{"id":"https://openalex.org/W4383503699","doi":"https://doi.org/10.1109/tnnls.2023.3289315","title":"Human-in-the-Loop Reinforcement Learning in Continuous-Action Space","display_name":"Human-in-the-Loop Reinforcement Learning in Continuous-Action Space","publication_year":2023,"publication_date":"2023-07-07","ids":{"openalex":"https://openalex.org/W4383503699","doi":"https://doi.org/10.1109/tnnls.2023.3289315","pmid":"https://pubmed.ncbi.nlm.nih.gov/37418406"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3289315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3289315","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5012004938","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-3353-2586"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Biao Luo","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035530912","display_name":"Zhengke Wu","orcid":"https://orcid.org/0000-0002-0204-6606"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengke Wu","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044245328","display_name":"Fei Zhou","orcid":"https://orcid.org/0000-0002-5727-0445"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhou","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040076424","display_name":"Bing-Chuan Wang","orcid":"https://orcid.org/0000-0002-0234-2843"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Chuan Wang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012004938"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":6.0933,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97200521,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"11","first_page":"15735","last_page":"15744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8424000144004822,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.8424000144004822,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6348694562911987},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6307429075241089},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.6306415796279907},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5514576435089111},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5512883067131042},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.49627333879470825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3994670510292053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32560768723487854},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2931184768676758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21711942553520203},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.181083083152771},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12780627608299255},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06870868802070618}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6348694562911987},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6307429075241089},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.6306415796279907},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5514576435089111},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5512883067131042},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.49627333879470825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3994670510292053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32560768723487854},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2931184768676758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21711942553520203},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.181083083152771},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12780627608299255},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06870868802070618},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3289315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3289315","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37418406","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37418406","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4615517790","display_name":null,"funder_award_id":"2020JJ2049","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G5137249975","display_name":null,"funder_award_id":"62022094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6608089276","display_name":null,"funder_award_id":"61873350","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/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W114159433","https://openalex.org/W1971890413","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W2098584016","https://openalex.org/W2102847492","https://openalex.org/W2110064869","https://openalex.org/W2145339207","https://openalex.org/W2156869222","https://openalex.org/W2157726050","https://openalex.org/W2398264187","https://openalex.org/W2799745602","https://openalex.org/W2944766483","https://openalex.org/W2963489214","https://openalex.org/W2963761387","https://openalex.org/W2964177756","https://openalex.org/W2965723696","https://openalex.org/W2966349401","https://openalex.org/W2967503332","https://openalex.org/W2968491743","https://openalex.org/W2982316857","https://openalex.org/W2996868001","https://openalex.org/W3001507548","https://openalex.org/W3037767967","https://openalex.org/W3046093665","https://openalex.org/W3046195400","https://openalex.org/W3093201391","https://openalex.org/W3100789280","https://openalex.org/W3164005523","https://openalex.org/W3169375224","https://openalex.org/W3174733757","https://openalex.org/W3188648403","https://openalex.org/W3205626500","https://openalex.org/W3208134787","https://openalex.org/W4214717370","https://openalex.org/W4226361140","https://openalex.org/W6631533588","https://openalex.org/W6640174482","https://openalex.org/W6674812091","https://openalex.org/W6703110798","https://openalex.org/W6718092244","https://openalex.org/W6730844258","https://openalex.org/W6739585900","https://openalex.org/W6745347688","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6755473067","https://openalex.org/W6769977606","https://openalex.org/W6772005887","https://openalex.org/W6791684492","https://openalex.org/W6796168157","https://openalex.org/W6796718340","https://openalex.org/W6840917455","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W4367173559","https://openalex.org/W2902961658","https://openalex.org/W2782058284","https://openalex.org/W3103937890"],"abstract_inverted_index":{"Human-in-the-loop":[0],"for":[1,22,52,102,167],"reinforcement":[2],"learning":[3,165,203],"(RL)":[4],"is":[5,87,154],"usually":[6],"employed":[7],"to":[8,89,142,171],"overcome":[9],"the":[10,17,23,57,63,71,78,90,103,108,112,116,122,125,128,134,138,144,147,150,164,168,176,180,191,196],"challenge":[11],"of":[12,60,74,105,146,178],"sample":[13],"inefficiency,":[14],"in":[15,70,99,115,121,137,190],"which":[16,162],"human":[18,61,64,113],"expert":[19,65,114,157],"provides":[20,163],"advice":[21,69,120],"agent":[24,75,79,160],"when":[25],"necessary.":[26],"The":[27,84],"current":[28,139],"human-in-the-loop":[29],"RL":[30],"(HRL)":[31],"results":[32,197],"mainly":[33],"focus":[34],"on":[35,184],"discrete":[36],"action":[37,54,82,187],"space.":[38,55],"In":[39],"this":[40,100],"article,":[41],"we":[42],"propose":[43],"a":[44],"Q":[45,130],"value-dependent":[46],"policy":[47,95],"(QDP)-based":[48],"HRL":[49],"(QDP-HRL)":[50],"algorithm":[51,97,170],"continuous":[53,186],"Considering":[56],"cognitive":[58],"costs":[59],"monitoring,":[62],"only":[66],"selectively":[67],"gives":[68],"early":[72],"stage":[73],"learning,":[76],"where":[77],"implements":[80],"human-advised":[81],"instead.":[83],"QDP":[85],"framework":[86],"adapted":[88],"twin":[91,129],"delayed":[92],"deep":[93],"deterministic":[94],"gradient":[96],"(TD3)":[98],"article":[101],"convenience":[104],"comparison":[106],"with":[107],"state-of-the-art":[109],"TD3.":[110],"Specifically,":[111],"QDP-HRL":[117,169,200],"considers":[118],"giving":[119],"case":[123],"that":[124,199],"difference":[126,136],"between":[127],"-networks'":[131],"output":[132],"exceeds":[133],"maximum":[135],"queue.":[140],"Moreover,":[141],"guide":[143],"update":[145],"critic":[148],"network,":[149],"advantage":[151],"loss":[152],"function":[153],"developed":[155],"using":[156],"experience":[158],"and":[159,195,205],"policy,":[161],"direction":[166],"some":[172],"extent.":[173],"To":[174],"verify":[175],"effectiveness":[177],"QDP-HRL,":[179],"experiments":[181],"are":[182],"conducted":[183],"several":[185],"space":[188],"tasks":[189],"OpenAI":[192],"gym":[193],"environment,":[194],"demonstrate":[198],"greatly":[201],"improves":[202],"speed":[204],"performance.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}