{"id":"https://openalex.org/W1997861816","doi":"https://doi.org/10.1109/icsmc.2010.5642266","title":"Complex-valued reinforcement learning with hierarchical architecture","display_name":"Complex-valued reinforcement learning with hierarchical architecture","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W1997861816","doi":"https://doi.org/10.1109/icsmc.2010.5642266","mag":"1997861816"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2010.5642266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","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/A5076930751","display_name":"Atsuhiro Yamazaki","orcid":null},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Atsuhiro Yamazaki","raw_affiliation_strings":["Graduate School of Engineering, Yokohama National University, Yokohama, Japan","Graduate School of Engineering, Yokohama National University, YNU, 79-5 Tokiwadai, Hodogayaku, Yokohama JAPAN"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Yokohama National University, Yokohama, Japan","institution_ids":["https://openalex.org/I180203408"]},{"raw_affiliation_string":"Graduate School of Engineering, Yokohama National University, YNU, 79-5 Tokiwadai, Hodogayaku, Yokohama JAPAN","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008935743","display_name":"Tomoki Hamagami","orcid":"https://orcid.org/0000-0002-2649-3777"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hamagami","raw_affiliation_strings":["Graduate School of Engineering, Yokohama National University, Yokohama, Japan","Graduate School of Engineering, Yokohama National University, YNU, 79-5 Tokiwadai, Hodogayaku, Yokohama JAPAN"],"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Yokohama National University, Yokohama, Japan","institution_ids":["https://openalex.org/I180203408"]},{"raw_affiliation_string":"Graduate School of Engineering, Yokohama National University, YNU, 79-5 Tokiwadai, Hodogayaku, Yokohama JAPAN","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101693065","display_name":"Takeshi Shibuya","orcid":"https://orcid.org/0000-0003-4645-5898"},"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":"Takeshi Shibuya","raw_affiliation_strings":["Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan","Graduate Sch. of Syst. & Inf. Eng., Univ. of Tsukuba, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Graduate Sch. of Syst. & Inf. Eng., Univ. of Tsukuba, Japan#TAB#","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076930751"],"corresponding_institution_ids":["https://openalex.org/I180203408"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79375091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"49","issue":null,"first_page":"1925","last_page":"1931"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9876000285148621,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9876000285148621,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9739999771118164,"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/T10320","display_name":"Neural Networks and Applications","score":0.9587000012397766,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8915401697158813},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.8376145362854004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.702224850654602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872671604156494},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.524774968624115},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.497590571641922},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.475801557302475},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.44930392503738403},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.41778358817100525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38826414942741394}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8915401697158813},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.8376145362854004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.702224850654602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872671604156494},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.524774968624115},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.497590571641922},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.475801557302475},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.44930392503738403},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.41778358817100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38826414942741394},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2010.5642266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2010.5642266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1570690983","https://openalex.org/W2146398222","https://openalex.org/W2170979741","https://openalex.org/W2912185451","https://openalex.org/W4214717370","https://openalex.org/W6681781451"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1966456942","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W3148138296","https://openalex.org/W4294873804","https://openalex.org/W3127551068","https://openalex.org/W2808546214","https://openalex.org/W2152445738","https://openalex.org/W225045806"],"abstract_inverted_index":{"Hierarchical":[0,41],"complex-valued":[1,45,92,104,130],"reinforcement":[2,46,93,131],"learning":[3,36,47,132],"is":[4,18,26,57,87,140],"proposed":[5,49,149],"in":[6,28,50],"order":[7,51],"to":[8,52,111],"solve":[9,53],"the":[10,95,109,122,145,148],"perceptual":[11,15,125],"aliasing":[12,16],"problem.":[13,55],"The":[14],"problem":[17,34],"encountered":[19],"when":[20],"an":[21,29,39],"incomplete":[22],"set":[23],"of":[24,61,70,85,97,121,124,147],"sensors":[25],"used":[27],"actual":[30],"environment,":[31],"and":[32,44],"this":[33,54,128],"makes":[35],"difficult":[37],"for":[38,89],"agent.":[40],"Q-learning":[42],"(HQ-learning)":[43],"are":[48,66],"HQ-learning":[56,135],"a":[58,82,137],"hierarchical":[59,138],"extension":[60],"Q-learning.":[62],"In":[63,91,127],"HQ-learning,":[64],"tasks":[65],"divided":[67],"into":[68],"sequences":[69],"simpler":[71],"sub-tasks":[72],"that":[73],"can":[74,99],"be":[75,100],"solved":[76],"by":[77,102],"adopting":[78],"memory-less":[79],"policies,":[80],"but":[81,115],"considerable":[83],"amount":[84],"time":[86],"required":[88],"learning.":[90],"learning,":[94],"dependence":[96],"contexts":[98],"represented":[101],"using":[103],"action-value":[105],"functions.":[106],"It":[107],"enables":[108],"agent":[110],"adaptively":[112],"perform":[113],"actions,":[114],"may":[116],"not":[117],"deal":[118],"problems":[119],"because":[120],"cycle":[123],"aliasing.":[126],"paper,":[129],"based":[133],"on":[134],"with":[136],"design":[139],"proposed.":[141],"Experimental":[142],"results":[143],"show":[144],"effectiveness":[146],"method.":[150]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}