{"id":"https://openalex.org/W2073995413","doi":"https://doi.org/10.1109/iros.2005.1545206","title":"Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning","display_name":"Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2073995413","doi":"https://doi.org/10.1109/iros.2005.1545206","mag":"2073995413"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2005.1545206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2005.1545206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-38199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055732660","display_name":"Noriaki Mitsunaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"N. Mitsunaga","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories"],"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060213000","display_name":"Christian Smith","orcid":"https://orcid.org/0000-0003-2078-8854"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"C. Smith","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories","Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories","institution_ids":[]},{"raw_affiliation_string":"Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028939608","display_name":"Takayuki Kanda","orcid":"https://orcid.org/0000-0002-9546-5825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Kanda","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories"],"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Ishiguro","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories","Graduate School of Engineering, Osaka University, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Engineering, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015175458","display_name":"Norihiro Hagita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Hagita","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories"],"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055732660"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4587,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.97086189,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"218","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8363634347915649},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.778846800327301},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7510436177253723},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.6955040693283081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6758792996406555},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5415281653404236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310647487640381},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5293313264846802},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.4933258593082428},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.47625041007995605},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4660182297229767},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4475265443325043},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4465765058994293},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12616440653800964},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05698952078819275}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8363634347915649},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.778846800327301},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7510436177253723},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6955040693283081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758792996406555},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5415281653404236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310647487640381},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5293313264846802},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.4933258593082428},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.47625041007995605},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4660182297229767},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4475265443325043},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4465765058994293},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12616440653800964},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05698952078819275},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2005.1545206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2005.1545206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-38199","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-38199","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-38199","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-38199","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W20116688","https://openalex.org/W63886951","https://openalex.org/W1966725752","https://openalex.org/W2026000422","https://openalex.org/W2031375782","https://openalex.org/W2118756286","https://openalex.org/W2139053308","https://openalex.org/W2139274531","https://openalex.org/W2144446635","https://openalex.org/W2153458938","https://openalex.org/W2155027007","https://openalex.org/W2160422000","https://openalex.org/W3103182070","https://openalex.org/W6602531481"],"related_works":["https://openalex.org/W4388576605","https://openalex.org/W2062302545","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564"],"abstract_inverted_index":{"In":[0],"this":[1,38,57],"paper,":[2],"we":[3],"propose":[4,19],"an":[5,65],"adaptation":[6,60],"mechanism":[7,22],"for":[8],"robot":[9],"behaviors":[10],"to":[11,40,61],"make":[12],"robot-human":[13],"interactions":[14],"run":[15],"more":[16],"smoothly.":[17],"We":[18,54],"such":[20],"a":[21,33],"based":[23],"on":[24],"reinforcement":[25],"learning,":[26],"which":[27],"reads":[28],"minute":[29],"body":[30],"signals":[31],"from":[32],"human":[34],"partner,":[35],"and":[36,46,49],"uses":[37],"information":[39],"adjust":[41],"interaction":[42],"distances,":[43],"gaze":[44],"meeting,":[45],"motion":[47],"speed":[48],"timing":[50],"in":[51],"human-robot":[52],"interaction.":[53],"show":[55],"that":[56],"enables":[58],"autonomous":[59],"individual":[62],"preferences":[63],"by":[64],"experiment":[66],"with":[67],"twelve":[68],"subjects.":[69]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
