{"id":"https://openalex.org/W7125948346","doi":"https://doi.org/10.1109/smc58881.2025.11343484","title":"Data sharing procedure for effective learnings in deep reinforcement learning of multiagent systems","display_name":"Data sharing procedure for effective learnings in deep reinforcement learning of multiagent systems","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125948346","doi":"https://doi.org/10.1109/smc58881.2025.11343484"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/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":true,"raw_author_name":"Tomohiro Hayashida","raw_affiliation_strings":["Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124106552","display_name":"Kotaro Asano","orcid":null},"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":"Kotaro Asano","raw_affiliation_strings":["Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","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,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ichiro Nishizaki","orcid":null},"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,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527"],"affiliations":[{"raw_affiliation_string":"Hiroshima University,Graduate School of Advanced Science and Engineering,Hiroshima,Japan,739-8527","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037043794"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85096845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3653","last_page":"3658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9096999764442444,"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":0.9096999764442444,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7569000124931335},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5508000254631042},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.4952000081539154},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.42800000309944153},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3601999878883362},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7569000124931335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5733000040054321},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5508000254631042},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4952000081539154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":8,"referenced_works":["https://openalex.org/W2096145798","https://openalex.org/W2145339207","https://openalex.org/W2969843367","https://openalex.org/W2973229164","https://openalex.org/W3196151837","https://openalex.org/W4320928015","https://openalex.org/W4362519817","https://openalex.org/W7124280187"],"related_works":[],"abstract_inverted_index":{"In":[0,134],"recent":[1],"years,":[2],"reinforcement":[3],"learning":[4,72,87,110,158,200],"has":[5,128],"made":[6],"significant":[7],"progress":[8],"in":[9,20,50,53,70,112,156,160,202],"a":[10,47,145,165],"wide":[11],"range":[12],"of":[13,27,34,62,94],"domains,":[14],"including":[15],"autonomous":[16],"driving,":[17],"behavior":[18],"analysis":[19],"electricity":[21],"markets,":[22],"and":[23,115,152,177],"robotic":[24],"control.":[25],"Many":[26],"these":[28],"studies":[29,98],"have":[30,80,99],"demonstrated":[31],"the":[32,54,60,71,91,140,196],"effectiveness":[33,155],"applying":[35],"Multi-Agent":[36],"Systems":[37],"(MAS),":[38],"where":[39,122],"multiple":[40],"agents":[41,107,143],"act":[42],"cooperatively":[43],"or":[44],"competitively.":[45],"However,":[46],"major":[48],"challenge":[49],"MAS":[51],"lies":[52],"increased":[55],"environmental":[56],"uncertainty":[57],"caused":[58],"by":[59,89],"influence":[61],"other":[63,95],"agents,":[64,192],"which":[65],"can":[66,108],"lead":[67],"to":[68,85,131,181],"instability":[69],"process.":[73],"To":[74],"address":[75],"this":[76,135,179],"issue,":[77],"various":[78],"approaches":[79],"been":[81],"proposed":[82,197],"that":[83,101,168,195],"aim":[84],"improve":[86],"efficiency":[88,111,201],"leveraging":[90],"experience":[92,104,126,171],"data":[93,105,127,151,172,180],"agents.":[96],"Previous":[97],"reported":[100],"sharing":[102,123],"full":[103],"among":[106],"enhance":[109],"both":[113],"cooperative":[114],"competitive":[116],"settings.":[117],"Furthermore,":[118],"there":[119],"are":[120],"cases":[121],"only":[124],"partial":[125],"also":[129],"led":[130],"performance":[132,159],"improvements.":[133],"paper,":[136],"we":[137,163,193],"focus":[138],"on":[139,174],"similarity":[141,176],"between":[142],"as":[144],"key":[146],"criterion":[147],"for":[148],"selecting":[149],"shared":[150],"demonstrate":[153],"its":[154],"improving":[157],"MAS.":[161],"Specifically,":[162],"propose":[164],"novel":[166],"method":[167,198],"selectively":[169],"shares":[170],"based":[173],"agent":[175],"utilizes":[178],"complement":[182],"an":[183],"agent\u2019s":[184],"own":[185],"experiences.":[186],"Through":[187],"simulations":[188],"with":[189],"heterogeneous":[190],"(asymmetric)":[191],"show":[194],"enhances":[199],"multi-agent":[203],"environments.":[204]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-29T00:00:00"}