{"id":"https://openalex.org/W4297098388","doi":"https://doi.org/10.1109/jcc56315.2022.00013","title":"Improving scalability of multi-agent reinforcement learning with parameters sharing","display_name":"Improving scalability of multi-agent reinforcement learning with parameters sharing","publication_year":2022,"publication_date":"2022-08-01","ids":{"openalex":"https://openalex.org/W4297098388","doi":"https://doi.org/10.1109/jcc56315.2022.00013"},"language":"en","primary_location":{"id":"doi:10.1109/jcc56315.2022.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc56315.2022.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101660068","display_name":"Ning Yang","orcid":"https://orcid.org/0000-0001-7021-3894"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Yang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science,Changsha","College of Computer Science, National University of Defense Technology, Changsha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science,Changsha","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science,Changsha","College of Computer Science, National University of Defense Technology, Changsha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science,Changsha","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989290","display_name":"Peichang Shi","orcid":"https://orcid.org/0000-0002-0973-7899"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"PeiChang Shi","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science,Changsha","College of Computer Science, National University of Defense Technology, Changsha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science,Changsha","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science,Changsha","College of Computer Science, National University of Defense Technology, Changsha"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science,Changsha","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science, National University of Defense Technology, Changsha","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9857000112533569,"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":0.9696000218391418,"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":0.8344964981079102},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8302246332168579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8236421346664429},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5651206374168396},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.543463408946991},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.459159255027771},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4391271471977234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3479083180427551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33161187171936035},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1195363700389862},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06156852841377258}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8344964981079102},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8302246332168579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236421346664429},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5651206374168396},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.543463408946991},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.459159255027771},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4391271471977234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3479083180427551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33161187171936035},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1195363700389862},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06156852841377258},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jcc56315.2022.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jcc56315.2022.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Joint Cloud Computing (JCC)","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":28,"referenced_works":["https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2735995851","https://openalex.org/W2768629321","https://openalex.org/W2963934958","https://openalex.org/W2994073215","https://openalex.org/W2995481444","https://openalex.org/W3084269620","https://openalex.org/W3118993660","https://openalex.org/W3170118067","https://openalex.org/W3170381145","https://openalex.org/W3174153107","https://openalex.org/W3200104413","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6738796088","https://openalex.org/W6740879895","https://openalex.org/W6749304979","https://openalex.org/W6758846586","https://openalex.org/W6771750343","https://openalex.org/W6783140480","https://openalex.org/W6784778700","https://openalex.org/W6787618087","https://openalex.org/W6791079441","https://openalex.org/W6796880758"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2389214306","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090"],"abstract_inverted_index":{"Improving":[0],"the":[1,10,31,37,53,61,98,120,124,127],"scalability":[2,125],"of":[3,9,33,39,63,88,93,126],"a":[4,25,71,78,106],"multi-agent":[5,128],"system":[6],"is":[7,24,95],"one":[8,87],"key":[11],"challenges":[12],"for":[13,81],"applying":[14],"reinforcement":[15],"learning":[16,34],"to":[17,29,45],"learn":[18],"an":[19],"effective":[20],"policy.":[21],"Parameter":[22],"sharing":[23,49,74,101],"common":[26],"approach":[27],"used":[28],"improve":[30,119],"efficiency":[32],"by":[35,97],"reducing":[36],"volume":[38],"policy":[40,72,79],"network":[41,80],"parameters":[42,50,102],"that":[43,114],"need":[44],"be":[46],"updated.":[47],"However,":[48],"also":[51,123],"reduces":[52],"variance":[54],"between":[55],"agents\u2019":[56],"policies,":[57],"which":[58],"further":[59],"restricts":[60],"diversity":[62],"their":[64],"behaviors.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69],"introduce":[70],"parameter":[73],"approach,":[75],"it":[76],"maintains":[77],"each":[82],"agent,":[83],"and":[84,122],"only":[85],"updates":[86],"them.":[89],"The":[90],"differentiated":[91],"behavior":[92],"agents":[94],"maintained":[96],"policy,":[99],"while":[100],"are":[103],"updated":[104],"through":[105],"soft":[107],"way.":[108],"Experiments":[109],"in":[110],"foraging":[111],"scenarios":[112],"demonstrate":[113],"our":[115],"method":[116],"can":[117],"effectively":[118],"performance":[121],"systems.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
