{"id":"https://openalex.org/W4403534251","doi":"https://doi.org/10.1109/thms.2024.3467370","title":"The Augmented Intelligence Perspective on Human-in-the-Loop Reinforcement Learning: Review, Concept Designs, and Future Directions","display_name":"The Augmented Intelligence Perspective on Human-in-the-Loop Reinforcement Learning: Review, Concept Designs, and Future Directions","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4403534251","doi":"https://doi.org/10.1109/thms.2024.3467370"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2024.3467370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2024.3467370","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/A5055349217","display_name":"Kok\u2010Lim Alvin Yau","orcid":"https://orcid.org/0000-0003-3110-2782"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Kok-Lim Alvin Yau","raw_affiliation_strings":["Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-3110-2782","affiliations":[{"raw_affiliation_string":"Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069233011","display_name":"Yasir Saleem","orcid":"https://orcid.org/0000-0003-1998-1446"},"institutions":[{"id":"https://openalex.org/I16038530","display_name":"Aberystwyth University","ror":"https://ror.org/015m2p889","country_code":"GB","type":"education","lineage":["https://openalex.org/I16038530"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yasir Saleem","raw_affiliation_strings":["Department of Computer Science, Aberystwyth University, Aberystwyth, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aberystwyth University, Aberystwyth, U.K","institution_ids":["https://openalex.org/I16038530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078603752","display_name":"Yung-Wey Chong","orcid":"https://orcid.org/0000-0003-1750-7441"},"institutions":[{"id":"https://openalex.org/I139322472","display_name":"Universiti Sains Malaysia","ror":"https://ror.org/02rgb2k63","country_code":"MY","type":"education","lineage":["https://openalex.org/I139322472"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yung-Wey Chong","raw_affiliation_strings":["School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1750-7441","affiliations":[{"raw_affiliation_string":"School of Computer Sciences, Universiti Sains Malaysia, Penang, Malaysia","institution_ids":["https://openalex.org/I139322472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019723430","display_name":"Xiumei Fan","orcid":"https://orcid.org/0000-0002-6967-9248"},"institutions":[{"id":"https://openalex.org/I4210131919","display_name":"Xi'an University of Technology","ror":"https://ror.org/038avdt50","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210131919"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiumei Fan","raw_affiliation_strings":["School of Automation and Information Engineering, Xi&#x0027;an University of Technology, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-6967-9248","affiliations":[{"raw_affiliation_string":"School of Automation and Information Engineering, Xi&#x0027;an University of Technology, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I4210131919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114319780","display_name":"Jer Min Eyu","orcid":null},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jer Min Eyu","raw_affiliation_strings":["Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lee Kong Chian Faculty of Engineering and Science, Universiti Tunku Abdul Rahman, Kajang, Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017993236","display_name":"David Chieng","orcid":"https://orcid.org/0000-0002-9674-3436"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"David Chieng","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Faculty of Science and Engineering, University of Nottingham Ningbo, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-9674-3436","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Faculty of Science and Engineering, University of Nottingham Ningbo, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055349217"],"corresponding_institution_ids":["https://openalex.org/I931681460"],"apc_list":null,"apc_paid":null,"fwci":4.0931,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94903971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"54","issue":"6","first_page":"762","last_page":"777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8482000231742859,"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/T13553","display_name":"Age of Information Optimization","score":0.8087999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.752418041229248},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7427172660827637},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.6796820163726807},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5452954173088074},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5067036747932434},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.500389575958252},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.40355080366134644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38901689648628235},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3367437422275543},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3261297345161438},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14245831966400146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0745660662651062}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.752418041229248},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7427172660827637},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.6796820163726807},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5452954173088074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5067036747932434},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.500389575958252},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.40355080366134644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38901689648628235},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3367437422275543},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3261297345161438},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14245831966400146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0745660662651062},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2024.3467370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2024.3467370","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":[],"funders":[{"id":"https://openalex.org/F4320321709","display_name":"Ministry