{"id":"https://openalex.org/W4365800577","doi":"https://doi.org/10.1109/lra.2023.3267385","title":"Outperformance of Mall-Receptionist Android as Inverse Reinforcement Learning is Transitioned to Reinforcement Learning","display_name":"Outperformance of Mall-Receptionist Android as Inverse Reinforcement Learning is Transitioned to Reinforcement Learning","publication_year":2023,"publication_date":"2023-04-14","ids":{"openalex":"https://openalex.org/W4365800577","doi":"https://doi.org/10.1109/lra.2023.3267385"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3267385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3267385","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-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/A5025153228","display_name":"Zhichao Chen","orcid":"https://orcid.org/0000-0002-1362-7940"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhichao Chen","raw_affiliation_strings":["Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan","Graduate School of Engineering Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1362-7940","affiliations":[{"raw_affiliation_string":"Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan","institution_ids":["https://openalex.org/I4210110652"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011580159","display_name":"Yutaka Nakamura","orcid":"https://orcid.org/0000-0001-6307-5104"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Nakamura","raw_affiliation_strings":["Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6307-5104","affiliations":[{"raw_affiliation_string":"Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"last","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":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0805-7648","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0621,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88628239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"8","issue":"6","first_page":"3350","last_page":"3357"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9783999919891357,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7837003469467163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7172508239746094},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5976510047912598},{"id":"https://openalex.org/keywords/android","display_name":"Android (operating system)","score":0.5540307760238647},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5505903959274292},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4845925569534302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48430362343788147},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.446174681186676},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4165090024471283},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14049074053764343}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7837003469467163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172508239746094},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5976510047912598},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.5540307760238647},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5505903959274292},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4845925569534302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48430362343788147},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.446174681186676},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4165090024471283},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14049074053764343},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3267385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3267385","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2022365837","https://openalex.org/W2145339207","https://openalex.org/W2227909145","https://openalex.org/W2737258237","https://openalex.org/W2761873684","https://openalex.org/W2890001928","https://openalex.org/W2902907165","https://openalex.org/W2967199722","https://openalex.org/W2981030070","https://openalex.org/W4205213211","https://openalex.org/W4210870706","https://openalex.org/W4285194984","https://openalex.org/W4286904999","https://openalex.org/W4389666601","https://openalex.org/W6696380822","https://openalex.org/W6714580625","https://openalex.org/W6718092244","https://openalex.org/W6732837357","https://openalex.org/W6759225949","https://openalex.org/W6769174716","https://openalex.org/W6796613488","https://openalex.org/W6797399245"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2185469136","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Robots":[0],"can":[1],"tackle":[2],"human\u2013robot":[3],"interaction":[4,58],"(HRI)":[5],"tasks":[6],"through":[7],"inverse":[8,45],"reinforcement":[9,46,49],"learning":[10,47,50,120,141],"(IRL).":[11],"However,":[12],"offline":[13],"IRL":[14],"agents'":[15],"performance":[16],"is":[17],"upper-bounded":[18],"by":[19],"experts.":[20],"Limited":[21],"demonstration":[22],"fails":[23],"to":[24,48,112,117,137,145],"provide":[25],"an":[26],"overall":[27],"picture":[28],"of":[29,92,109],"the":[30,70,73,83,107,110,130],"environment,":[31],"especially":[32],"in":[33,60,115,148],"real-world":[34,56,150],"applications.":[35,152],"To":[36],"further":[37],"enhance":[38],"IRL's":[39],"performance,":[40],"we":[41,87],"implement":[42],"a":[43,55,62,76,98,123],"cross-modal":[44],"(IRL-to-RL)":[51],"transition":[52],"framework":[53,111,136],"for":[54,101],"HRI":[57,151],"task,":[59],"which":[61],"mall":[63],"receptionist":[64],"android":[65,74],"promotes":[66],"sanitizer":[67],"usage.":[68],"During":[69],"10-day":[71],"experiment,":[72],"develops":[75],"more":[77,139,149],"proactive":[78],"and":[79,96,127],"effective":[80],"strategy":[81],"than":[82],"human":[84,131],"expert.":[85,132],"Furthermore,":[86],"explore":[88],"four":[89],"decay":[90],"modes":[91],"prior":[93],"knowledge":[94],"supervision":[95],"suggest":[97],"preferable":[99],"pattern":[100],"practical":[102],"use.":[103],"Our":[104],"results":[105],"demonstrate":[106],"feasibility":[108],"assist":[113],"robots":[114,144],"switching":[116],"diverse":[118],"modalities,":[119],"incrementally":[121],"with":[122],"sparse":[124],"reward":[125],"function,":[126],"eventually":[128],"outperforming":[129],"We":[133],"anticipate":[134],"our":[135],"inspire":[138],"IRL-to-better":[140],"paradigms,":[142],"facilitating":[143],"outcompete":[146],"teachers":[147]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}