{"id":"https://openalex.org/W7117112261","doi":"https://doi.org/10.1109/tii.2025.3643604","title":"Lexicographically Projected Policy Gradient Reinforcement Learning for Prioritized Multiobjective Process Control Problems","display_name":"Lexicographically Projected Policy Gradient Reinforcement Learning for Prioritized Multiobjective Process Control Problems","publication_year":2025,"publication_date":"2025-12-24","ids":{"openalex":"https://openalex.org/W7117112261","doi":"https://doi.org/10.1109/tii.2025.3643604"},"language":null,"primary_location":{"id":"doi:10.1109/tii.2025.3643604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3643604","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","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/A5020341921","display_name":"Ruiyu Qiu","orcid":"https://orcid.org/0009-0004-2458-049X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyu Qiu","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-2458-049X","affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-7651-795X"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-7651-795X","affiliations":[{"raw_affiliation_string":"Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051097158","display_name":"Guanghui Yang","orcid":"https://orcid.org/0000-0003-1083-3623"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Yang","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110536071","display_name":"Zhijiang Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijiang Shao","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-3016-4658","affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52921582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"3251","last_page":"3262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.6198999881744385,"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":0.6198999881744385,"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":0.07519999891519547,"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":0.05689999833703041,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lexicographical-order","display_name":"Lexicographical order","score":0.8884000182151794},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6104000210762024},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5701000094413757},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5073000192642212},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44279998540878296},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4348999857902527},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.8884000182151794},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6726999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396999955177307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.40689998865127563},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2025.3643604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2025.3643604","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"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 Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2914172257","display_name":null,"funder_award_id":"62120106003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G827929139","display_name":null,"funder_award_id":"62173301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,18,179],"real-world":[1],"industrial":[2],"processes,":[3,113],"there":[4],"are":[5,102,199],"many":[6],"lexicographic":[7,28,87],"multiobjective":[8,88],"problems,":[9,130],"which":[10,35,63],"consist":[11],"of":[12,77,166,213],"conflicting":[13],"subtasks":[14],"with":[15,27,108,120,154,217],"explicit":[16],"priorities.":[17],"the":[19,54,68,72,171,207,211],"past,":[20],"model":[21],"predictive":[22],"control":[23,111],"(MPC)":[24],"is":[25,137],"combined":[26],"optimization":[29,56],"to":[30,91,105,145,169,185],"form":[31],"Lexicographic":[32],"MPC":[33],"(LMPC),":[34],"handles":[36],"priorities":[37,44],"in":[38,47,86,112,127],"a":[39,147],"hierarchical":[40],"manner.":[41],"Although":[42],"higher":[43],"like":[45],"safety":[46],"chemical":[48],"reactions,":[49],"can":[50],"be":[51],"strictly":[52],"maintained,":[53],"recursive":[55],"incurs":[57],"great":[58,69],"burden":[59],"for":[60,95,175],"online":[61,74],"computation,":[62],"makes":[64],"LMPC":[65,221],"impractical.":[66],"Considering":[67],"success,":[70],"especially":[71],"low":[73,109],"computation":[75],"cost":[76],"reinforcement":[78],"learning":[79],"(RL),":[80],"several":[81],"studies":[82],"have":[83],"been":[84],"conducted":[85],"RL":[89,135,159],"(LMORL)":[90],"train":[92],"end-to-end":[93],"policies":[94],"prioritized":[96],"problems.":[97],"However,":[98],"existing":[99],"LMORL":[100,219],"methods":[101],"either":[103],"limited":[104],"discrete":[106],"domains":[107],"precision":[110],"or":[114],"heavily":[115],"reliant":[116],"on":[117],"hyperparameter":[118],"tuning":[119],"prior":[121],"knowledge.":[122],"To":[123],"address":[124],"these":[125],"limitations":[126],"continuous":[128,156],"process":[129],"lexicographically":[131],"projected":[132],"policy":[133,142,149,157],"gradient":[134,143,158,177,187],"(LPPG-RL)":[136],"proposed.":[138],"LPPG-RL":[139,161,181,214],"performs":[140],"sequential":[141],"projections":[144],"identify":[146],"feasible":[148],"update":[150],"direction,":[151],"ensuring":[152],"compatibility":[153],"general":[155],"algorithms.":[160],"employs":[162],"Dykstra's":[163],"projection":[164],"instead":[165],"generic":[167],"solvers":[168],"accelerate":[170],"direction":[172],"search,":[173],"particularly":[174],"high-dimension":[176],"vectors.":[178],"addition,":[180],"introduces":[182],"subproblem":[183],"exploration":[184],"mitigate":[186],"vanishing":[188],"and":[189,196,220],"improve":[190],"training":[191],"stability.":[192],"Furthermore,":[193],"convergence":[194],"proof":[195],"stepsize":[197],"analysis":[198],"provided.":[200],"Finally,":[201],"two":[202],"CSTR":[203],"problems":[204],"serve":[205],"as":[206],"case":[208],"study,":[209],"demonstrating":[210],"effectiveness":[212],"through":[215],"comparisons":[216],"baseline":[218],"methods.":[222]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-12-24T00:00:00"}