672546},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3749000132083893}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8159000277519226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5130000114440918},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1088/2632-2153/ae2fa8","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2fa8","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:digitalcommons.odu.edu:datascience-pubs-1012","is_oa":true,"landing_page_url":"https://digitalcommons.odu.edu/datascience-pubs/12","pdf_url":null,"source":{"id":"https://openalex.org/S4377196314","display_name":"ODU Digital Commons (Old Dominion University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I81365321","host_organization_name":"Old Dominion University","host_organization_lineage":["https://openalex.org/I81365321"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:3f72454386fc412784438db887787982","is_oa":true,"landing_page_url":"https://doaj.org/article/3f72454386fc412784438db887787982","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 7, Iss 1, p 015005 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ae2fa8","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2fa8","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2263355576","display_name":null,"funder_award_id":"DE-AC05\u201306OR23177","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1653517664","https://openalex.org/W1977655452","https://openalex.org/W1979769287","https://openalex.org/W2011892815","https://openalex.org/W2239232218","https://openalex.org/W2327814894","https://openalex.org/W2607839392","https://openalex.org/W2899283552","https://openalex.org/W2902907165","https://openalex.org/W2964145209","https://openalex.org/W2973119841","https://openalex.org/W2981906852","https://openalex.org/W3027004035","https://openalex.org/W3086458503","https://openalex.org/W3093963944","https://openalex.org/W3108809127","https://openalex.org/W3122672375","https://openalex.org/W3123083763","https://openalex.org/W3139004010","https://openalex.org/W3160002411","https://openalex.org/W3163993681","https://openalex.org/W3183976931","https://openalex.org/W4213199992","https://openalex.org/W4283729766","https://openalex.org/W4293077149","https://openalex.org/W4307958945","https://openalex.org/W4311738441","https://openalex.org/W4313259737","https://openalex.org/W4383212980","https://openalex.org/W4384937372","https://openalex.org/W4386285856","https://openalex.org/W4387447711","https://openalex.org/W4390673572","https://openalex.org/W4392910533","https://openalex.org/W4396797875","https://openalex.org/W4399071588","https://openalex.org/W4400411751","https://openalex.org/W4401611165","https://openalex.org/W4402189838","https://openalex.org/W4408556832","https://openalex.org/W4413817852"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"We":[1,79],"present":[2],"a":[3,44,69,84,138],"reinforcement":[4],"learning":[5],"(RL)":[6],"framework":[7],"for":[8,48,148],"optimizing":[9],"particle":[10,87],"accelerator":[11,88,151],"experiments":[12],"that":[13,33,134],"builds":[14],"explainable":[15],"physics-based":[16,139],"constraints":[17],"on":[18,83],"agent":[19,119],"behavior.":[20],"The":[21],"goal":[22],"is":[23],"to":[24,57,92,116,122,145],"increase":[25],"transparency":[26],"and":[27,54],"trust":[28],"by":[29,68,73],"letting":[30],"users":[31],"verify":[32],"the":[34,94,105,109,118,124,135],"agent\u2019s":[35],"decision-making":[36],"process":[37],"incorporates":[38],"suitable":[39],"physics.":[40],"Our":[41],"algorithm":[42,82],"uses":[43,55],"learnable":[45],"surrogate":[46,64,140],"function":[47],"physical":[49],"observables,":[50],"such":[51],"as":[52],"energy,":[53],"them":[56],"fine-tune":[58],"how":[59],"actions":[60],"are":[61,114],"chosen.":[62],"This":[63],"can":[65],"be":[66],"represented":[67],"neural":[70],"network":[71],"or":[72],"an":[74],"interpretable":[75],"sparse":[76],"dictionary":[77],"model.":[78],"test":[80],"our":[81,142],"range":[85],"of":[86,108,127,137],"optimization":[89,152],"environments":[90],"designed":[91],"emulate":[93],"Continuous":[95],"Electron":[96],"Beam":[97],"Accelerator":[98],"Facility":[99],"at":[100],"Jefferson":[101],"Lab.":[102],"By":[103],"examining":[104],"mathematical":[106],"form":[107],"learned":[110,121],"constraint":[111],"function,":[112],"we":[113,132],"able":[115],"confirm":[117],"has":[120],"use":[123],"established":[125],"physics":[126],"each":[128],"environment.":[129],"In":[130],"addition,":[131],"find":[133],"introduction":[136],"enables":[141],"RL":[143],"algorithms":[144],"reliably":[146],"converge":[147],"difficult":[149],"high-dimensional":[150],"environments.":[153]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-12-19T00:00:00"}