of Higher Education, Malaysia","ror":"https://ror.org/05mcs2t73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W1536323281","https://openalex.org/W1965520710","https://openalex.org/W2064675550","https://openalex.org/W2095914067","https://openalex.org/W2114864106","https://openalex.org/W2121110499","https://openalex.org/W2140584963","https://openalex.org/W2152706824","https://openalex.org/W2156869222","https://openalex.org/W2200867663","https://openalex.org/W2293706533","https://openalex.org/W2300445845","https://openalex.org/W2560862806","https://openalex.org/W2565110810","https://openalex.org/W2589425367","https://openalex.org/W2604847142","https://openalex.org/W2606248652","https://openalex.org/W2736549917","https://openalex.org/W2738893935","https://openalex.org/W2739573821","https://openalex.org/W2774647452","https://openalex.org/W2777604108","https://openalex.org/W2786194544","https://openalex.org/W2807744285","https://openalex.org/W2889720216","https://openalex.org/W2889983762","https://openalex.org/W2890809352","https://openalex.org/W2896273125","https://openalex.org/W2909713847","https://openalex.org/W2921017360","https://openalex.org/W2926849453","https://openalex.org/W2941405176","https://openalex.org/W2948937890","https://openalex.org/W2963017537","https://openalex.org/W2963489214","https://openalex.org/W2965208105","https://openalex.org/W2986621272","https://openalex.org/W3000181076","https://openalex.org/W3011807390","https://openalex.org/W3022194887","https://openalex.org/W3033740321","https://openalex.org/W3039772337","https://openalex.org/W3048625561","https://openalex.org/W3079513054","https://openalex.org/W3088607834","https://openalex.org/W3089731385","https://openalex.org/W3091627088","https://openalex.org/W3094387578","https://openalex.org/W3097470552","https://openalex.org/W3109289797","https://openalex.org/W3111710787","https://openalex.org/W3119094839","https://openalex.org/W3125786462","https://openalex.org/W3128318087","https://openalex.org/W3131947895","https://openalex.org/W3150177537","https://openalex.org/W3150894284","https://openalex.org/W3158218109","https://openalex.org/W3159667783","https://openalex.org/W3161302686","https://openalex.org/W3177181149","https://openalex.org/W3190142562","https://openalex.org/W3192495122","https://openalex.org/W3193850114","https://openalex.org/W3202542428","https://openalex.org/W3203694549","https://openalex.org/W3204496322","https://openalex.org/W3205269667","https://openalex.org/W3205371299","https://openalex.org/W3208860346","https://openalex.org/W3213330367","https://openalex.org/W4200270753","https://openalex.org/W4200326476","https://openalex.org/W4205284927","https://openalex.org/W4205292422","https://openalex.org/W4206663600","https://openalex.org/W4210790685","https://openalex.org/W4210866977","https://openalex.org/W4214717370","https://openalex.org/W4220970489","https://openalex.org/W4240649100","https://openalex.org/W4283211846","https://openalex.org/W4287553698","https://openalex.org/W4388283561","https://openalex.org/W4389459425","https://openalex.org/W6637967152","https://openalex.org/W6674812091","https://openalex.org/W6677151524","https://openalex.org/W6683397050","https://openalex.org/W6712392314","https://openalex.org/W6752707627","https://openalex.org/W6763056091","https://openalex.org/W6786884049","https://openalex.org/W6801727026"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W4367173559","https://openalex.org/W2782058284"],"abstract_inverted_index":{"Augmented":[0],"intelligence":[1,9,13],"(AuI)":[2],"is":[3,41],"a":[4,42],"concept":[5,92,133],"that":[6,45,151],"combines":[7],"human":[8,152],"(HI)":[10],"and":[11,64,67,76,88,102,114,124,157],"artificial":[12],"(AI)":[14],"to":[15,24,58,167,181],"leverage":[16],"their":[17,33,81],"respective":[18],"strengths.":[19],"While":[20],"AI":[21,115],"typically":[22],"aims":[23],"replace":[25],"humans,":[26],"AuI":[27,75,123],"integrates":[28,46],"humans":[29,47,63],"into":[30,48,128,131],"machines,":[31],"recognizing":[32],"irreplaceable":[34],"role.":[35],"Meanwhile,":[36],"human-in-the-loop":[37],"reinforcement":[38,51],"learning":[39,52],"(HITL-RL)":[40],"semisupervised":[43],"algorithm":[44],"the":[49,110,174],"traditional":[50,168],"(RL)":[53],"algorithm,":[54],"enabling":[55],"autonomous":[56],"agents":[57],"gather":[59],"inputs":[60],"from":[61],"both":[62],"environments,":[65],"learn,":[66],"select":[68],"optimal":[69],"actions":[70],"across":[71],"various":[72],"environments.":[73],"Both":[74],"HITL-RL":[77,125],"are":[78,179],"still":[79],"in":[80,109,117,138,173,185],"infancy.":[82],"Based":[83],"on":[84,122],"AuI,":[85],"we":[86],"propose":[87],"investigate":[89],"three":[90],"separate":[91],"designs":[93],"for":[94,144],"HITL-RL:":[95],"<italic":[96,99,103],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[97,100,104,170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">HI-AI</i>,":[98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">AI-HI</i>,":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">parallel-HI-and-AI</i>":[105],"approaches,":[106],"each":[107],"differing":[108],"order":[111],"of":[112],"HI":[113,130],"involvement":[116,153],"decision":[118],"making.":[119],"The":[120],"literature":[121],"offers":[126,142],"insights":[127,143],"integrating":[129],"existing":[132],"designs.":[134],"A":[135],"preliminary":[136],"study":[137],"an":[139],"Atari":[140],"game":[141],"future":[145],"research":[146,177],"directions.":[147],"Simulation":[148],"results":[149],"show":[150],"maintains":[154],"RL":[155],"convergence":[156],"improves":[158],"system":[159],"stability,":[160],"while":[161],"achieving":[162],"approximately":[163],"similar":[164],"average":[165],"scores":[166],"<inline-formula":[169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[171],"notation=\"LaTeX\">$Q$</tex-math></inline-formula>-learning":[172],"game.":[175],"Future":[176],"directions":[178],"proposed":[180],"encourage":[182],"further":[183],"investigation":[184],"this":[186],"area.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}