{"id":"https://openalex.org/W4206925719","doi":"https://doi.org/10.1109/ssci50451.2021.9659982","title":"Efficient exploration by switching agents according to degree of convergence of learning on Heterogeneous Multi-Agent Reinforcement Learning in Single Robot","display_name":"Efficient exploration by switching agents according to degree of convergence of learning on Heterogeneous Multi-Agent Reinforcement Learning in Single Robot","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4206925719","doi":"https://doi.org/10.1109/ssci50451.2021.9659982"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9659982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659982","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/A5050984626","display_name":"Riku Narita","orcid":null},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Riku Narita","raw_affiliation_strings":["Division of Information and Electronic Engineering, Muroran Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Division of Information and Electronic Engineering, Muroran Institute of Technology, Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013748345","display_name":"Tatsufumi Matsushima","orcid":null},"institutions":[{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsufumi Matsushima","raw_affiliation_strings":["Panasonic ITS Co. Ltd. Development center 1 Section 1, Japan"],"affiliations":[{"raw_affiliation_string":"Panasonic ITS Co. Ltd. Development center 1 Section 1, Japan","institution_ids":["https://openalex.org/I1283155146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067555059","display_name":"Kentarou Kurashige","orcid":"https://orcid.org/0000-0001-9364-1269"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentarou Kurashige","raw_affiliation_strings":["Muroran Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology, Japan","institution_ids":["https://openalex.org/I41725924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050984626"],"corresponding_institution_ids":["https://openalex.org/I41725924"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53047299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9835","issue":null,"first_page":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9914000034332275,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9491999745368958,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.910122275352478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7727651596069336},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6000679731369019},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5670068264007568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577801465988159},{"id":"https://openalex.org/keywords/exploratory-research","display_name":"Exploratory research","score":0.5550143718719482},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5270992517471313},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5217538475990295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5073105692863464},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4952057898044586},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42689546942710876},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1922730803489685},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09404292702674866}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.910122275352478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727651596069336},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6000679731369019},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5670068264007568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577801465988159},{"id":"https://openalex.org/C85973986","wikidata":"https://www.wikidata.org/wiki/Q1091731","display_name":"Exploratory research","level":2,"score":0.5550143718719482},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5270992517471313},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5217538475990295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5073105692863464},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4952057898044586},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42689546942710876},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1922730803489685},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09404292702674866},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9659982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9659982","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1789155456","https://openalex.org/W2036619160","https://openalex.org/W2094201647","https://openalex.org/W2107544712","https://openalex.org/W2107726111","https://openalex.org/W2117514361","https://openalex.org/W2620645529","https://openalex.org/W2799899844","https://openalex.org/W2883550421","https://openalex.org/W2885779696","https://openalex.org/W4248367297","https://openalex.org/W6753305141"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W2930863966","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2126211886","https://openalex.org/W2367922714","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2117511420"],"abstract_inverted_index":{"In":[0,99],"recent":[1],"years,":[2],"a":[3,45,58,87,121,146],"robot":[4],"is":[5,86],"required":[6],"to":[7,23,49,123,162],"perform":[8],"autonomously":[9,21,106],"in":[10,31,68,138],"complex":[11],"environment.":[12,24],"Some":[13],"researchers":[14],"use":[15],"reinforcement":[16,33],"learning":[17,26,34,82,95,117,134,156],"that":[18,60,89,105],"learns":[19],"actions":[20,40,75,92,150],"according":[22],"Reinforcement":[25,64],"requires":[27],"exploratory":[28,39,54,74,91,149],"actions,":[29,55],"but":[30],"conventional":[32],"it":[35],"was":[36,158,173],"random.":[37],"Random":[38],"are":[41],"inefficient":[42,53],"and":[43,167],"takes":[44],"lot":[46],"of":[47,96,130,132,135,170,180],"time":[48],"learn.":[50],"To":[51],"prevent":[52],"we":[56],"proposed":[57,165,182],"method":[59,122,166,169,183],"uses":[61],"Heterogeneous":[62],"Multi-Agent":[63],"Learning":[65],"system":[66,85,88],"(HMARL)":[67],"previous":[69,171],"research.":[70],"HMARL":[71,84,101,139],"enables":[72],"efficient":[73,148],"by":[76,151],"using":[77,93,127],"multiple":[78,97,152],"agents":[79,114,137,153],"with":[80,154],"heterogeneous":[81,116],"spaces.":[83],"performs":[90],"the":[94,113,128,133,136,142,164,168,178,181],"agents.":[98],"addition,":[100],"needs":[102],"an":[103,108,125],"index":[104],"selects":[107],"agent":[109,126],"from":[110],"among":[111],"all":[112],"inside":[115],"space.":[118],"We":[119],"propose":[120],"select":[124],"degree":[129],"convergence":[131],"based":[140],"on":[141],"TD":[143],"errors.":[144],"As":[145],"result,":[147],"different":[155],"spaces":[157],"achieved.":[159],"Then,":[160],"experiment":[161],"compare":[163],"research":[172],"conducted.":[174],"From":[175],"experimental":[176],"results,":[177],"usefulness":[179],"has":[184],"been":[185],"demonstrated.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}