{"id":"https://openalex.org/W4285093735","doi":"https://doi.org/10.1080/00207179.2022.2097957","title":"Improved model-free H\u221e control for batch processes via off-policy 2D game Q-learning","display_name":"Improved model-free H\u221e control for batch processes via off-policy 2D game Q-learning","publication_year":2022,"publication_date":"2022-07-12","ids":{"openalex":"https://openalex.org/W4285093735","doi":"https://doi.org/10.1080/00207179.2022.2097957"},"language":"en","primary_location":{"id":"doi:10.1080/00207179.2022.2097957","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2022.2097957","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","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/A5006251003","display_name":"Xueying Jiang","orcid":"https://orcid.org/0000-0001-8828-2687"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Jiang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007392914","display_name":"Min Huang","orcid":"https://orcid.org/0000-0003-3793-968X"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Huang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052689650","display_name":"Hanbin Kuang","orcid":"https://orcid.org/0000-0003-4830-5623"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I90727586","display_name":"Zhejiang University of Finance and Economics","ror":"https://ror.org/055vj5234","country_code":"CN","type":"education","lineage":["https://openalex.org/I90727586"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbin Kuang","raw_affiliation_strings":["School of Economics, Zhejiang University of Finance & Economics, Hangzhou, People\u2019s Republic of China","State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Economics, Zhejiang University of Finance & Economics, Hangzhou, People\u2019s Republic of China","institution_ids":["https://openalex.org/I90727586"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089738672","display_name":"Huiyuan Shi","orcid":"https://orcid.org/0000-0002-3097-0732"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyuan Shi","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, People\u2019s Republic of China","State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, People\u2019s Republic of China","institution_ids":["https://openalex.org/I166846921"]},{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, College of Information Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326915","display_name":"Xingwei Wang","orcid":"https://orcid.org/0000-0003-2856-4716"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Wang","raw_affiliation_strings":["College of Computer Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Northeastern University, Shenyang, People\u2019s Republic of China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007751109","display_name":"Loo Hay Lee","orcid":"https://orcid.org/0000-0001-9359-0027"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Loo Hay Lee","raw_affiliation_strings":["Department of Industrial and Systems Engineering, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007392914"],"corresponding_institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.9049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76945748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"96","issue":"10","first_page":"2447","last_page":"2463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9944000244140625,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9860000014305115,"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/bellman-equation","display_name":"Bellman equation","score":0.6248264312744141},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6148306131362915},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6122211217880249},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5665493011474609},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5458108186721802},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5379678606987},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5215346813201904},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5141830444335938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.507515549659729},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.5057640075683594},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4928755760192871},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4816955029964447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4372323155403137},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4222601056098938},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4017295241355896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24082952737808228},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1224256157875061},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11213970184326172}],"concepts":[{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6248264312744141},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6148306131362915},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6122211217880249},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5665493011474609},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5458108186721802},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5379678606987},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5215346813201904},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5141830444335938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.507515549659729},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.5057640075683594},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4928755760192871},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4816955029964447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4372323155403137},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4222601056098938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4017295241355896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24082952737808228},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1224256157875061},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11213970184326172},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/00207179.2022.2097957","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2022.2097957","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/245286","is_oa":false,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/245286","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Taylor & Francis","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1834587319","display_name":null,"funder_award_id":"71620107003","funder_id":"https://openalex.org/F4320335576","funder_display_name":"Major International Joint Research Programme"},{"id":"https://openalex.org/G6853615381","display_name":null,"funder_award_id":"71601039","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"},{"id":"https://openalex.org/F4320335576","display_name":"Major International Joint Research Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1488674906","https://openalex.org/W1530596433","https://openalex.org/W1614417283","https://openalex.org/W1994199977","https://openalex.org/W2000110725","https://openalex.org/W2005437559","https://openalex.org/W2019338681","https://openalex.org/W2033552200","https://openalex.org/W2045398296","https://openalex.org/W2169109555","https://openalex.org/W2344294935","https://openalex.org/W2484646121","https://openalex.org/W2498694880","https://openalex.org/W2551113280","https://openalex.org/W2580629550","https://openalex.org/W2761756876","https://openalex.org/W2781636116","https://openalex.org/W2787667011","https://openalex.org/W2789465846","https://openalex.org/W2807176303","https://openalex.org/W2886719343","https://openalex.org/W2888901227","https://openalex.org/W2890471261","https://openalex.org/W2896819676","https://openalex.org/W2910599652","https://openalex.org/W2939824672","https://openalex.org/W2962347855","https://openalex.org/W2967813116","https://openalex.org/W2979795810","https://openalex.org/W2979846470","https://openalex.org/W2981970936","https://openalex.org/W3008200810","https://openalex.org/W3092434546","https://openalex.org/W3103939126","https://openalex.org/W3108612728","https://openalex.org/W3135903369","https://openalex.org/W3171786593","https://openalex.org/W3213837598","https://openalex.org/W4214717370","https://openalex.org/W4226287877","https://openalex.org/W4239749515","https://openalex.org/W4248923150"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W2156232164","https://openalex.org/W2025663273","https://openalex.org/W2787184676","https://openalex.org/W2089415692","https://openalex.org/W2171609577","https://openalex.org/W2145363145","https://openalex.org/W4378771262","https://openalex.org/W2361707576","https://openalex.org/W1973039793"],"abstract_inverted_index":{"To":[0],"eliminate":[1],"the":[2,5,30,36,51,67,71,78,83,99,103,106,109,115,122,127],"requirement":[3],"of":[4,70,108,118,126],"precise":[6],"model":[7],"for":[8,20,65],"model-based":[9],"control":[10,16,80],"methods,":[11],"an":[12,56,92],"improved":[13],"modelfree":[14],"H\u221e":[15,73],"method":[17,62],"is":[18,47,63],"designed":[19,72],"batch":[21],"processes":[22],"with":[23],"unknown":[24],"dynamics":[25],"and":[26,35,44,82,105,124],"disturbances.":[27],"Firstly,":[28],"both":[29],"zero-sum":[31],"game":[32,60,95],"value":[33],"function":[34],"Q-function":[37],"are":[38,87,112],"presented":[39],"as":[40],"two-dimensional":[41],"(2D)":[42],"forms,":[43],"their":[45],"relation":[46],"analyzed":[48],"to":[49],"obtain":[50],"model-free":[52],"Bellman":[53],"equation.":[54],"Secondly,":[55],"on":[57],"policy":[58,81,86],"2D":[59,94],"Q-learning":[61,96],"proposed":[64,128],"learning":[66],"optimal":[68],"gains":[69],"controller.":[74],"On":[75],"this":[76],"basis,":[77],"behavior":[79,84],"disturbance":[85],"individually":[88],"applied":[89],"by":[90],"developing":[91],"off-policy":[93,110],"method.":[97],"Subsequently,":[98],"strict":[100],"proof":[101],"about":[102],"convergence":[104],"unbiasedness":[107],"approach":[111],"given.":[113],"Finally,":[114],"simulation":[116],"results":[117],"injection":[119],"velocity":[120],"manifest":[121],"validity":[123],"effectivity":[125],"algorithm.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
