{"id":"https://openalex.org/W3133958367","doi":"https://doi.org/10.1109/tii.2021.3063489","title":"Shifting Deep Reinforcement Learning Algorithm Toward Training Directly in Transient Real-World Environment: A Case Study in Powertrain Control","display_name":"Shifting Deep Reinforcement Learning Algorithm Toward Training Directly in Transient Real-World Environment: A Case Study in Powertrain Control","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3133958367","doi":"https://doi.org/10.1109/tii.2021.3063489","mag":"3133958367"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2021.3063489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2021.3063489","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/A5022417497","display_name":"Bo Hu","orcid":"https://orcid.org/0000-0003-2995-2358"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Hu","raw_affiliation_strings":["Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing, China","Ningbo Yinzhou DLT Technology, Company, Ltd., Ningbo, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]},{"raw_affiliation_string":"Ningbo Yinzhou DLT Technology, Company, Ltd., Ningbo, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730103","display_name":"Jiaxi Li","orcid":"https://orcid.org/0000-0003-3941-8554"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Li","raw_affiliation_strings":["Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing, China","institution_ids":["https://openalex.org/I50632499"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5022417497"],"corresponding_institution_ids":["https://openalex.org/I50632499"],"apc_list":null,"apc_paid":null,"fwci":1.9246,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.85038443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"17","issue":"12","first_page":"8198","last_page":"8206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10808","display_name":"Electric and Hybrid Vehicle Technologies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10808","display_name":"Electric and Hybrid Vehicle Technologies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.989300012588501,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9702000021934509,"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":0.8660835027694702},{"id":"https://openalex.org/keywords/powertrain","display_name":"Powertrain","score":0.8598799705505371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.568474531173706},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5621678233146667},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5415239334106445},{"id":"https://openalex.org/keywords/turbocharger","display_name":"Turbocharger","score":0.521988034248352},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4578394591808319},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4479290843009949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44277554750442505},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43416279554367065},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42590904235839844},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.33145672082901},{"id":"https://openalex.org/keywords/torque","display_name":"Torque","score":0.12687289714813232},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08607202768325806}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8660835027694702},{"id":"https://openalex.org/C76047896","wikidata":"https://www.wikidata.org/wiki/Q1786258","display_name":"Powertrain","level":3,"score":0.8598799705505371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.568474531173706},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5621678233146667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5415239334106445},{"id":"https://openalex.org/C21541133","wikidata":"https://www.wikidata.org/wiki/Q185525","display_name":"Turbocharger","level":3,"score":0.521988034248352},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4578394591808319},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4479290843009949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44277554750442505},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43416279554367065},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42590904235839844},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33145672082901},{"id":"https://openalex.org/C144171764","wikidata":"https://www.wikidata.org/wiki/Q48103","display_name":"Torque","level":2,"score":0.12687289714813232},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08607202768325806},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2778449969","wikidata":"https://www.wikidata.org/wiki/Q130760","display_name":"Turbine","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2021.3063489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2021.3063489","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/G415527274","display_name":null,"funder_award_id":"51905061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6393788340","display_name":null,"funder_award_id":"cstc2019jcyj-msxmX0097","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G6923447686","display_name":null,"funder_award_id":"2020M671842","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W1845972764","https://openalex.org/W2008791002","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2164419340","https://openalex.org/W2397581010","https://openalex.org/W2741122588","https://openalex.org/W2766447205","https://openalex.org/W2906669385","https://openalex.org/W2911283634","https://openalex.org/W2918400102","https://openalex.org/W2920406591","https://openalex.org/W2945623569","https://openalex.org/W2948689530","https://openalex.org/W2963575966","https://openalex.org/W2963864421","https://openalex.org/W2964536243","https://openalex.org/W2968522222","https://openalex.org/W2969277962","https://openalex.org/W2990954138","https://openalex.org/W3004006877","https://openalex.org/W3044345870","https://openalex.org/W3103078407","https://openalex.org/W4242457953","https://openalex.org/W6680724558","https://openalex.org/W6684159546","https://openalex.org/W6684921986","https://openalex.org/W6689723076","https://openalex.org/W6712392314","https://openalex.org/W6742461812","https://openalex.org/W6743563064","https://openalex.org/W6762542541"],"related_works":["https://openalex.org/W1991883354","https://openalex.org/W3152280654","https://openalex.org/W2387679487","https://openalex.org/W2374045587","https://openalex.org/W2369062741","https://openalex.org/W4205570609","https://openalex.org/W4252393869","https://openalex.org/W3145472954","https://openalex.org/W2383640325","https://openalex.org/W4200626784"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,18,127,168],"(DRL)":[3],"excels":[4],"at":[5],"playing":[6],"a":[7,16,24,36,64,75,125,129,134,147],"wide":[8],"variety":[9],"of":[10,27,40,112,173],"simulated":[11],"games":[12],"and":[13,47,109,166],"allows":[14],"for":[15,146,204],"generic":[17],"process":[19],"that":[20,35,48,81,100,104],"does":[21],"not":[22],"consider":[23],"specific":[25],"knowledge":[26,103,123],"the":[28,33,43,49,87,98,113,142,157,161,167,189,194,198],"task.":[29],"However,":[30],"due":[31],"to":[32,177,210],"fact":[34],"large":[37],"prohibitively":[38],"number":[39],"interactions":[41],"with":[42,133,182],"environment":[44,66,90,115],"are":[45,117],"required":[46],"initial":[50,162],"policy":[51],"behavior":[52],"is":[53,91,95],"almost":[54],"random,":[55],"such":[56],"an":[57,110,155,171],"algorithm":[58,132,159,191],"cannot":[59],"be":[60,139],"trained":[61],"directly":[62,85],"in":[63,86,175,197],"real-world":[65,89],"while":[67],"satisfying":[68],"given":[69],"safety":[70],"constraints.":[71],"In":[72],"this":[73,121],"article,":[74],"control":[76,144,187,208],"framework":[77],"based":[78],"on":[79,97],"DRL":[80,131],"shifts":[82],"toward":[83],"training":[84],"transient":[88],"proposed.":[92],"This":[93],"research":[94],"working":[96],"assumption":[99],"some":[101],"demonstration":[102],"operates":[105],"under":[106],"previous":[107],"controllers":[108],"abstract":[111],"agent":[114],"dynamics":[116],"available.":[118],"By":[119],"encoding":[120],"prior":[122],"into":[124],"sophisticated":[126],"architecture,":[128],"warm-starting":[130],"safe":[135],"exploration":[136],"guarantee":[137],"can":[138,192],"anticipated.":[140],"Taking":[141],"boost":[143],"problem":[145],"variable":[148],"geometry":[149],"turbocharger":[150],"equipped":[151],"diesel":[152],"engine":[153],"as":[154],"example,":[156],"proposed":[158,190],"improves":[160],"performance":[163],"by":[164,170],"74.6%":[165],"efficiency":[169],"order":[172],"magnitude":[174],"contrast":[176],"its":[178],"vanilla":[179],"counterpart.":[180],"Compared":[181],"other":[183],"existing":[184],"DRL-based":[185,206],"powertrain":[186,207],"methods,":[188],"realize":[193],"\u201cmodel-free\u201d":[195],"concept":[196],"strict":[199],"sense,":[200],"making":[201],"it":[202],"attractive":[203],"future":[205],"algorithms":[209],"build":[211],"on.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}