{"id":"https://openalex.org/W3081788171","doi":"https://doi.org/10.1587/transinf.2019edp7298","title":"Hybrid of Reinforcement and Imitation Learning for Human-Like Agents","display_name":"Hybrid of Reinforcement and Imitation Learning for Human-Like Agents","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3081788171","doi":"https://doi.org/10.1587/transinf.2019edp7298","mag":"3081788171"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7298","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7298","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7298/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7298/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081912903","display_name":"Rousslan Fernand Julien Dossa","orcid":"https://orcid.org/0000-0003-0572-692X"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rousslan F. J. DOSSA","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063628500","display_name":"Xinyu Lian","orcid":"https://orcid.org/0009-0003-8143-4862"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xinyu LIAN","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059473234","display_name":"Nomoto Hirokazu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125814","display_name":"Equilibrium Research","ror":"https://ror.org/03gcx9p86","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210125814"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hirokazu NOMOTO","raw_affiliation_strings":["EQUOS RESEARCH Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EQUOS RESEARCH Co., Ltd","institution_ids":["https://openalex.org/I4210125814"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068667478","display_name":"Takashi Matsubara","orcid":"https://orcid.org/0000-0003-0642-4800"},"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":"Takashi MATSUBARA","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023847482","display_name":"Kuniaki Uehara","orcid":"https://orcid.org/0000-0002-7160-3752"},"institutions":[{"id":"https://openalex.org/I11381156","display_name":"Osaka Gakuin University","ror":"https://ror.org/04a8t1e98","country_code":"JP","type":"education","lineage":["https://openalex.org/I11381156"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuniaki UEHARA","raw_affiliation_strings":["Faculty of Business Administration, Osaka Gakuin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Business Administration, Osaka Gakuin University","institution_ids":["https://openalex.org/I11381156"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3911,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68939452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"E103.D","issue":"9","first_page":"1960","last_page":"1970"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9484000205993652,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8526431322097778},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8338919878005981},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6648310422897339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.622307538986206},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5268845558166504},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4664928913116455},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4521132707595825},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44072216749191284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42566001415252686},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3286382257938385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526431322097778},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8338919878005981},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6648310422897339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.622307538986206},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5268845558166504},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4664928913116455},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4521132707595825},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44072216749191284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42566001415252686},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3286382257938385},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7298","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7298","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7298/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7298","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7298","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7298/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1218567653","display_name":"Development of Multimodal Data Retrieval Engine Based on Human Cognitive System","funder_award_id":"19H04172","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6127555850","display_name":"Uncertainty in Deep Learning for Undetstanding Data Mechanism and Anomaly Detection","funder_award_id":"19K20344","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338243","display_name":"JST-Mirai Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081788171.pdf","grobid_xml":"https://content.openalex.org/works/W3081788171.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W112666333","https://openalex.org/W1522301498","https://openalex.org/W1777239053","https://openalex.org/W1821462560","https://openalex.org/W1850531616","https://openalex.org/W1931054966","https://openalex.org/W1931877416","https://openalex.org/W2095705004","https://openalex.org/W2104805229","https://openalex.org/W2121863487","https://openalex.org/W2136065562","https://openalex.org/W2137549137","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2260756217","https://openalex.org/W2434014514","https://openalex.org/W2530849036","https://openalex.org/W2583993537","https://openalex.org/W2607198029","https://openalex.org/W2623491082","https://openalex.org/W2727840223","https://openalex.org/W2766447205","https://openalex.org/W2789740610","https://openalex.org/W2924268550","https://openalex.org/W2925314672","https://openalex.org/W2962957031","https://openalex.org/W2963098081","https://openalex.org/W2963099939","https://openalex.org/W2963625099","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964250417","https://openalex.org/W2977322142","https://openalex.org/W3100944043","https://openalex.org/W3103780890","https://openalex.org/W4214717370","https://openalex.org/W4394639904"],"related_works":["https://openalex.org/W207075081","https://openalex.org/W2164258403","https://openalex.org/W2023953290","https://openalex.org/W2085786406","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W2779259119","https://openalex.org/W4319083788","https://openalex.org/W3210520478"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,60,101,121],"methods":[2],"achieve":[3],"performance":[4,20,75,116],"superior":[5],"to":[6,78,89],"humans":[7],"in":[8,31],"a":[9,32,54,65,70,86,91,114,118,132],"wide":[10],"range":[11],"of":[12,64],"complex":[13],"tasks":[14],"and":[15,44,46,68,93,99,104,123],"uncertain":[16],"environments.":[17],"However,":[18,73],"high":[19],"is":[21,47,76,129],"not":[22],"the":[23,62,79],"sole":[24],"metric":[25],"for":[26,50,56,102],"practical":[27],"use":[28],"such":[29],"as":[30],"game":[33],"AI":[34],"or":[35],"autonomous":[36],"driving.":[37],"A":[38],"highly":[39],"efficient":[40,94],"agent":[41,95,112,122],"performs":[42],"greedily":[43],"selfishly,":[45],"thus":[48],"inconvenient":[49],"surrounding":[51],"users,":[52],"hence":[53],"demand":[55],"human-like":[57,71,92,126],"agents.":[58],"Imitation":[59],"reproduces":[61],"behavior":[63],"human":[66,133],"expert":[67],"builds":[69],"agent.":[72],"its":[74],"limited":[77],"expert's.":[80],"In":[81],"this":[82],"study,":[83],"we":[84],"propose":[85],"training":[87],"scheme":[88],"construct":[90],"via":[96,131],"mixing":[97],"reinforcement":[98],"imitation":[100,120],"discrete":[103],"continuous":[105],"action":[106],"space":[107],"problems.":[108],"The":[109],"proposed":[110],"hybrid":[111],"achieves":[113],"higher":[115],"than":[117],"strict":[119],"exhibits":[124],"more":[125],"behavior,":[127],"which":[128],"measured":[130],"sensitivity":[134],"test.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}