{"id":"https://openalex.org/W4396542881","doi":"https://doi.org/10.1109/mhs59931.2023.10510080","title":"Study on High-Level Structure of cognition control construction in Exploration and Exploitation within Multi-Armed Bandit Model of Reinforcement Learning","display_name":"Study on High-Level Structure of cognition control construction in Exploration and Exploitation within Multi-Armed Bandit Model of Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-20","ids":{"openalex":"https://openalex.org/W4396542881","doi":"https://doi.org/10.1109/mhs59931.2023.10510080"},"language":"en","primary_location":{"id":"doi:10.1109/mhs59931.2023.10510080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mhs59931.2023.10510080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)","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/A5082588749","display_name":"Jiaxing Tian","orcid":"https://orcid.org/0000-0002-1473-8474"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jiaxing Tian","raw_affiliation_strings":["Graduate School of Science and Technology, University of Tsukuba,Empowerment Informatics","Empowerment Informatics, Graduate School of Science and Technology, University of Tsukuba"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Technology, University of Tsukuba,Empowerment Informatics","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Empowerment Informatics, Graduate School of Science and Technology, University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":null,"display_name":"Izawa Jun","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Izawa Jun","raw_affiliation_strings":["Institute of Systems and Information Engineering, University of Tsukuba Tennodai 1-1-1,Tsukuba, Ibaraki,Japan,305-8573"],"affiliations":[{"raw_affiliation_string":"Institute of Systems and Information Engineering, University of Tsukuba Tennodai 1-1-1,Tsukuba, Ibaraki,Japan,305-8573","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082588749"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22402708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9890000224113464,"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":0.9890000224113464,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9617999792098999,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9577999711036682,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.835450291633606},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.6368557214736938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6117236018180847},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6060354113578796},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5526431798934937},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5121150016784668},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.427815705537796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42039138078689575},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20077815651893616},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18503224849700928},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06675601005554199}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.835450291633606},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.6368557214736938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6117236018180847},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6060354113578796},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5526431798934937},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5121150016784668},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.427815705537796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42039138078689575},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20077815651893616},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18503224849700928},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06675601005554199},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mhs59931.2023.10510080","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mhs59931.2023.10510080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Micro-NanoMehatronics and Human Science (MHS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2012418261","https://openalex.org/W2044924321","https://openalex.org/W2059320470","https://openalex.org/W2078943705","https://openalex.org/W2084300636","https://openalex.org/W2150328967","https://openalex.org/W2170961478","https://openalex.org/W2495612759","https://openalex.org/W3115652637","https://openalex.org/W3193145993","https://openalex.org/W4285098202"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,43],"models":[2],"have":[3],"been":[4],"instrumental":[5],"in":[6,41,109],"simulating":[7],"the":[8,35,76,82,90,94,100,113,120],"behaviors":[9],"of":[10,93],"animals":[11],"and":[12,16,39,86,143],"humans,":[13],"whose":[14],"actions":[15],"choices":[17],"are":[18],"largely":[19],"influenced":[20],"by":[21],"rewards.":[22,106],"This":[23,45,79,126],"study":[24],"proposes":[25],"a":[26,59,64,69,97],"high-level":[27,70],"environmental":[28,54,124,141],"monitoring":[29],"structure":[30,73,80,129],"into":[31],"cognitive":[32,77],"models,":[33],"optimizing":[34],"balance":[36,83],"between":[37,84],"exploration":[38,85,103,117,144],"exploitation":[40,87],"reinforcement":[42],"theory.":[44],"approach":[46],"allows":[47],"for":[48,133],"more":[49],"flexible":[50],"adaptation":[51],"to":[52,89,104,118,140],"complex":[53],"changes.":[55,125],"We":[56],"focus":[57],"on":[58,75],"multi-armed":[60],"bandit":[61],"task,":[62],"incorporating":[63],"hierarchical":[65,128],"model":[66,101,114],"that":[67],"adds":[68],"cognition":[71],"control":[72],"based":[74],"system.":[78],"adjusts":[81],"according":[88],"perceived":[91],"uncertainty":[92,142],"environment.":[95],"In":[96,107],"stable":[98],"environment,":[99,112],"minimizes":[102],"maximize":[105],"contrast,":[108],"an":[110],"unstable":[111],"promotes":[115],"rapid":[116],"identify":[119],"best":[121],"strategy":[122],"after":[123],"cognition-based":[127],"offers":[130],"valuable":[131],"insights":[132],"future":[134],"studies":[135],"about":[136],"analyzing":[137],"human":[138],"responses":[139],"behavior.":[145]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}