{"id":"https://openalex.org/W3216963336","doi":"https://doi.org/10.1109/iwcia52852.2021.9626024","title":"Improvement of learning method of multi-agent system by sharing learning data","display_name":"Improvement of learning method of multi-agent system by sharing learning data","publication_year":2021,"publication_date":"2021-11-06","ids":{"openalex":"https://openalex.org/W3216963336","doi":"https://doi.org/10.1109/iwcia52852.2021.9626024","mag":"3216963336"},"language":"en","primary_location":{"id":"doi:10.1109/iwcia52852.2021.9626024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia52852.2021.9626024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 12th International Workshop on Computational Intelligence and Applications (IWCIA)","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/A5100734777","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0003-3067-8333"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Hiroshima University, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037043794","display_name":"Tomohiro Hayashida","orcid":"https://orcid.org/0000-0003-4476-7468"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Hayashida","raw_affiliation_strings":["Hiroshima University, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158867","display_name":"Ichiro Nishizaki","orcid":"https://orcid.org/0000-0002-0060-4360"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Nishizaki","raw_affiliation_strings":["Hiroshima University, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029138417","display_name":"Shinya Sekizaki","orcid":"https://orcid.org/0000-0002-8493-7700"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinya Sekizaki","raw_affiliation_strings":["Hiroshima University, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Hiroshima University, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100734777"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64702347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"325","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9900000095367432,"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":0.9900000095367432,"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":0.9355999827384949,"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":0.9332000017166138,"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/computer-science","display_name":"Computer science","score":0.7834933996200562},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.751057505607605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6544883251190186},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6529914140701294},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.628223180770874},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5384547114372253},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5002644062042236},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.41474419832229614},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1123921275138855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834933996200562},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.751057505607605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6544883251190186},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6529914140701294},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.628223180770874},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5384547114372253},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5002644062042236},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.41474419832229614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1123921275138855},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcia52852.2021.9626024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcia52852.2021.9626024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 12th International Workshop on Computational Intelligence and Applications (IWCIA)","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":10,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2908261578","https://openalex.org/W2950014024","https://openalex.org/W2964043796","https://openalex.org/W2991046523","https://openalex.org/W4214717370","https://openalex.org/W4299802797","https://openalex.org/W6692846177","https://openalex.org/W6738796088","https://openalex.org/W6760279721"],"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/W20361778"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,21,31,49,83],"algorithms":[3],"have":[4],"been":[5],"employed":[6],"to":[7,77,120],"solve":[8],"the":[9,15,20,30,46,53,60,79,82,86,94,100,103,108,122],"problems":[10],"of":[11,28,37,48,69,81,88],"multi-agent":[12],"learning,":[13],"especially":[14],"non-stationarity":[16],"problem":[17],"that":[18,45,93],"reduces":[19],"efficiency.":[22],"In":[23,66],"this":[24,89],"study,":[25],"an":[26,35],"architecture":[27],"improving":[29],"efficiency":[32],"by":[33,102],"using":[34],"adaptation":[36],"Actor-Critic":[38],"method":[39],"is":[40],"proposed.":[41],"It":[42],"was":[43,75],"clear":[44],"convergence":[47],"became":[50],"faster":[51],"when":[52],"agents":[54,62,95,109],"shared":[55],"their":[56,97,114],"experience":[57],"data":[58],"with":[59],"other":[61],"at":[63],"some":[64,72],"rate.":[65],"two":[67],"kinds":[68],"maze":[70],"benchmarks,":[71],"numerical":[73,90],"experiments":[74,91],"conducted":[76],"show":[78],"performance":[80],"architecture.":[84],"And":[85],"result":[87],"showed":[92],"achieved":[96],"purpose":[98],"in":[99],"mazes":[101],"proposed":[104],"method.":[105],"Even":[106],"though":[107],"did":[110],"not":[111],"share":[112],"all":[113],"data,":[115],"they":[116],"could":[117],"be":[118],"trained":[119],"take":[121],"optimal":[123],"policies.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}