{"id":"https://openalex.org/W2728201397","doi":"https://doi.org/10.1007/s10458-017-9374-8","title":"Social interaction for efficient agent learning from human reward","display_name":"Social interaction for efficient agent learning from human reward","publication_year":2017,"publication_date":"2017-07-03","ids":{"openalex":"https://openalex.org/W2728201397","doi":"https://doi.org/10.1007/s10458-017-9374-8","mag":"2728201397"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-017-9374-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-017-9374-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10458-017-9374-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","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%2Fs10458-017-9374-8.pdf","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Guangliang Li","raw_affiliation_strings":["Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1728-5711","affiliations":[{"raw_affiliation_string":"Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["University of Oxford, Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056649746","display_name":"W. Bradley Knox","orcid":"https://orcid.org/0000-0002-6006-9523"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bradley Knox","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061353073","display_name":"Hayley Hung","orcid":"https://orcid.org/0000-0001-9574-5395"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hayley Hung","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101812014"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.4943,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91687055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9817000031471252,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.941100001335144,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/trainer","display_name":"Trainer","score":0.9160391688346863},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6495087146759033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5454526543617249},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5196408033370972},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4953650236129761},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4903430938720703},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.41011911630630493},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39131098985671997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30077749490737915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12410047650337219}],"concepts":[{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.9160391688346863},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6495087146759033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5454526543617249},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5196408033370972},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4953650236129761},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4903430938720703},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.41011911630630493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39131098985671997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30077749490737915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12410047650337219},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-017-9374-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-017-9374-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10458-017-9374-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:tud:oai:tudelft.nl:uuid:0d7c1f54-57e2-47e4-b247-1c4252f76820","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:0d7c1f54-57e2-47e4-b247-1c4252f76820","pdf_url":"http://resolver.tudelft.nl/uuid:0d7c1f54-57e2-47e4-b247-1c4252f76820","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Autonomous Agents and Multi-Agent Systems, 32(1)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10458-017-9374-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-017-9374-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10458-017-9374-8.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"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"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2728201397.pdf","grobid_xml":"https://content.openalex.org/works/W2728201397.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W48268975","https://openalex.org/W70760313","https://openalex.org/W121023703","https://openalex.org/W610349085","https://openalex.org/W1453801241","https://openalex.org/W1490153224","https://openalex.org/W1515851193","https://openalex.org/W1536323281","https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1591803298","https://openalex.org/W1777239053","https://openalex.org/W1888002310","https://openalex.org/W1986014385","https://openalex.org/W1998933811","https://openalex.org/W2010047273","https://openalex.org/W2027106130","https://openalex.org/W2069734023","https://openalex.org/W2074056782","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2107574152","https://openalex.org/W2111119385","https://openalex.org/W2114864106","https://openalex.org/W2115064627","https://openalex.org/W2116157560","https://openalex.org/W2118756286","https://openalex.org/W2121110499","https://openalex.org/W2121665678","https://openalex.org/W2121863487","https://openalex.org/W2122982548","https://openalex.org/W2123859855","https://openalex.org/W2129659607","https://openalex.org/W2132504164","https://openalex.org/W2134372241","https://openalex.org/W2147489905","https://openalex.org/W2151570541","https://openalex.org/W2154633587","https://openalex.org/W2156384466","https://openalex.org/W2156869222","https://openalex.org/W2157174816","https://openalex.org/W2167724517","https://openalex.org/W2171691785","https://openalex.org/W2290053245","https://openalex.org/W2294422333","https://openalex.org/W2316716009","https://openalex.org/W2406827402","https://openalex.org/W2515171688","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6601295022","https://openalex.org/W6635327058","https://openalex.org/W6677151524","https://openalex.org/W6677916085","https://openalex.org/W6696265566","https://openalex.org/W7019546885"],"related_works":["https://openalex.org/W1866966336","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W4285792946","https://openalex.org/W4388176369","https://openalex.org/W2000494260","https://openalex.org/W154293939","https://openalex.org/W2035734194","https://openalex.org/W2912415823","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Learning":[0],"from":[1,208],"rewards":[2],"generated":[3],"by":[4,114,184,187],"a":[5,18,117,197,201,232,237],"human":[6,84],"trainer":[7,46,55,158],"observing":[8],"an":[9],"agent":[10,58,148],"in":[11,116,125],"action":[12],"has":[13],"been":[14],"proven":[15],"to":[16,25,64,149,163,168,222,226],"be":[17,60,206],"powerful":[19],"method":[20],"for":[21,30],"teaching":[22],"autonomous":[23],"agents":[24,112,170,182,225],"perform":[26],"challenging":[27],"tasks,":[28],"especially":[29],"those":[31],"non-technical":[32],"users.":[33],"Since":[34],"the":[35,43,45,51,54,57,66,69,75,78,83,89,103,120,123,126,131,136,142,147,157,174,189,209,213],"efficacy":[36],"of":[37,68,77,94,111,122],"this":[38,154],"approach":[39],"depends":[40],"critically":[41],"on":[42,82],"reward":[44],"provides,":[47],"we":[48],"consider":[49],"how":[50],"interaction":[52],"between":[53],"and":[56,88,109,129,172,191,212],"should":[59],"designed":[61],"so":[62],"as":[63],"increase":[65],"efficiency":[67],"training":[70,86],"process.":[71],"This":[72],"article":[73],"investigates":[74],"influence":[76],"agent\u2019s":[79,90,104,160,175,214],"socio-competitive":[80,106],"feedback":[81,155,194,218],"trainer\u2019s":[85,210],"behavior":[87],"learning.":[91,176],"The":[92],"results":[93],"our":[95],"user":[96],"study":[97],"with":[98],"85":[99],"participants":[100,124,137,167,221],"suggest":[101],"that":[102,181,204,229],"passive":[105,190],"feedback\u2014showing":[107],"performance":[108,161,199,234],"score":[110,202,238],"trained":[113,183],"trainers":[115,185],"leaderboard\u2014substantially":[118],"increases":[119],"engagement":[121],"game":[127,143],"task":[128],"improves":[130,173],"agents\u2019":[132],"performance,":[133],"even":[134],"though":[135],"do":[138,150],"not":[139],"directly":[140],"play":[141],"but":[144],"instead":[145],"train":[146,169,224],"so.":[151],"Moreover,":[152],"making":[153],"active\u2014sending":[156],"her":[159],"relative":[162],"others\u2014further":[164],"induces":[165],"more":[166],"longer":[171],"Our":[177],"further":[178,223],"analysis":[179],"shows":[180],"affected":[186],"both":[188],"active":[192,216],"social":[193,217],"could":[195,205],"obtain":[196,231],"higher":[198,233],"under":[200,235],"mechanism":[203],"optimized":[207],"perspective":[211],"additional":[215],"can":[219,230],"keep":[220],"learn":[227],"policies":[228],"such":[236],"mechanism.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
