{"id":"https://openalex.org/W4407950241","doi":"https://doi.org/10.1109/cdc56724.2024.10886857","title":"Decision Boundary Estimation Using Reinforcement Learning for Complex Classification Problems","display_name":"Decision Boundary Estimation Using Reinforcement Learning for Complex Classification Problems","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407950241","doi":"https://doi.org/10.1109/cdc56724.2024.10886857"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005904658","display_name":"Josh Netter","orcid":"https://orcid.org/0009-0001-0566-9024"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Netter","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30334"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30334","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30334"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel Guggenheim School of Aerospace Engineering,Atlanta,GA,USA,30334","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011440992","display_name":"Timothy Walsh","orcid":"https://orcid.org/0009-0000-5013-4996"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy F. Walsh","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,NM,USA,87123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,NM,USA,87123","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075624899","display_name":"Jaideep Ray","orcid":"https://orcid.org/0009-0000-9908-7035"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaideep Ray","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,NM,USA,87123"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,NM,USA,87123","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3396","last_page":"3401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.38339999318122864,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.38339999318122864,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.866716742515564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692568302154541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6392912864685059},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6077420711517334},{"id":"https://openalex.org/keywords/decision-boundary","display_name":"Decision boundary","score":0.5998422503471375},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5304854512214661},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.43812304735183716},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19919586181640625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13808047771453857},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10893753170967102}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.866716742515564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692568302154541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392912864685059},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6077420711517334},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.5998422503471375},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5304854512214661},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.43812304735183716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19919586181640625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13808047771453857},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10893753170967102},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2056805518","https://openalex.org/W2117063635","https://openalex.org/W2119821739","https://openalex.org/W2567758457","https://openalex.org/W2899283552","https://openalex.org/W2964152520","https://openalex.org/W3034603778","https://openalex.org/W3082610291","https://openalex.org/W3093966823","https://openalex.org/W3120333448","https://openalex.org/W4214717370","https://openalex.org/W4292794718","https://openalex.org/W6734517396"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W4310513257","https://openalex.org/W4225319475","https://openalex.org/W2042026454"],"abstract_inverted_index":{"In":[0],"this":[1,100,133],"paper,":[2],"we":[3,102],"propose":[4],"a":[5,10,48,76,92,104],"method":[6],"for":[7,17,80],"quickly":[8,128],"training":[9,55],"binary":[11],"support":[12],"vector":[13],"machine":[14],"(SVM)":[15],"classifier":[16,40,122],"recognizing":[18],"valid":[19],"input":[20],"spaces":[21],"in":[22,138],"high-dimensional,":[23],"highly":[24],"constrained":[25],"systems":[26],"by":[27,57],"using":[28],"reinforcement":[29],"learning":[30],"to":[31,70,85,107,119],"find":[32,54,108],"inputs":[33,109,118],"along":[34],"the":[35,39,43,51,64,73,87,112,121,124],"decision":[36,125],"boundary":[37,126],"of":[38,45,47,68,132],"while":[41],"minimizing":[42],"number":[44],"runs":[46],"simulation":[49],"representing":[50],"system.":[52],"We":[53],"points":[56,69,81],"first":[58],"defining":[59],"an":[60],"optimization":[61],"problem":[62],"where":[63],"action":[65],"space":[66],"consists":[67],"test,":[71],"and":[72,90,114],"reward":[74],"is":[75,127,135],"function":[77],"that":[78,82,110],"searches":[79],"are":[83,91],"close":[84],"violating":[86],"given":[88],"constraints":[89],"sufficient":[93],"distance":[94],"from":[95],"one":[96],"another.":[97],"After":[98],"formulating":[99],"process,":[101],"use":[103,116],"Q-learning":[105],"framework":[106],"maximize":[111],"reward,":[113],"then":[115,136],"these":[117],"train":[120],"so":[123],"well-defined.":[129],"The":[130],"efficacy":[131],"approach":[134],"shown":[137],"simulations.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}