{"id":"https://openalex.org/W4407782396","doi":"https://doi.org/10.1109/tsmc.2025.3539349","title":"Toward Universal Controller: Performance-Aware Self-Optimizing Reinforcement Learning for Discrete-Time Systems With Uncontrollable Factors","display_name":"Toward Universal Controller: Performance-Aware Self-Optimizing Reinforcement Learning for Discrete-Time Systems With Uncontrollable Factors","publication_year":2025,"publication_date":"2025-02-20","ids":{"openalex":"https://openalex.org/W4407782396","doi":"https://doi.org/10.1109/tsmc.2025.3539349"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3539349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3539349","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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":null,"display_name":"Jianfeng Zhang","orcid":"https://orcid.org/0000-0003-1916-4809"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Zhang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1916-4809","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]},{"raw_affiliation_string":"College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340490","display_name":"Haoran Zhang","orcid":"https://orcid.org/0000-0002-6883-1375"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6883-1375","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]},{"raw_affiliation_string":"College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038929132","display_name":"Chunhui Zhao","orcid":"https://orcid.org/0000-0002-0254-5763"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhui Zhao","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0254-5763","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]},{"raw_affiliation_string":"College of Control Science and Engineering, State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4391767838"],"apc_list":null,"apc_paid":null,"fwci":0.7779,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67220996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"55","issue":"5","first_page":"3249","last_page":"3260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9609000086784363,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9609000086784363,"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"}},{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9372000098228455,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9077000021934509,"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":0.7845277190208435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5836889147758484},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5569947957992554},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5259217023849487},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5081615447998047},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.453890323638916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39301982522010803},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3362003564834595},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22866377234458923},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20914199948310852},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.160228431224823},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1591314673423767},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10839724540710449},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0534365177154541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7845277190208435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5836889147758484},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5569947957992554},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5259217023849487},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5081615447998047},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.453890323638916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39301982522010803},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3362003564834595},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22866377234458923},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20914199948310852},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.160228431224823},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1591314673423767},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10839724540710449},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0534365177154541},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3539349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3539349","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1148198825","display_name":null,"funder_award_id":"62125306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4648104307","display_name":null,"funder_award_id":"ICT2024A06","funder_id":"https://openalex.org/F4320326952","funder_display_name":"State Key Laboratory of Industrial Control Technology"},{"id":"https://openalex.org/G5140321009","display_name":null,"funder_award_id":"62450020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5528295948","display_name":null,"funder_award_id":"20242BAB27003","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320326952","display_name":"State Key Laboratory of Industrial Control Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1949543980","https://openalex.org/W2013895638","https://openalex.org/W2035003264","https://openalex.org/W2076337359","https://openalex.org/W2132858840","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2344118647","https://openalex.org/W2767050701","https://openalex.org/W2963614114","https://openalex.org/W2990747716","https://openalex.org/W3019898994","https://openalex.org/W3039138740","https://openalex.org/W3046992251","https://openalex.org/W3100366369","https://openalex.org/W3175254947","https://openalex.org/W3188776388","https://openalex.org/W4214717370","https://openalex.org/W4281252251","https://openalex.org/W4283790903","https://openalex.org/W4285040511","https://openalex.org/W4285215557","https://openalex.org/W4285820445","https://openalex.org/W4292185499","https://openalex.org/W4296913260","https://openalex.org/W4323022540","https://openalex.org/W4382371069","https://openalex.org/W4382568359","https://openalex.org/W4383213778","https://openalex.org/W4385819723","https://openalex.org/W4386522183","https://openalex.org/W4386798114","https://openalex.org/W4389722556","https://openalex.org/W4401446880","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6682889407","https://openalex.org/W6684191040","https://openalex.org/W6741002519","https://openalex.org/W6760955315","https://openalex.org/W6766271513","https://openalex.org/W6777635358","https://openalex.org/W6846634178"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2000675896"],"abstract_inverted_index":{"The":[0,81],"industrial":[1],"system":[2,27,127],"usually":[3],"contains":[4],"not":[5],"only":[6],"controllable":[7],"variables":[8,13],"(CVs)":[9],"but":[10],"also":[11],"uncontrollable":[12],"(unCVs),":[14],"e.g.,":[15],"weather":[16],"conditions":[17],"and":[18,57,64,90,95,146],"friction.":[19],"These":[20],"unCVs":[21,89,100,125,145,186],"have":[22],"a":[23,70,112,134,166],"direct":[24],"impact":[25,46,67,98,123,184],"on":[26,126],"control":[28,39,55,109,115,128,168],"performance.":[29],"Despite":[30],"the":[31,45,52,60,66,86,97,122,142,151,156,173,183,192,196,199,209,213,228,231],"success":[32],"of":[33,42,47,54,59,68,88,99,124,144,185,195,212,230],"current":[34],"deep":[35],"reinforcement":[36],"learning":[37],"(DRL)":[38],"algorithms,":[40],"most":[41,107],"them":[43],"neglect":[44],"unCVs,":[48,69],"which":[49,104,170],"can":[50,171,187],"cause":[51],"deterioration":[53],"performance":[56,116,129],"instability":[58],"system.":[61],"To":[62,190],"perceive":[63,94,121],"eliminate":[65,96],"performance-aware":[71,136],"self-optimizing":[72],"universal":[73,167],"controller":[74,91,147],"(PASOUC)":[75],"is":[76,118,138,162,205],"designed":[77,139],"in":[78],"this":[79,181],"article.":[80],"PASOUC":[82],"aims":[83],"at":[84],"integrating":[85],"representation":[87,143],"design":[92,148],"to":[93,120,140,164,207,226],"under":[101,130,177],"different":[102,131],"conditions,":[103],"goes":[105],"beyond":[106],"existing":[108],"methods.":[110],"Technically,":[111],"historical":[113],"trajectory-inspired":[114],"perceptron":[117],"developed":[119],"conditions.":[132,179],"Subsequently,":[133],"new":[135],"reward":[137],"integrate":[141],"while":[149],"training":[150,160,215],"DRL":[152],"controller.":[153],"In":[154,180],"addition,":[155],"domain":[157],"randomization":[158],"(DR)":[159],"strategy":[161],"employed":[163],"learn":[165],"policy,":[169],"access":[172],"approximate":[174],"optimal":[175],"trajectory":[176],"nonideal":[178],"way,":[182],"be":[188],"eliminated.":[189],"handle":[191],"low":[193],"efficiency":[194],"DR":[197,214],"training,":[198],"policy":[200,219],"improvement-policy":[201],"proximal":[202],"optimization":[203],"(PI-PPO)":[204],"proposed":[206,232],"enhance":[208],"convergence":[210],"speed":[211],"by":[216],"performing":[217],"explicit":[218],"improvement.":[220],"Finally,":[221],"illustrative":[222],"examples":[223],"are":[224],"presented":[225],"demonstrate":[227],"superiority":[229],"method.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}