{"id":"https://openalex.org/W3023933011","doi":"https://doi.org/10.1109/ro-man47096.2020.9223451","title":"Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies","display_name":"Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3023933011","doi":"https://doi.org/10.1109/ro-man47096.2020.9223451","mag":"3023933011"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man47096.2020.9223451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223451","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.03987","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020458999","display_name":"R\u00e9mi Dromnelle","orcid":"https://orcid.org/0000-0002-7322-2523"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Remi Dromnelle","raw_affiliation_strings":["Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","Pierre-and-Marie-Curie University"],"affiliations":[{"raw_affiliation_string":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]},{"raw_affiliation_string":"Pierre-and-Marie-Curie University","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024513825","display_name":"Beno\u00eet Girard","orcid":"https://orcid.org/0000-0002-8117-7064"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Girard","raw_affiliation_strings":["Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004027918","display_name":"Erwan Renaudo","orcid":"https://orcid.org/0000-0003-3282-8972"},"institutions":[{"id":"https://openalex.org/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Erwan Renaudo","raw_affiliation_strings":["Universitat Innsbruck,Intelligent and Interactive Systems Group,Innsbruck,Austria"],"affiliations":[{"raw_affiliation_string":"Universitat Innsbruck,Intelligent and Interactive Systems Group,Innsbruck,Austria","institution_ids":["https://openalex.org/I190249584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114376610","display_name":"Raja Chatila","orcid":"https://orcid.org/0000-0001-7822-0634"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Raja Chatila","raw_affiliation_strings":["Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016381589","display_name":"Mehdi Khamassi","orcid":"https://orcid.org/0000-0002-2515-1046"},"institutions":[{"id":"https://openalex.org/I4210150358","display_name":"Institut Syst\u00e8mes Intelligents et de Robotique","ror":"https://ror.org/05neq8668","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I39804081","https://openalex.org/I4210150358","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mehdi Khamassi","raw_affiliation_strings":["Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Université,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9,Institute of Intelligent Systems and Robotics,Paris,France","institution_ids":["https://openalex.org/I4210150358","https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020458999"],"corresponding_institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210150358"],"apc_list":null,"apc_paid":null,"fwci":0.1371,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53639891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"612","last_page":"617"},"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":0.9976000189781189,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7806323766708374},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6361621618270874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5735946893692017},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5700557827949524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5503654479980469},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5476173758506775},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5182990431785583},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3934665024280548},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3215218186378479},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.20176607370376587},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1746949553489685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11524620652198792}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7806323766708374},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6361621618270874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5735946893692017},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5700557827949524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503654479980469},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5476173758506775},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5182990431785583},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3934665024280548},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3215218186378479},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.20176607370376587},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1746949553489685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11524620652198792},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":7,"locations":[{"id":"doi:10.1109/ro-man47096.2020.9223451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ro-man47096.2020.9223451","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"},{"id":"pmh:oai:arXiv.org:2005.03987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.03987","pdf_url":"https://arxiv.org/pdf/2005.03987","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3023933011","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.03987v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-02883717v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-02883717","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020)","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02899767v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-02899767","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE RO-MAN 2020","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-02899767v2","is_oa":true,"landing_page_url":"https://hal.science/hal-02899767","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020), Aug 2020, Naples (en ligne), Italy. ⟨10.1109/RO-MAN47096.2020.9223451⟩","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2005.03987","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.03987","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.03987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.03987","pdf_url":"https://arxiv.org/pdf/2005.03987","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W8140010","https://openalex.org/W1152374494","https://openalex.org/W1515851193","https://openalex.org/W2045089344","https://openalex.org/W2090161303","https://openalex.org/W2098441518","https://openalex.org/W2116157560","https://openalex.org/W2167362547","https://openalex.org/W2294422333","https://openalex.org/W2395263189","https://openalex.org/W2396715201","https://openalex.org/W2769771125","https://openalex.org/W3020831056","https://openalex.org/W3044387171","https://openalex.org/W3116844635","https://openalex.org/W4214717370","https://openalex.org/W4249667184","https://openalex.org/W6600358712","https://openalex.org/W6674812091","https://openalex.org/W6677262939","https://openalex.org/W6696972564","https://openalex.org/W6711819936","https://openalex.org/W6746034202","https://openalex.org/W6788369252"],"related_works":["https://openalex.org/W3046547158","https://openalex.org/W2824479732","https://openalex.org/W2918544916","https://openalex.org/W2795577874","https://openalex.org/W2048497019","https://openalex.org/W2287257424","https://openalex.org/W2913184176","https://openalex.org/W3167073030","https://openalex.org/W2774894600","https://openalex.org/W3181385848","https://openalex.org/W3091667945","https://openalex.org/W2897664012","https://openalex.org/W2485586407","https://openalex.org/W2766273539","https://openalex.org/W2980045354","https://openalex.org/W2526379199","https://openalex.org/W2969015047","https://openalex.org/W3012113410","https://openalex.org/W1323832","https://openalex.org/W3127658528"],"abstract_inverted_index":{"An":[0],"important":[1],"current":[2],"challenge":[3],"in":[4,24,72,90,104],"Human-Robot":[5],"Interaction":[6],"(HRI)":[7],"is":[8,149],"to":[9,12,32,40,87,115,161],"enable":[10],"robots":[11],"learn":[13],"on-the-fly":[14],"from":[15],"human":[16,63,143,169],"feedback.":[17,170],"However,":[18],"humans":[19],"show":[20,95],"a":[21,58,77,91,133,158],"great":[22],"variability":[23,139],"the":[25,38,62,65,69,73,116,121,130,138,141,155],"way":[26,160],"they":[27],"reward":[28],"robots.":[29],"We":[30,53,94],"propose":[31],"address":[33],"this":[34,82,152],"issue":[35],"by":[36,151],"enabling":[37],"robot":[39,66,105,163],"combine":[41],"different":[42],"learning":[43,164],"strategies,":[44],"namely":[45],"model-based":[46],"(MB)":[47],"and":[48,76],"model-free":[49],"(MF)":[50],"reinforcement":[51],"learning.":[52],"simulate":[54],"two":[55],"HRI":[56],"scenarios:":[57],"simple":[59],"task":[60,83],"where":[61,84],"congratulates":[64],"for":[67],"putting":[68],"right":[70,74],"cubes":[71,85],"boxes,":[75],"more":[78],"complicated":[79],"version":[80],"of":[81,140],"have":[86],"be":[88],"placed":[89],"specific":[92],"order.":[93],"that":[96],"our":[97],"existing":[98],"MB-MF":[99],"coordination":[100],"algorithm":[101,131],"previously":[102],"tested":[103],"navigation":[106],"works":[107],"well":[108],"here":[109],"without":[110],"retuning":[111],"parameters.":[112],"It":[113],"leads":[114],"maximal":[117],"performance":[118,135],"while":[119,145],"producing":[120],"same":[122],"minimal":[123],"computational":[124],"cost":[125],"as":[126],"MF":[127],"alone.":[128],"Moreover,":[129],"gives":[132],"robust":[134],"no":[136],"matter":[137],"simulated":[142],"feedback,":[144],"each":[146],"strategy":[147],"alone":[148],"impacted":[150],"variability.":[153],"Overall,":[154],"results":[156],"suggest":[157],"promising":[159],"promote":[162],"flexibility":[165],"when":[166],"facing":[167],"variable":[168]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}