{"id":"https://openalex.org/W3093713113","doi":"https://doi.org/10.1109/ro-man47096.2020.9223516","title":"Human Social Feedback for Efficient Interactive Reinforcement Agent Learning","display_name":"Human Social Feedback for Efficient Interactive Reinforcement Agent Learning","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3093713113","doi":"https://doi.org/10.1109/ro-man47096.2020.9223516","mag":"3093713113"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man47096.2020.9223516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-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/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":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"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/A5090585862","display_name":"Qilei Zhang","orcid":"https://orcid.org/0000-0002-5718-0319"},"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":"Qilei Zhang","raw_affiliation_strings":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"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":"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":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and 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":["College of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"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":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6771,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77205813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"706","last_page":"712"},"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":0.9690999984741211,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9638000130653381,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8558188080787659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507021427154541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6550419330596924},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5637208819389343},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5593875646591187},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5375131964683533},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5317809581756592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48132169246673584},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33134961128234863},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09628412127494812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07361015677452087}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8558188080787659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507021427154541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6550419330596924},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5637208819389343},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5593875646591187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5375131964683533},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5317809581756592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48132169246673584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33134961128234863},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09628412127494812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07361015677452087},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man47096.2020.9223516","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W32403112","https://openalex.org/W121023703","https://openalex.org/W214582704","https://openalex.org/W745775011","https://openalex.org/W1453801241","https://openalex.org/W1503384494","https://openalex.org/W1816914876","https://openalex.org/W2111119385","https://openalex.org/W2114864106","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2132504164","https://openalex.org/W2140584963","https://openalex.org/W2156869222","https://openalex.org/W2157726050","https://openalex.org/W2168438882","https://openalex.org/W2169562625","https://openalex.org/W2419349576","https://openalex.org/W2539402368","https://openalex.org/W2580300496","https://openalex.org/W2898227854","https://openalex.org/W2911719076","https://openalex.org/W2913668833","https://openalex.org/W2944766483","https://openalex.org/W2963489214","https://openalex.org/W3005891386","https://openalex.org/W3013640622","https://openalex.org/W4214717370","https://openalex.org/W4288593469","https://openalex.org/W4297736515","https://openalex.org/W6604963999","https://openalex.org/W6608628637","https://openalex.org/W6676661950","https://openalex.org/W6677151524","https://openalex.org/W6684746707","https://openalex.org/W6717094648","https://openalex.org/W6732417791","https://openalex.org/W6745588108","https://openalex.org/W6755473067","https://openalex.org/W6758427599"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W3196817267"],"abstract_inverted_index":{"As":[0],"a":[1,79,86,93,105,159,179,188,215],"branch":[2],"of":[3,25,35,130,149,164,193,211,251],"reinforcement":[4,7,62,117],"learning,":[5],"interactive":[6,61],"learning":[8,63,118,143,165,174,194,249],"mainly":[9],"studies":[10],"the":[11,23,36,128,131,134,147,154,183,208,219,223,229,248],"interaction":[12],"process":[13,226],"between":[14],"humans":[15],"and":[16,28,82,123,125],"agents,":[17],"allowing":[18],"agents":[19,101,252],"to":[20,30,42,69,99,103,108,127,162,191],"learn":[21,70],"from":[22,71,144,166,175,195],"intentions":[24],"human":[26,39,72,242,255],"users":[27,40],"adapt":[29],"their":[31,109],"preferences.":[32,110],"In":[33],"most":[34],"current":[37],"studies,":[38],"need":[41],"intentionally":[43],"provide":[44],"explicit":[45],"feedback":[46,77,84,146,168,177,197,201,213],"via":[47,78,85],"pressing":[48],"keyboard":[49],"buttons":[50],"or":[51],"mouse":[52],"clicks.":[53],"However,":[54],"in":[55,115,222,228],"our":[56,113,204,234],"paper,":[57],"we":[58],"proposed":[59],"an":[60,67],"method":[64,91,114],"that":[65,141,163,192,207,237],"facilitates":[66],"agent":[68,156,185,220],"social":[73,243],"signals":[74,244],"-":[75,121,133],"facial":[76,145,212],"ordinary":[80,97],"camera":[81],"gestural":[83,176],"leap":[87],"motion":[88],"sensor.":[89],"Our":[90,137],"provides":[92],"natural":[94],"way":[95],"for":[96],"people":[98],"train":[100],"how":[102],"perform":[104],"task":[106],"according":[107],"We":[111],"tested":[112],"two":[116],"benchmarking":[119],"domains":[120],"LoopMaze":[122],"Tetris,":[124],"compared":[126],"state":[129],"art":[132],"TAMER":[135,155,184],"framework.":[136],"experimental":[138],"results":[139,205,235],"show":[140],"when":[142],"recognition":[148,209,240],"which":[150],"is":[151],"very":[152],"low,":[153],"can":[157,186,245],"get":[158],"similar":[160,189],"performance":[161,190,221],"keypress":[167,196],"with":[169,178,198,238,253],"slightly":[170],"more":[171,180],"feedback.":[172,256],"When":[173],"accurate":[181],"recognition,":[182],"obtain":[187],"much":[199],"less":[200,254],"received.":[202],"Moreover,":[203],"indicate":[206,236],"error":[210],"has":[214],"large":[216],"effect":[217],"on":[218],"beginning":[224],"training":[225,231],"than":[227],"later":[230],"stage.":[232],"Finally,":[233],"enough":[239],"accuracy,":[241],"effectively":[246],"improve":[247],"efficiency":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}