{"id":"https://openalex.org/W3169375224","doi":"https://doi.org/10.1109/tnnls.2021.3084198","title":"Weak Human Preference Supervision for Deep Reinforcement Learning","display_name":"Weak Human Preference Supervision for Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3169375224","doi":"https://doi.org/10.1109/tnnls.2021.3084198","mag":"3169375224","pmid":"https://pubmed.ncbi.nlm.nih.gov/34101604"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3084198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3084198","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/A5007077356","display_name":"Zehong Cao","orcid":"https://orcid.org/0000-0003-3656-0328"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zehong Cao","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Campus, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3656-0328","affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Campus, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046845983","display_name":"Kaichiu Wong","orcid":"https://orcid.org/0000-0003-0510-9219"},"institutions":[{"id":"https://openalex.org/I129801699","display_name":"University of Tasmania","ror":"https://ror.org/01nfmeh72","country_code":"AU","type":"education","lineage":["https://openalex.org/I129801699"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"KaiChiu Wong","raw_affiliation_strings":["MyState Bank, Hobart, TAS, Australia","School of Information and Communications Technology (ICT), University of Tasmania, Hobart, TAS, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0510-9219","affiliations":[{"raw_affiliation_string":"MyState Bank, Hobart, TAS, Australia","institution_ids":[]},{"raw_affiliation_string":"School of Information and Communications Technology (ICT), University of Tasmania, Hobart, TAS, Australia","institution_ids":["https://openalex.org/I129801699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058936239","display_name":"Chin\u2010Teng Lin","orcid":"https://orcid.org/0000-0001-8371-8197"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chin-Teng Lin","raw_affiliation_strings":["Australian Artificial Intelligence Institute (AAII) and the School of Computer Science, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8371-8197","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute (AAII) and the School of Computer Science, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9527,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.9590945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":"12","first_page":"5369","last_page":"5378"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.989799976348877,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/preference","display_name":"Preference","score":0.7366364002227783},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7356253266334534},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5811823606491089},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.48805272579193115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.387207567691803},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.37365996837615967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3151192367076874},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.28775298595428467},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15545231103897095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14964744448661804}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7366364002227783},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7356253266334534},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5811823606491089},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.48805272579193115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.387207567691803},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.37365996837615967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3151192367076874},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28775298595428467},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15545231103897095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14964744448661804}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008124","descriptor_name":"Locomotion","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2021.3084198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3084198","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:34101604","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34101604","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},{"id":"pmh:oai:urm_publish:9916604351001831","is_oa":false,"landing_page_url":"https://hdl.handle.net/11541.2/27029","pdf_url":null,"source":{"id":"https://openalex.org/S4306402528","display_name":"UniSA Research Outputs Repository (University of South Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170239107","host_organization_name":"University of South Australia","host_organization_lineage":["https://openalex.org/I170239107"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1479148548","display_name":null,"funder_award_id":"ONRG-NICOP-N62909-19-1-2058","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"},{"id":"https://openalex.org/G8327365677","display_name":"A closed-loop human\u2013agent learning framework to enhance decision making","funder_award_id":"DE220100265","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320320609","display_name":"University of Tasmania","ror":"https://ror.org/01nfmeh72"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2116671302","https://openalex.org/W2145339207","https://openalex.org/W2154023516","https://openalex.org/W2158782408","https://openalex.org/W2399852338","https://openalex.org/W2462906003","https://openalex.org/W2470789286","https://openalex.org/W2581799494","https://openalex.org/W2604382266","https://openalex.org/W2736601468","https://openalex.org/W2750875954","https://openalex.org/W2781585732","https://openalex.org/W2912423342","https://openalex.org/W2913416895","https://openalex.org/W2940193529","https://openalex.org/W2953384591","https://openalex.org/W2963014947","https://openalex.org/W2964177756","https://openalex.org/W3006334608","https://openalex.org/W3022749764","https://openalex.org/W3035205925","https://openalex.org/W3037213697","https://openalex.org/W3089929416","https://openalex.org/W4288595807","https://openalex.org/W4321392130","https://openalex.org/W6677285668","https://openalex.org/W6713055699","https://openalex.org/W6713134421","https://openalex.org/W6718836005","https://openalex.org/W6720060057","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6743636021","https://openalex.org/W6747387971","https://openalex.org/W6748210908","https://openalex.org/W6758217563","https://openalex.org/W6774482699","https://openalex.org/W6776797931","https://openalex.org/W6780287401","https://openalex.org/W6780559895","https://openalex.org/W6783097404"],"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/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"The":[0,107],"current":[1],"reward":[2,21,215],"learning":[3,14,94,210,216],"from":[4],"human":[5,47,60,69,77,105,110,134,142,162,197,205],"preferences":[6,38,99,206],"could":[7],"be":[8,219],"used":[9],"to":[10,19,95,130,166,221],"resolve":[11],"complex":[12,117],"reinforcement":[13],"(RL)":[15],"tasks":[16,119],"without":[17],"access":[18],"a":[20,25,58,68,89,182],"function":[22],"by":[23,164],"defining":[24],"single":[26,132],"fixed":[27,133],"preference":[28,61,70,111],"between":[29,39,85],"pairs":[30],"of":[31,37,51,79,82,104,149,161,177,187,190,196],"trajectory":[32],"segments.":[33],"However,":[34],"the":[35,76,80,97,102,131,150,154,159,170,175,188],"judgment":[36],"trajectories":[40,86],"is":[41],"not":[42],"dynamic":[43],"and":[44,87,120,156,217],"still":[45],"requires":[46,141],"input":[48],"over":[49],"thousands":[50],"iterations.":[52],"In":[53],"this":[54],"study,":[55],"we":[56,66,180],"proposed":[57,108],"weak":[59,83,109],"supervision":[62,112],"framework,":[63],"for":[64,100,145,213],"which":[65],"developed":[67],"scaling":[71],"model":[72],"that":[73,201],"naturally":[74,203],"reflects":[75],"perception":[78],"degree":[81],"choices":[84],"established":[88,138],"human-demonstration":[90,139],"estimator":[91,140],"through":[92],"supervised":[93,209],"generate":[96],"predicted":[98],"reducing":[101],"number":[103],"inputs.":[106],"framework":[113],"can":[114,218],"effectively":[115],"solve":[116],"RL":[118,223],"achieve":[121],"higher":[122],"cumulative":[123],"rewards":[124],"in":[125],"simulated":[126],"robot":[127],"locomotion-MuJoCo":[128],"games-relative":[129],"preferences.":[135],"Furthermore,":[136],"our":[137,178,202],"feedback":[143],"only":[144],"less":[146],"than":[147],"0.01%":[148],"agent's":[151],"interactions":[152],"with":[153,169,207],"environment":[155],"significantly":[157],"reduces":[158],"cost":[160],"inputs":[163],"up":[165],"30%":[167],"compared":[168],"existing":[171],"approaches.":[172],"To":[173],"present":[174],"flexibility":[176],"approach,":[179],"released":[181],"video":[183],"(https://youtu.be/jQPe1OILT0M)":[184],"showing":[185],"comparisons":[186],"behaviors":[189],"agents":[191],"trained":[192],"on":[193],"different":[194],"types":[195],"input.":[198],"We":[199],"believe":[200],"inspired":[204],"weakly":[208],"are":[211],"beneficial":[212],"precise":[214],"applied":[220],"state-of-the-art":[222],"systems,":[224],"such":[225],"as":[226],"human-autonomy":[227],"teaming":[228],"systems.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}