{"id":"https://openalex.org/W4414118231","doi":"https://doi.org/10.1109/ccta53793.2025.11151453","title":"Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach","display_name":"Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4414118231","doi":"https://doi.org/10.1109/ccta53793.2025.11151453"},"language":"en","primary_location":{"id":"doi:10.1109/ccta53793.2025.11151453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta53793.2025.11151453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Control Technology and Applications (CCTA)","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/A5020891282","display_name":"Mohammad S. Ramadan","orcid":"https://orcid.org/0000-0003-4850-9714"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad S. Ramadan","raw_affiliation_strings":["Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA,60439"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA,60439","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008166253","display_name":"Mahmoud A. Hayajnh","orcid":"https://orcid.org/0000-0002-0685-5777"},"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":"Mahmoud A. Hayajnh","raw_affiliation_strings":["The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056621190","display_name":"Michael T. Tolley","orcid":"https://orcid.org/0000-0001-7821-7777"},"institutions":[{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Tolley","raw_affiliation_strings":["University of California,Department of Mechanical and Aerospace Engineering,San Diego,CA,USA,92161"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical and Aerospace Engineering,San Diego,CA,USA,92161","institution_ids":["https://openalex.org/I160856358","https://openalex.org/I36258959"]}]},{"author_position":"last","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":["The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology,GA,USA,30332-0150","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8373000025749207},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6365000009536743},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.552299976348877},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5460000038146973},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.47049999237060547},{"id":"https://openalex.org/keywords/stochastic-programming","display_name":"Stochastic programming","score":0.4666999876499176},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4300999939441681},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3991999924182892}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8373000025749207},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5767999887466431},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5532000064849854},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.552299976348877},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.47049999237060547},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37549999356269836},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C7493553","wikidata":"https://www.wikidata.org/wiki/Q1520777","display_name":"Certainty","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2590999901294708},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccta53793.2025.11151453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta53793.2025.11151453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4220965824","display_name":null,"funder_award_id":"CPS-1851588,CPS-2227185,S&AS-1849198,SATC-2231651","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1483307070","https://openalex.org/W1508545910","https://openalex.org/W1993192904","https://openalex.org/W2003967703","https://openalex.org/W2009061689","https://openalex.org/W2052029349","https://openalex.org/W2101051269","https://openalex.org/W2122512809","https://openalex.org/W2123967330","https://openalex.org/W2126736494","https://openalex.org/W2134610525","https://openalex.org/W2135234120","https://openalex.org/W2160067530","https://openalex.org/W2754517384","https://openalex.org/W2822752092","https://openalex.org/W2973229164","https://openalex.org/W4205747042","https://openalex.org/W4214717370","https://openalex.org/W4236076921","https://openalex.org/W4236323066"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2,132],"we":[3,66],"propose":[4],"a":[5,134,139],"framework":[6],"towards":[7],"achieving":[8],"two":[9],"intertwined":[10],"objectives:":[11],"(i)":[12],"equipping":[13],"reinforcement":[14,54,91],"learning":[15,55,92,125],"with":[16,133,143],"active":[17],"exploration":[18,102,107],"and":[19,28,35,38,96,103,108,112,153,166],"deliberate":[20],"information":[21],"gathering,":[22],"such":[23],"that":[24,98],"it":[25],"regulates":[26],"state":[27],"parameter":[29],"uncertainties":[30],"resulting":[31,87],"from":[32],"modeling":[33],"mismatches":[34],"noisy":[36],"sensory;":[37],"(ii)":[39],"overcoming":[40],"the":[41,58,68,73,77,83,86,118,124,131,144],"computational":[42],"intractability":[43],"of":[44,70,76,162],"stochastic":[45,59,78,88],"optimal":[46,60,89,100],"control.":[47],"We":[48,129],"approach":[49,159],"both":[50],"objectives":[51],"by":[52,117],"using":[53],"to":[56,150],"compute":[57],"control":[61,90],"law.":[62],"On":[63,82],"one":[64],"hand,":[65,85],"avoid":[67],"curse":[69],"dimensionality":[71],"prohibiting":[72],"direct":[74],"solution":[75],"dynamic":[79],"programming":[80],"equation.":[81],"other":[84],"agent":[93],"admits":[94],"caution":[95,111],"probing,":[97],"is,":[99],"online":[101],"exploitation.":[104],"Unlike":[105],"fixed":[106],"exploitation":[109],"balance,":[110],"probing":[113],"are":[114],"employed":[115],"automatically":[116],"controller":[119],"in":[120],"real-time,":[121],"even":[122],"after":[123],"process":[126],"is":[127,160],"terminated.":[128],"conclude":[130],"numerical":[135],"simulation,":[136],"illustrating":[137],"how":[138],"Linear":[140],"Quadratic":[141],"Regulator":[142],"certainty":[145],"equivalence":[146],"assumption":[147],"may":[148],"lead":[149],"poor":[151],"performance":[152],"filter":[154],"divergence,":[155],"while":[156],"our":[157],"proposed":[158],"stabilizing,":[161],"an":[163],"acceptable":[164],"performance,":[165],"computationally":[167],"convenient.":[168]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}