{"id":"https://openalex.org/W3039772337","doi":"https://doi.org/10.1109/access.2020.3006254","title":"A Review on Interactive Reinforcement Learning From Human Social Feedback","display_name":"A Review on Interactive Reinforcement Learning From Human Social Feedback","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3039772337","doi":"https://doi.org/10.1109/access.2020.3006254","mag":"3039772337"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3006254","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3006254","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09131765.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09131765.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032678341","display_name":"Jinying Lin","orcid":"https://orcid.org/0000-0001-8019-9758"},"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":"Jinying Lin","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-8019-9758","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089566227","display_name":"Zhen Ma","orcid":"https://orcid.org/0000-0002-3881-7417"},"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":"Zhen Ma","raw_affiliation_strings":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-3881-7417","affiliations":[{"raw_affiliation_string":"Department of Electronic 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 Company Ltd., Wako, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3191-6818","affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company 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 Company Ltd., Wako, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4979-2083","affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Ltd., Wako, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760748","display_name":"Bo He","orcid":"https://orcid.org/0000-0001-6826-4721"},"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":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6826-4721","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","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":["Department of Electronic Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1728-5711","affiliations":[{"raw_affiliation_string":"Department of Electronic 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":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.3427,"has_fulltext":true,"cited_by_count":97,"citation_normalized_percentile":{"value":0.96462471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"120757","last_page":"120765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9864000082015991,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9821000099182129,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8805980086326599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7329707145690918},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6673797369003296},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5961677432060242},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5438698530197144},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5393898487091064},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.48709845542907715},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4621933102607727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3832170069217682},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11319312453269958}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8805980086326599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329707145690918},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6673797369003296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5961677432060242},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5438698530197144},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5393898487091064},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.48709845542907715},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4621933102607727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3832170069217682},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11319312453269958},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3006254","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3006254","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09131765.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2d6ffc68ec64442c88b24d5d307ed3d4","is_oa":true,"landing_page_url":"https://doaj.org/article/2d6ffc68ec64442c88b24d5d307ed3d4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 120757-120765 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3006254","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3006254","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09131765.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"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/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3039772337.pdf","grobid_xml":"https://content.openalex.org/works/W3039772337.grobid-xml"},"referenced_works_count":95,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W114159433","https://openalex.org/W121023703","https://openalex.org/W197704362","https://openalex.org/W1453801241","https://openalex.org/W1502767928","https://openalex.org/W1536323281","https://openalex.org/W1637016997","https://openalex.org/W1671650850","https://openalex.org/W1777239053","https://openalex.org/W1888002310","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W1989386832","https://openalex.org/W1999874108","https://openalex.org/W2024649868","https://openalex.org/W2046376809","https://openalex.org/W2062821321","https://openalex.org/W2074056782","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2104308387","https://openalex.org/W2107574152","https://openalex.org/W2111715140","https://openalex.org/W2114864106","https://openalex.org/W2116157560","https://openalex.org/W2118756286","https://openalex.org/W2119299928","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2122982548","https://openalex.org/W2128662966","https://openalex.org/W2129659607","https://openalex.org/W2137375617","https://openalex.org/W2140584963","https://openalex.org/W2145339207","https://openalex.org/W2148166693","https://openalex.org/W2151074445","https://openalex.org/W2154342426","https://openalex.org/W2154633587","https://openalex.org/W2156869222","https://openalex.org/W2158013657","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2397581010","https://openalex.org/W2419349576","https://openalex.org/W2518139248","https://openalex.org/W2545521674","https://openalex.org/W2560862806","https://openalex.org/W2565110810","https://openalex.org/W2774277131","https://openalex.org/W2885518439","https://openalex.org/W2890809352","https://openalex.org/W2894609524","https://openalex.org/W2898227854","https://openalex.org/W2900406861","https://openalex.org/W2920768993","https://openalex.org/W2944766483","https://openalex.org/W2949059942","https://openalex.org/W2963367210","https://openalex.org/W2963489214","https://openalex.org/W2964460729","https://openalex.org/W2964654516","https://openalex.org/W2964915587","https://openalex.org/W2985882473","https://openalex.org/W3005891386","https://openalex.org/W3022194887","https://openalex.org/W3039444588","https://openalex.org/W4288593469","https://openalex.org/W4300110528","https://openalex.org/W6604963999","https://openalex.org/W6607978175","https://openalex.org/W6638088447","https://openalex.org/W6674812091","https://openalex.org/W6676828045","https://openalex.org/W6677151524","https://openalex.org/W6677262939","https://openalex.org/W6678200026","https://openalex.org/W6680322746","https://openalex.org/W6682015148","https://openalex.org/W6682945686","https://openalex.org/W6696265566","https://openalex.org/W6696972564","https://openalex.org/W6712392314","https://openalex.org/W6717094648","https://openalex.org/W6726261588","https://openalex.org/W6732417791","https://openalex.org/W6745138362","https://openalex.org/W6746803943","https://openalex.org/W6753814467","https://openalex.org/W6754891083","https://openalex.org/W6755473067","https://openalex.org/W6758427599","https://openalex.org/W6777640276"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,18,33,42,67,113],"agent":[2,78,94,114],"learns":[3],"how":[4],"to":[5,37,45,53,74,115],"perform":[6],"a":[7],"task":[8],"by":[9,50,64],"interacting":[10],"with":[11],"the":[12,27,40,122],"environment.":[13],"The":[14,93],"use":[15],"of":[16,26,124],"reinforcement":[17,32,112],"in":[19],"real-life":[20,65],"applications":[21],"has":[22,34],"been":[23,35],"limited":[24],"because":[25],"sample":[28],"efficiency":[29],"problem.":[30],"Interactive":[31],"developed":[36],"speed":[38],"up":[39],"agent's":[41],"and":[43,121,133],"facilitate":[44],"learn":[46,97,116],"from":[47,98,117],"ordinary":[48],"people":[49],"allowing":[51],"them":[52],"provide":[54,75],"social":[55,119],"feedback,":[56,59],"e.g,":[57],"evaluative":[58],"advice":[60],"or":[61,91,102],"instruction.":[62],"Inspired":[63],"biological":[66],"scenarios,":[68],"there":[69],"could":[70],"be":[71],"many":[72],"ways":[73,123],"feedback":[76,99,120],"for":[77,110],"learning,":[79],"such":[80],"as":[81],"via":[82,100],"hardware":[83],"delivered,":[84],"natural":[85],"interaction":[86],"like":[87],"facial":[88],"expressions,":[89],"speech":[90],"gestures.":[92],"can":[95],"even":[96],"unimodal":[101],"multimodal":[103],"sensory":[104],"input.":[105],"This":[106],"paper":[107],"reviews":[108],"methods":[109],"interactive":[111],"human":[118],"delivering":[125],"feedback.":[126],"Finally,":[127],"we":[128],"discuss":[129],"some":[130],"open":[131],"problems":[132],"possible":[134],"future":[135],"research":[136],"directions.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-06T08:01:05.025921","created_date":"2025-10-10T00:00:00"}