{"id":"https://openalex.org/W4206941702","doi":"https://doi.org/10.1109/ssci50451.2021.9659877","title":"Swarm Reinforcement Learning Method Based on Hierarchical Q-Learning","display_name":"Swarm Reinforcement Learning Method Based on Hierarchical Q-Learning","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4206941702","doi":"https://doi.org/10.1109/ssci50451.2021.9659877"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9659877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659877","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5001161243","display_name":"Yasuaki Kuroe","orcid":"https://orcid.org/0000-0001-5126-0660"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yasuaki Kuroe","raw_affiliation_strings":["Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","institution_ids":["https://openalex.org/I56624758"]},{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003115794","display_name":"Kenya Takeuchi","orcid":null},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenya Takeuchi","raw_affiliation_strings":["Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","institution_ids":["https://openalex.org/I56624758"]},{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077497999","display_name":"Yutaka Maeda","orcid":"https://orcid.org/0000-0003-0502-5621"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yutaka Maeda","raw_affiliation_strings":["Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Kansai University,Faculty of Engineering Science,Suita-shi,Osaka,Japan","institution_ids":["https://openalex.org/I56624758"]},{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001161243"],"corresponding_institution_ids":["https://openalex.org/I56624758"],"apc_list":null,"apc_paid":null,"fwci":0.1229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39964737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"101","issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9675999879837036,"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":0.9553999900817871,"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":0.9085103273391724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695717215538025},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7127647399902344},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.6280534267425537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5833368897438049},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5440726280212402},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.470090389251709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44593408703804016},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41334834694862366},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3973134458065033},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.34076255559921265},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.17467549443244934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12307113409042358}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9085103273391724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695717215538025},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7127647399902344},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.6280534267425537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5833368897438049},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5440726280212402},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.470090389251709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44593408703804016},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41334834694862366},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3973134458065033},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.34076255559921265},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.17467549443244934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12307113409042358},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9659877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659877","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5390497008","display_name":null,"funder_award_id":"18K11483","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1542094515","https://openalex.org/W1554486125","https://openalex.org/W1568318154","https://openalex.org/W2009785399","https://openalex.org/W2039496311","https://openalex.org/W2055921164","https://openalex.org/W2083533909","https://openalex.org/W2101786389","https://openalex.org/W2107726111","https://openalex.org/W2114317160","https://openalex.org/W2171084228","https://openalex.org/W2397962349","https://openalex.org/W2912185451","https://openalex.org/W2914656440","https://openalex.org/W6633984492","https://openalex.org/W6684973485"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370"],"abstract_inverted_index":{"In":[0,108],"last":[1],"decades":[2],"the":[3,60,70,99,104,113,118,171,184],"reinforcement":[4,62,77,140,152],"learning":[5,63,78,141,153],"method":[6,22,79,142,154,173],"has":[7,80,87],"attracted":[8],"a":[9,25,138,150,160],"great":[10],"deal":[11,145],"of":[12,106,132,163,183],"attention":[13],"and":[14,28,47,84,120,177],"many":[15,51,109],"studies":[16],"have":[17,58],"been":[18,81,88],"done.":[19],"However,":[20],"this":[21,133],"is":[23,66,135,159,166],"basically":[24],"trial-and-error":[26],"scheme":[27],"it":[29],"takes":[30],"much":[31],"computational":[32],"time":[33],"to":[34,136],"acquire":[35],"optimal":[36,39],"strategies.":[37],"Furthermore,":[38],"strategies":[40],"may":[41],"not":[42],"be":[43],"obtained":[44],"for":[45,90,94],"large":[46],"complicated":[48],"problems":[49,56],"with":[50,146],"states.":[52],"To":[53],"resolve":[54],"these":[55],"we":[57],"proposed":[59,172],"swarm":[61,139,151],"method,":[64],"which":[65,143,158],"developed":[67],"inspired":[68],"by":[69],"multi-point":[71],"search":[72],"optimization":[73],"methods.":[74],"The":[75,130],"Swarm":[76],"extensively":[82],"studied":[83],"its":[85],"effectiveness":[86],"confirmed":[89],"several":[91],"problems,":[92,111],"especially":[93],"Markov":[95,126],"decision":[96,127],"processes":[97,128],"where":[98],"agents":[100,114],"can":[101,144,174],"fully":[102,116],"observe":[103,117],"states":[105],"environments.":[107],"real-world":[110],"however,":[112],"cannot":[115],"environments":[119],"they":[121],"are":[122],"usually":[123],"partially":[124],"observable":[125],"(POMDPs).":[129],"purpose":[131],"paper":[134],"develop":[137],"POMDPs.":[147],"We":[148],"propose":[149],"based":[155],"on":[156],"HQ-learning,":[157],"hierarchical":[161],"extension":[162],"Q-learning.":[164],"It":[165],"shown":[167],"through":[168],"experiments":[169],"that":[170,182],"handle":[175],"POMDPs":[176],"possesses":[178],"higher":[179],"performance":[180],"than":[181],"original":[185],"HQ-learning.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}