{"id":"https://openalex.org/W4413318779","doi":"https://doi.org/10.1109/tase.2025.3600504","title":"Autonomous PID Tuning: Two-Phase Reinforcement Learning Through Adversarial Imitation Learning Under Imperfect Demonstrations","display_name":"Autonomous PID Tuning: Two-Phase Reinforcement Learning Through Adversarial Imitation Learning Under Imperfect Demonstrations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413318779","doi":"https://doi.org/10.1109/tase.2025.3600504"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3600504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3600504","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5109218574","display_name":"G. Jounghyun Kim","orcid":"https://orcid.org/0009-0001-4321-9147"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gon Kim","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079106943","display_name":"Kyuchang Chang","orcid":"https://orcid.org/0000-0003-1928-9417"},"institutions":[{"id":"https://openalex.org/I70591777","display_name":"Jeonju University","ror":"https://ror.org/015v9d997","country_code":"KR","type":"education","lineage":["https://openalex.org/I70591777"]},{"id":"https://openalex.org/I83202590","display_name":"Jeju National University","ror":"https://ror.org/05hnb4n85","country_code":"KR","type":"education","lineage":["https://openalex.org/I83202590"]},{"id":"https://openalex.org/I4210165782","display_name":"Jeju National University Hospital","ror":"https://ror.org/05p64mb74","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I4210165782","https://openalex.org/I83202590"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuchang Chang","raw_affiliation_strings":["Department of Software, Jeju National University, Jeju, South Korea","Department of Software, Jeju University, Jeju, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Software, Jeju National University, Jeju, South Korea","institution_ids":["https://openalex.org/I83202590"]},{"raw_affiliation_string":"Department of Software, Jeju University, Jeju, South Korea","institution_ids":["https://openalex.org/I70591777","https://openalex.org/I83202590","https://openalex.org/I4210165782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058569502","display_name":"Yunseon Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunseon Byun","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021164528","display_name":"Jun\u2010Geol Baek","orcid":"https://orcid.org/0000-0002-7088-1478"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Geol Baek","raw_affiliation_strings":["Department of Industrial and Management Engineering, Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109218574"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.7428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76475768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":null,"first_page":"20280","last_page":"20295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12495","display_name":"Electrostatic Discharge in Electronics","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12495","display_name":"Electrostatic Discharge in Electronics","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9822999835014343,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.6681811809539795},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6512132287025452},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.6476719975471497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5770920515060425},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5691371560096741},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5211229920387268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.451504111289978},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.41760382056236267},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.27748292684555054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.27234649658203125},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2704755365848541},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14114955067634583},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.07567819952964783}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6681811809539795},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6512132287025452},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.6476719975471497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5770920515060425},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5691371560096741},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5211229920387268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.451504111289978},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41760382056236267},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27748292684555054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27234649658203125},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2704755365848541},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14114955067634583},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.07567819952964783},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3600504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3600504","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G6048335315","display_name":null,"funder_award_id":"NRF-2022R1A2C2004457","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2076337359","https://openalex.org/W2140246545","https://openalex.org/W2165726932","https://openalex.org/W2898018938","https://openalex.org/W2904246096","https://openalex.org/W2954878698","https://openalex.org/W2963099939","https://openalex.org/W3015921997","https://openalex.org/W3135940841","https://openalex.org/W3155878512","https://openalex.org/W3173562687","https://openalex.org/W3185464543","https://openalex.org/W3211847530","https://openalex.org/W4220737776","https://openalex.org/W4226257065","https://openalex.org/W4280520192","https://openalex.org/W4285184150","https://openalex.org/W4308459823","https://openalex.org/W4310541177","https://openalex.org/W4312639427","https://openalex.org/W4315471897","https://openalex.org/W4324144157","https://openalex.org/W4379881949","https://openalex.org/W4383112908","https://openalex.org/W4384916966","https://openalex.org/W4386034812","https://openalex.org/W4388469888","https://openalex.org/W4390823570","https://openalex.org/W4391551585","https://openalex.org/W4400770903","https://openalex.org/W4403158459","https://openalex.org/W4405907436"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2892258405"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2,110],"stable":[3,66,128],"reinforcement":[4,47],"learning":[5,9,13,32,48,158],"through":[6],"adversarial":[7,30],"imitation":[8,31],"(SRAIL),":[10],"a":[11],"two-phase":[12],"framework":[14],"for":[15,166],"automatic":[16,83],"proportional":[17],"integral":[18],"derivative":[19],"(PID)":[20],"tuning":[21,84,90],"in":[22,85,155,170],"the":[23,56,71,104,114,132,141,156],"absence":[24,133],"of":[25,70,100,108,134,144,168],"high-quality":[26,135],"demonstration":[27,44,77,136],"data.":[28,45],"First,":[29],"(AIL)":[33],"is":[34,62],"used":[35],"to":[36,54,64,95],"learn":[37],"an":[38],"initial":[39,52,157],"control":[40,59,129],"policy":[41,53],"using":[42],"imperfect":[43,76],"Subsequently,":[46],"(RL)":[49],"refines":[50],"this":[51],"derive":[55],"optimal":[57],"PID":[58,89],"policy.":[60],"SRAIL":[61,122,151],"designed":[63],"ensure":[65],"and":[67,82,98,138,162],"safe":[68],"exploration":[69,154],"RL":[72,109,169],"agent,":[73],"even":[74],"with":[75],"data,":[78],"thereby":[79],"enabling":[80],"efficient":[81],"industrial":[86,172],"environments.":[87,173],"Conventional":[88],"methods":[91],"are":[92],"time-consuming":[93],"owing":[94],"system":[96],"complexity":[97],"lack":[99],"prior":[101],"knowledge.":[102],"Furthermore,":[103],"random":[105,153],"exploratory":[106],"nature":[107],"significant":[111],"risks":[112],"during":[113],"early":[115],"training":[116],"phase,":[117,159],"limiting":[118],"its":[119,164],"practical":[120],"application.":[121],"addresses":[123],"these":[124],"challenges":[125],"by":[126,139],"ensuring":[127,160],"performance":[130],"despite":[131],"data":[137],"enhancing":[140],"convergence":[142],"speed":[143],"RL.":[145],"The":[146],"experimental":[147],"results":[148],"demonstrate":[149],"that":[150],"minimizes":[152],"safety,":[161],"highlighting":[163],"potential":[165],"implementation":[167],"real-world":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}