{"id":"https://openalex.org/W4225659902","doi":"https://doi.org/10.1109/tii.2022.3159570","title":"DIP-QL: A Novel Reinforcement Learning Method for Constrained Industrial Systems","display_name":"DIP-QL: A Novel Reinforcement Learning Method for Constrained Industrial Systems","publication_year":2022,"publication_date":"2022-03-16","ids":{"openalex":"https://openalex.org/W4225659902","doi":"https://doi.org/10.1109/tii.2022.3159570"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2022.3159570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3159570","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/A5100677721","display_name":"Hyungjun Park","orcid":"https://orcid.org/0000-0003-2195-6442"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungjun Park","raw_affiliation_strings":["Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073891368","display_name":"Daiki Min","orcid":"https://orcid.org/0000-0003-3583-5879"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daiki Min","raw_affiliation_strings":["School of Business, Ewha Womans University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Business, Ewha Womans University, Seoul, South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088879664","display_name":"Jong-hyun Ryu","orcid":"https://orcid.org/0000-0002-0270-7937"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-hyun Ryu","raw_affiliation_strings":["College of Business Management, Hongik University, Sejong, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Business Management, Hongik University, Sejong, South Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087992646","display_name":"Dong Gu Choi","orcid":"https://orcid.org/0000-0003-3208-060X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong Gu Choi","raw_affiliation_strings":["Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-3208-060X","affiliations":[{"raw_affiliation_string":"Department of Industrial and Management Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2306,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89344276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"11","first_page":"7494","last_page":"7503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10223","display_name":"Microgrid Control and Optimization","score":0.9842000007629395,"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":0.8583873510360718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7616415023803711},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6406860947608948},{"id":"https://openalex.org/keywords/penalty-method","display_name":"Penalty method","score":0.5563835501670837},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.49139633774757385},{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.41622093319892883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2859402298927307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10782918334007263}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8583873510360718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616415023803711},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6406860947608948},{"id":"https://openalex.org/C6180225","wikidata":"https://www.wikidata.org/wiki/Q3411771","display_name":"Penalty method","level":2,"score":0.5563835501670837},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.49139633774757385},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.41622093319892883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2859402298927307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10782918334007263},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tii.2022.3159570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2022.3159570","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"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/113772","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/113772","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2008336247","display_name":null,"funder_award_id":"20213030160250","funder_id":"https://openalex.org/F4320335199","funder_display_name":"Korea Institute of Energy Technology Evaluation and Planning"},{"id":"https://openalex.org/G6291778365","display_name":null,"funder_award_id":"NRF-2020R1C1C1003461","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320335199","display_name":"Korea Institute of Energy Technology Evaluation and Planning","ror":"https://ror.org/02zq38y32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1987670263","https://openalex.org/W2013227046","https://openalex.org/W2022185333","https://openalex.org/W2054786539","https://openalex.org/W2071277918","https://openalex.org/W2130801532","https://openalex.org/W2145339207","https://openalex.org/W2156562940","https://openalex.org/W2343217767","https://openalex.org/W2403095561","https://openalex.org/W2784465508","https://openalex.org/W2790306973","https://openalex.org/W2900859370","https://openalex.org/W2902429452","https://openalex.org/W2913548458","https://openalex.org/W2924269685","https://openalex.org/W2949816299","https://openalex.org/W2952326029","https://openalex.org/W2959895084","https://openalex.org/W2962909019","https://openalex.org/W2963293747","https://openalex.org/W3005426010","https://openalex.org/W3005637364","https://openalex.org/W3009523569","https://openalex.org/W3038813703","https://openalex.org/W3098532584","https://openalex.org/W3119186746","https://openalex.org/W3160458447","https://openalex.org/W4293545785","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6737893269","https://openalex.org/W6747790125","https://openalex.org/W6756764608","https://openalex.org/W6765804866","https://openalex.org/W6779803226"],"related_works":["https://openalex.org/W2018662469","https://openalex.org/W2109185638","https://openalex.org/W2098882706","https://openalex.org/W1988507758","https://openalex.org/W2048756781","https://openalex.org/W2347558389","https://openalex.org/W122341662","https://openalex.org/W2106069570","https://openalex.org/W4285154570","https://openalex.org/W2945790020"],"abstract_inverted_index":{"Existing":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"methods":[4],"have":[5],"limited":[6,55],"applicability":[7],"to":[8,31,87,132,142],"real-world":[9],"industrial":[10],"control":[11,99],"problems":[12],"because":[13],"of":[14,35,114],"their":[15],"various":[16],"constraints.":[17,43],"To":[18],"overcome":[19],"this":[20,23],"challenge,":[21],"in":[22,91],"article,":[24],"we":[25,72,122],"devise":[26,73],"a":[27,36,46,62,128],"novel":[28],"RL":[29,48],"method":[30,52,66,141],"enable":[32,84],"the":[33,41,57,85,92,101,112,124,143,147],"optimization":[34],"policy":[37,136],"while":[38],"strictly":[39],"satisfying":[40],"system":[42],"By":[44],"leveraging":[45],"value-based":[47],"approach,":[49],"our":[50,140],"proposed":[51,107],"is":[53],"not":[54],"by":[56,95],"challenges":[58],"faced":[59],"when":[60],"searching":[61],"constrained":[63,135],"policy.":[64],"Our":[65],"has":[67],"two":[68,74],"main":[69],"features.":[70],"First,":[71],"distance-based":[75],"Q-value":[76],"update":[77,108],"schemes,":[78],"incentive":[79],"and":[80,117,146],"penalty":[81,125,131],"updates,":[82],"which":[83],"agent":[86],"decide":[88],"on":[89],"controls":[90],"feasible":[93,103],"region":[94],"replacing":[96],"an":[97],"infeasible":[98,119],"with":[100],"nearest":[102],"continuous":[104,116],"control.":[105],"The":[106],"schemes":[109],"can":[110],"adjust":[111],"values":[113],"both":[115],"original":[118],"controls.":[120],"Second,":[121],"define":[123],"cost":[126],"as":[127],"shadow":[129],"price-weighted":[130],"achieve":[133],"efficient,":[134],"learning.":[137],"We":[138],"apply":[139],"microgrid":[144],"control,":[145],"case":[148],"study":[149],"demonstrates":[150],"its":[151],"superiority.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}