{"id":"https://openalex.org/W2944766483","doi":"https://doi.org/10.1109/thms.2019.2912447","title":"Human-Centered Reinforcement Learning: A Survey","display_name":"Human-Centered Reinforcement Learning: A Survey","publication_year":2019,"publication_date":"2019-05-08","ids":{"openalex":"https://openalex.org/W2944766483","doi":"https://doi.org/10.1109/thms.2019.2912447","mag":"2944766483"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2019.2912447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2019.2912447","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"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 Human-Machine Systems","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/A5101812014","display_name":"Guangliang Li","orcid":"https://orcid.org/0000-0003-1728-5711"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1728-5711","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052470310","display_name":"Randy G\u00f3mez","orcid":"https://orcid.org/0000-0002-3191-6818"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Randy Gomez","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd., Wako, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049329632","display_name":"Keisuke Nakamura","orcid":"https://orcid.org/0000-0002-4979-2083"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Nakamura","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd., Wako, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd., Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113949081","display_name":"Bo He","orcid":"https://orcid.org/0000-0001-9092-9152"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo He","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-9092-9152","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6009,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":{"value":0.9833835,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"49","issue":"4","first_page":"337","last_page":"349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.935699999332428,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7736600637435913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783515214920044},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5203830003738403},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4948813319206238},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4572652280330658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4139094948768616},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34693706035614014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07928204536437988},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06605353951454163}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7736600637435913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783515214920044},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5203830003738403},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4948813319206238},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4572652280330658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4139094948768616},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34693706035614014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07928204536437988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06605353951454163},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2019.2912447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2019.2912447","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"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 Human-Machine Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G226851083","display_name":null,"funder_award_id":"861705020036","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G2654232817","display_name":null,"funder_award_id":"841713015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5362766921","display_name":null,"funder_award_id":"ZR2018QF003","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G8754186815","display_name":null,"funder_award_id":"51809246","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W32403112","https://openalex.org/W114159433","https://openalex.org/W121023703","https://openalex.org/W197704362","https://openalex.org/W745775011","https://openalex.org/W1453801241","https://openalex.org/W1536323281","https://openalex.org/W1589747210","https://openalex.org/W1590759229","https://openalex.org/W1591803298","https://openalex.org/W1601974704","https://openalex.org/W1646707810","https://openalex.org/W1777239053","https://openalex.org/W1888002310","https://openalex.org/W1914583973","https://openalex.org/W1977655452","https://openalex.org/W1983420732","https://openalex.org/W1985741044","https://openalex.org/W1999874108","https://openalex.org/W2024649868","https://openalex.org/W2027106130","https://openalex.org/W2046376809","https://openalex.org/W2049633694","https://openalex.org/W2056833498","https://openalex.org/W2074056782","https://openalex.org/W2076063813","https://openalex.org/W2094387729","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2107574152","https://openalex.org/W2107726111","https://openalex.org/W2109588128","https://openalex.org/W2111119385","https://openalex.org/W2111316871","https://openalex.org/W2111935653","https://openalex.org/W2114864106","https://openalex.org/W2116157560","https://openalex.org/W2118756286","https://openalex.org/W2119299928","https://openalex.org/W2120982521","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2124290836","https://openalex.org/W2129659607","https://openalex.org/W2131600418","https://openalex.org/W2132504164","https://openalex.org/W2133993682","https://openalex.org/W2139053308","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2151074445","https://openalex.org/W2155027007","https://openalex.org/W2156869222","https://openalex.org/W2157726050","https://openalex.org/W2158969944","https://openalex.org/W2202549229","https://openalex.org/W2265674096","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2316716009","https://openalex.org/W2317130090","https://openalex.org/W2395263189","https://openalex.org/W2419349576","https://openalex.org/W2518139248","https://openalex.org/W2545521674","https://openalex.org/W2580300496","https://openalex.org/W2597613574","https://openalex.org/W2728201397","https://openalex.org/W2787259794","https://openalex.org/W2900406861","https://openalex.org/W2964263543","https://openalex.org/W4214717370","https://openalex.org/W4233071909","https://openalex.org/W4248205577","https://openalex.org/W4249362117","https://openalex.org/W4300110528","https://openalex.org/W4321392130","https://openalex.org/W6604963999","https://openalex.org/W6607978175","https://openalex.org/W6622050690","https://openalex.org/W6635285615","https://openalex.org/W6635327058","https://openalex.org/W6635991215","https://openalex.org/W6638088447","https://openalex.org/W6674812091","https://openalex.org/W6676270456","https://openalex.org/W6676661950","https://openalex.org/W6677151524","https://openalex.org/W6677262939","https://openalex.org/W6680657880","https://openalex.org/W6683204974","https://openalex.org/W6687713970","https://openalex.org/W6693439961","https://openalex.org/W6696265566","https://openalex.org/W6696972564","https://openalex.org/W6711819936","https://openalex.org/W6717094648","https://openalex.org/W6726261588","https://openalex.org/W6729512192","https://openalex.org/W6732417791","https://openalex.org/W6739585900"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Human-centered":[0],"reinforcement":[1],"learning":[2,162],"(RL),":[3],"in":[4,28,76,95,151],"which":[5,144],"an":[6,111,185],"agent":[7,44],"learns":[8],"how":[9],"to":[10,36,47,50,64,86,101],"perform":[11],"a":[12,19,42,66,88,191],"task":[13],"from":[14,38,118,132,163],"evaluative":[15,142,166],"feedback":[16,40,167],"delivered":[17],"by":[18],"human":[20,39,58,141,165],"observer,":[21],"has":[22,45],"become":[23,65],"more":[24,26],"and":[25,62,98,105,129,168,190,196],"popular":[27],"recent":[29,93],"years.":[30],"The":[31],"advantage":[32],"of":[33,82,91,113,116,126,140,178,187,193],"being":[34],"able":[35],"learn":[37],"for":[41,69],"RL":[43,60,117,128,149],"led":[46],"increasing":[48],"applicability":[49],"real-life":[51],"problems.":[52],"This":[53],"paper":[54,84,122],"describes":[55],"the":[56,80,92,102,114,124,152,176],"state-of-the-art":[57],"centered":[59],"algorithms":[61,150],"aims":[63],"starting":[67,109],"point":[68],"researchers":[70],"who":[71],"are":[72],"initiating":[73],"their":[74],"endeavors":[75],"human-centered":[77,127,148,179],"RL.":[78,134,180],"Moreover,":[79],"objective":[81],"this":[83,96,121],"is":[85],"present":[87],"comprehensive":[89],"survey":[90],"breakthroughs":[94],"field":[97],"provide":[99],"references":[100],"most":[103],"interesting":[104],"successful":[106],"works.":[107],"After":[108],"with":[110,184],"introduction":[112],"concepts":[115],"environmental":[119,169],"reward,":[120],"discusses":[123],"origins":[125],"its":[130],"difference":[131],"traditional":[133],"Then":[135],"we":[136,157,182],"describe":[137,158],"different":[138],"interpretations":[139],"feedback,":[143],"have":[145],"produced":[146],"many":[147],"past":[153],"decade.":[154],"In":[155],"addition,":[156],"research":[159],"on":[160,174],"agents":[161],"both":[164],"rewards":[170],"as":[171,173],"well":[172],"improving":[175],"efficiency":[177],"Finally,":[181],"conclude":[183],"overview":[186],"application":[188],"areas":[189],"discussion":[192],"future":[194],"work":[195],"open":[197],"questions.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":22}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}