{"id":"https://openalex.org/W4411133700","doi":"https://doi.org/10.1007/s10462-025-11260-4","title":"HIAT: human-in-the-loop reinforcement learning with auxiliary task","display_name":"HIAT: human-in-the-loop reinforcement learning with auxiliary task","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411133700","doi":"https://doi.org/10.1007/s10462-025-11260-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11260-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11260-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11260-4.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11260-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024053576","display_name":"Ben Niu","orcid":"https://orcid.org/0000-0001-5822-8743"},"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":"Bo Niu","raw_affiliation_strings":["School of Automation, Central South University, Changsha, 410083, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, 410083, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101479468","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-7476-3487"},"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, 410083, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, 410083, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084615495","display_name":"Yongzheng Cui","orcid":"https://orcid.org/0000-0002-5035-067X"},"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":"Yongzheng Cui","raw_affiliation_strings":["School of Automation, Central South University, Changsha, 410083, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, 410083, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061030501","display_name":"Xiaodong Xu","orcid":"https://orcid.org/0000-0003-4245-5989"},"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":"Xiaodong Xu","raw_affiliation_strings":["School of Automation, Central South University, Changsha, 410083, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, 410083, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883693","display_name":"Yuqian Zhao","orcid":"https://orcid.org/0000-0003-0261-9782"},"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":"Yuqian Zhao","raw_affiliation_strings":["School of Automation, Central South University, Changsha, 410083, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, 410083, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100628030","display_name":"Yu Feng","orcid":"https://orcid.org/0000-0003-0676-7344"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Feng","raw_affiliation_strings":["Information engineering College, Zhejiang University of Technology, Hangzhou, 310014, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information engineering College, Zhejiang University of Technology, Hangzhou, 310014, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101479468"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":3.7933,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93079434,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"58","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9944000244140625,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9793999791145325,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7713441848754883},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7522134780883789},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5930942893028259},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5724076628684998},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.5717752575874329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573265314102173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07746028900146484},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05414959788322449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713441848754883},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7522134780883789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5930942893028259},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5724076628684998},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.5717752575874329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573265314102173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07746028900146484},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05414959788322449},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-025-11260-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11260-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11260-4.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11260-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11260-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11260-4.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1342224670","display_name":null,"funder_award_id":"U2341216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5886857171","display_name":null,"funder_award_id":"62373375","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411133700.pdf","grobid_xml":"https://content.openalex.org/works/W4411133700.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2158782408","https://openalex.org/W2209913494","https://openalex.org/W2257979135","https://openalex.org/W2604847142","https://openalex.org/W2746553466","https://openalex.org/W2788862220","https://openalex.org/W2877093712","https://openalex.org/W2963411833","https://openalex.org/W2963489214","https://openalex.org/W3034853385","https://openalex.org/W3121045039","https://openalex.org/W3146254068","https://openalex.org/W3169375224","https://openalex.org/W4214717370","https://openalex.org/W4282020225","https://openalex.org/W4286253093","https://openalex.org/W4288076204","https://openalex.org/W4323363125","https://openalex.org/W4379622577","https://openalex.org/W4383503699","https://openalex.org/W4386700982","https://openalex.org/W4387319120","https://openalex.org/W4390872223","https://openalex.org/W4391808621","https://openalex.org/W4392203681","https://openalex.org/W4401506918","https://openalex.org/W6603707631"],"related_works":["https://openalex.org/W24774503","https://openalex.org/W4306904969","https://openalex.org/W4288099294","https://openalex.org/W2138720691","https://openalex.org/W4367173559","https://openalex.org/W4409348652","https://openalex.org/W4404795748","https://openalex.org/W4405627308","https://openalex.org/W4404893116","https://openalex.org/W2782058284"],"abstract_inverted_index":{"Human-in-the-loop":[0],"reinforcement":[1,72],"learning":[2,20,60,73,121],"(HIRL)":[3],"tackles":[4],"the":[5,19,34,46,100,106,111,120,127,134,159,162,166,191],"challenges":[6],"of":[7,36,49,123,136,161],"inefficient":[8],"exploration":[9,24],"and":[10,25,173,201],"low":[11],"sample":[12,37,142,202],"efficiency":[13,203],"by":[14,40,75,131,180],"incorporating":[15],"human":[16],"feedback":[17],"into":[18],"process":[21,122],"to":[22,58,93,108,205],"guide":[23],"speed":[26],"up":[27],"learning.":[28],"Nevertheless,":[29],"most":[30],"recent":[31],"approaches":[32],"overlook":[33],"problem":[35],"imbalance":[38],"caused":[39,179],"varying":[41],"behavioral":[42],"policy":[43,54,128],"distributions":[44],"in":[45,53,113],"early":[47],"stages":[48],"training,":[50],"which":[51,157],"results":[52,192],"performance":[55],"degradation":[56],"due":[57],"biased":[59],"toward":[61],"dominant":[62],"low-quality":[63],"data.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,145],"propose":[69],"a":[70],"human-in-the-loop":[71],"method":[74,118],"constructing":[76],"an":[77,95,147],"auxiliary":[78,96,163],"task,":[79],"namely":[80,151],"Human-in-the-Loop":[81],"Reinforcement":[82],"Learning":[83],"with":[84],"Auxiliary":[85],"Task":[86],"(HIAT).":[87],"Specifically,":[88],"state-action":[89],"pairs":[90],"are":[91],"utilized":[92],"create":[94],"task":[97,164,168],"that":[98,194],"assesses":[99],"similarity":[101],"between":[102,176],"different":[103,137,177],"policies,":[104],"forcing":[105],"model":[107],"focus":[109],"on":[110,165,170,186],"differences":[112],"data":[114],"sources.":[115],"The":[116],"HIAT":[117,155],"guides":[119],"new":[124],"policies":[125],"during":[126],"evaluation":[129],"phase":[130],"implicitly":[132],"influencing":[133],"assessment":[135],"actions,":[138],"thereby":[139],"compensating":[140],"for":[141],"imbalance.":[143],"Subsequently,":[144],"introduce":[146],"adaptive":[148,152],"weighting":[149,153],"version,":[150],"based":[154,169],"(AWHIAT),":[156],"adjusts":[158],"impact":[160],"primary":[167],"their":[171],"task-relevance":[172],"mitigates":[174],"conflicts":[175],"tasks":[178],"cognitive":[181],"load.":[182],"Through":[183],"empirical":[184],"evaluations":[185],"six":[187],"continuous":[188],"control":[189],"benchmarks,":[190],"demonstrate":[193],"AWHIAT":[195],"significantly":[196],"improves":[197],"mean":[198],"episode":[199],"reward":[200],"compared":[204],"four":[206],"representative":[207],"HIRL":[208],"methods.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}