{"id":"https://openalex.org/W2979846470","doi":"https://doi.org/10.1109/mmar.2019.8864632","title":"An improved reinforcement learning control strategy for batch processes","display_name":"An improved reinforcement learning control strategy for batch processes","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2979846470","doi":"https://doi.org/10.1109/mmar.2019.8864632","mag":"2979846470"},"language":"en","primary_location":{"id":"doi:10.1109/mmar.2019.8864632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmar.2019.8864632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 24th International Conference on Methods and Models in Automation and Robotics (MMAR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100364172","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-7518-4743"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["School of Engineering, Newcastle University, Newcastle upon Tyne, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685752","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-9745-664X"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["School of Engineering, Newcastle University, Newcastle upon Tyne, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011037821","display_name":"Yang Long","orcid":"https://orcid.org/0000-0002-2445-6112"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Long","raw_affiliation_strings":["School of Computing, Durham University, Durham, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Durham University, Durham, UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031969180","display_name":"Bingzhang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bingzhang Hu","raw_affiliation_strings":["School of Computing, Newcastle University, Newcastle upon Tyne, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Newcastle University, Newcastle upon Tyne, UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6258,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63498303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"36","issue":null,"first_page":"360","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9591000080108643,"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":0.9591000080108643,"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":0.9506000280380249,"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":0.9358999729156494,"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":0.9017598628997803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6912392973899841},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.615634560585022},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5836233496665955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5481579303741455},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4921559691429138},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43875184655189514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4292195439338684},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.33629167079925537},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21226057410240173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1348787248134613}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9017598628997803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912392973899841},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.615634560585022},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5836233496665955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481579303741455},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4921559691429138},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43875184655189514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4292195439338684},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33629167079925537},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21226057410240173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1348787248134613},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmar.2019.8864632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmar.2019.8864632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 24th International Conference on Methods and Models in Automation and Robotics (MMAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G3000430873","display_name":null,"funder_award_id":"MR/S003916/1","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G7197601580","display_name":null,"funder_award_id":"MR/S003916/2","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1606868664","https://openalex.org/W1977440921","https://openalex.org/W2000110725","https://openalex.org/W2029062311","https://openalex.org/W2062859931","https://openalex.org/W2067561969","https://openalex.org/W2075079150","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2127818367","https://openalex.org/W2145952809","https://openalex.org/W2173248099","https://openalex.org/W2335959470","https://openalex.org/W2343442488","https://openalex.org/W2623293810","https://openalex.org/W2738109916","https://openalex.org/W2787691009","https://openalex.org/W2792636771","https://openalex.org/W2800934671","https://openalex.org/W2805093171","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W6747831647"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":{"Batch":[0],"processes":[1],"are":[2,19],"significant":[3],"and":[4,17,31,39,47,56,62,72,107,134,142,156,173,187],"essential":[5],"manufacturing":[6,11],"route":[7],"for":[8],"the":[9,57,95,108,126,132,147,154,159,182],"agile":[10],"of":[12,25,103,128,136,158],"high":[13],"value":[14],"added":[15],"products":[16],"they":[18],"typically":[20],"difficult":[21],"to":[22,45,65,167],"control":[23,48,179],"because":[24],"unknown":[26],"disturbances,":[27],"model":[28],"plant":[29],"mismatches,":[30],"highly":[32,169],"nonlinear":[33,170],"characteristic.":[34],"Traditional":[35],"one-step":[36,53,184],"reinforcement":[37,54,185],"learning":[38,55,160,186],"neural":[40,58],"network":[41,59],"have":[42],"been":[43],"applied":[44,118,166],"optimize":[46],"batch":[49,171],"processes.":[50],"However,":[51],"traditional":[52,183],"lack":[60],"accuracy":[61],"robustness":[63],"leading":[64],"unsatisfactory":[66],"performance.":[67],"To":[68],"overcome":[69],"these":[70],"issues":[71],"difficulties,":[73],"a":[74,121,168],"modified":[75],"multi-step":[76],"action":[77,85,96,110,137],"Q-learning":[78,86],"algorithm":[79,164],"(MMSA)":[80],"based":[81],"on":[82],"multiple":[83],"step":[84],"(MSA)":[87],"is":[88,98,111,130,165,175],"proposed":[89,163],"in":[90,146],"this":[91],"paper.":[92],"For":[93],"MSA,":[94,125],"space":[97],"divided":[99],"into":[100],"some":[101],"periods":[102],"same":[104,109],"time":[105,150],"steps":[106],"explored":[112],"with":[113,124],"fixed":[114],"greedy":[115,144],"policy":[116,145],"being":[117],"continuously":[119],"during":[120],"period.":[122],"Compared":[123],"modification":[127],"MMSA":[129],"that":[131],"exploration":[133],"selection":[135],"will":[138],"follow":[139],"an":[140],"improved":[141],"various":[143],"whole":[148],"system":[149],"which":[151],"can":[152],"improve":[153],"flexibility":[155],"speed":[157],"algorithm.":[161],"The":[162],"process":[172],"it":[174],"shown":[176],"giving":[177],"better":[178],"performance":[180],"than":[181],"MSA.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}