{"id":"https://openalex.org/W7124165496","doi":"https://doi.org/10.1109/codit66093.2025.11321229","title":"Online-adaptive PID control using Reinforcement Learning","display_name":"Online-adaptive PID control using Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W7124165496","doi":"https://doi.org/10.1109/codit66093.2025.11321229"},"language":null,"primary_location":{"id":"doi:10.1109/codit66093.2025.11321229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5008159924","display_name":"Detlef Arend","orcid":"https://orcid.org/0000-0002-8315-2346"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Detlef Arend","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany"],"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123048762","display_name":"Amerik Toni Singh Padda","orcid":null},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amerik Toni Singh Padda","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany"],"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025397538","display_name":"Andreas Schwung","orcid":"https://orcid.org/0000-0001-8405-0977"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Schwung","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany"],"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002731863","display_name":"Dorothea Schwung","orcid":null},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Schwung","raw_affiliation_strings":["Hochschule Düsseldorf University of Applied Sciences,Artificial Intelligence and Data Science in Automation Technology,Düsseldorf,Germany"],"affiliations":[{"raw_affiliation_string":"Hochschule Düsseldorf University of Applied Sciences,Artificial Intelligence and Data Science in Automation Technology,Düsseldorf,Germany","institution_ids":["https://openalex.org/I83041830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008159924"],"corresponding_institution_ids":["https://openalex.org/I3130920692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7704608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9261000156402588,"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":0.9261000156402588,"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":0.029600000008940697,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.011599999852478504,"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":0.7111999988555908},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.6348999738693237},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5619999766349792},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.5464000105857849},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4999000132083893},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4925999939441681},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/process-control","display_name":"Process control","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7111999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758000254631042},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.6348999738693237},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.5551999807357788},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4925999939441681},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.43299999833106995},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.41670000553131104},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C167123822","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automatic control","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit66093.2025.11321229","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5382954478263855}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2094387729","https://openalex.org/W2787689390","https://openalex.org/W2944559718","https://openalex.org/W2953016745","https://openalex.org/W2980070341","https://openalex.org/W3023586494","https://openalex.org/W3093856499","https://openalex.org/W3101842714","https://openalex.org/W3168536305","https://openalex.org/W3211847530","https://openalex.org/W4206530644","https://openalex.org/W4226162222","https://openalex.org/W4281669285","https://openalex.org/W4289938462","https://openalex.org/W4292510839","https://openalex.org/W4294692120","https://openalex.org/W4297088081","https://openalex.org/W4382936459"],"related_works":[],"abstract_inverted_index":{"This":[0,20],"paper":[1],"presents":[2],"the":[3,60,82,94],"novel":[4],"RLPID":[5,54],"architecture":[6,83],"for":[7,49,72],"online-adaptive":[8,75],"control,":[9],"which":[10],"combines":[11],"classical":[12,73],"proportional-integral-derivative":[13],"(PID)":[14],"control":[15,31,43,90,110],"with":[16],"reinforcement":[17],"learning":[18],"(RL).":[19],"hybrid":[21,80],"approach":[22],"enables":[23],"dynamic":[24],"online":[25],"adjustment":[26],"of":[27,98],"PID":[28],"parameters":[29],"during":[30],"operation.":[32],"Specifically,":[33],"we":[34],"propose":[35],"a":[36,108],"multi-objective":[37],"reward":[38],"structure":[39],"that":[40],"integrates":[41],"established":[42],"criteria":[44],"and":[45,74,92,102],"analyze":[46],"suitable":[47],"configurations":[48],"different":[50],"system":[51],"dynamics.":[52],"The":[53],"controller":[55],"has":[56],"been":[57],"implemented":[58],"within":[59,93],"open-source":[61],"middleware":[62],"MLPro,":[63],"where":[64],"it":[65],"is":[66],"embedded":[67],"in":[68,88,107],"newly":[69],"developed":[70],"sub-frameworks":[71],"control.":[76],"Owing":[77],"to":[78],"its":[79],"nature,":[81],"can":[84],"be":[85],"used":[86],"both":[87],"traditional":[89],"loops":[91],"Markov":[95],"decision":[96],"process":[97],"RL.":[99],"Its":[100],"effectiveness":[101],"practical":[103],"applicability":[104],"are":[105],"demonstrated":[106],"cascade":[109],"scenario.":[111]},"counts_by_year":[],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2026-01-15T00:00:00"}