{"id":"https://openalex.org/W3156892212","doi":"https://doi.org/10.23919/acc53348.2022.9867376","title":"Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems","display_name":"Singular Perturbation-based Reinforcement Learning of Two-Point Boundary Optimal Control Systems","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W3156892212","doi":"https://doi.org/10.23919/acc53348.2022.9867376","mag":"3156892212"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867376","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867376","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","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/A5069767470","display_name":"Vasanth Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vasanth Reddy","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Blacksburg,VA,USA","Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Blacksburg,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038305381","display_name":"Hoda Eldardiry","orcid":"https://orcid.org/0000-0002-9712-6667"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoda Eldardiry","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Blacksburg,VA,USA","Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Blacksburg,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013572009","display_name":"Almuatazbellah Boker","orcid":"https://orcid.org/0000-0002-9484-7266"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Almuatazbellah Boker","raw_affiliation_strings":["Virginia Tech,Bradley Department of Electrical and Computer Engineering,Blacksburg,VA,USA","Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Bradley Department of Electrical and Computer Engineering,Blacksburg,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069767470"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.5188,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48349835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3323","last_page":"3328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9873999953269958,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9783999919891357,"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":0.7767512798309326},{"id":"https://openalex.org/keywords/singular-perturbation","display_name":"Singular perturbation","score":0.6533629894256592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5283364057540894},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5179542303085327},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.47148486971855164},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.46334606409072876},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4294111728668213},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42452430725097656},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37220901250839233},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3031657934188843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28262948989868164},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.2571083903312683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25032228231430054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17100194096565247},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15071198344230652},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11915934085845947}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7767512798309326},{"id":"https://openalex.org/C165160513","wikidata":"https://www.wikidata.org/wiki/Q7524249","display_name":"Singular perturbation","level":2,"score":0.6533629894256592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5283364057540894},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5179542303085327},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.47148486971855164},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.46334606409072876},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4294111728668213},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42452430725097656},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37220901250839233},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3031657934188843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28262948989868164},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2571083903312683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25032228231430054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17100194096565247},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15071198344230652},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11915934085845947},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867376","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867376","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W601351931","https://openalex.org/W1515224583","https://openalex.org/W1522531528","https://openalex.org/W1547397412","https://openalex.org/W1967965813","https://openalex.org/W1976956127","https://openalex.org/W1983523797","https://openalex.org/W2007641405","https://openalex.org/W2016909703","https://openalex.org/W2037025184","https://openalex.org/W2065264928","https://openalex.org/W2104866363","https://openalex.org/W2121863487","https://openalex.org/W2148439597","https://openalex.org/W2166260591","https://openalex.org/W2257848148","https://openalex.org/W2543834468","https://openalex.org/W2564717627","https://openalex.org/W2731745337","https://openalex.org/W2773318202","https://openalex.org/W2914054366","https://openalex.org/W2945576980","https://openalex.org/W3015548672","https://openalex.org/W3016893731","https://openalex.org/W3027032642","https://openalex.org/W3100727880","https://openalex.org/W4301886962","https://openalex.org/W6632629138"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W4327639758","https://openalex.org/W2116787190","https://openalex.org/W2154304710","https://openalex.org/W2019676381","https://openalex.org/W2623488306","https://openalex.org/W1971902905","https://openalex.org/W2006371715"],"abstract_inverted_index":{"We":[0,50,78],"solve":[1],"the":[2,27,38,47,53,56,62,67,72,86],"problem":[3,31],"of":[4,9,40,55,61],"two-point":[5],"boundary":[6],"optimal":[7,29,64],"control":[8,30,73],"linear":[10],"time-varying":[11,28],"systems":[12],"with":[13],"unknown":[14],"model":[15],"dynamics":[16],"using":[17],"reinforcement":[18],"learning.":[19],"Leveraging":[20],"singular":[21],"perturbation":[22],"theory":[23],"techniques,":[24],"we":[25],"transform":[26],"into":[32],"two":[33],"time-invariant":[34],"subproblems.":[35],"This":[36],"allows":[37],"utilization":[39],"an":[41],"off-policy":[42],"iteration":[43],"method":[44],"to":[45,84],"learn":[46],"controller":[48,58,65],"gains.":[49],"show":[51],"that":[52,60],"performance":[54],"learning-based":[57],"approximates":[59],"model-based":[63],"and":[66],"approximation":[68],"accuracy":[69],"improves":[70],"as":[71],"problem\u2019s":[74],"time":[75],"horizon":[76],"increases.":[77],"also":[79],"provide":[80],"a":[81],"simulation":[82],"example":[83],"verify":[85],"results.":[87]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}