{"id":"https://openalex.org/W4392904017","doi":"https://doi.org/10.1109/icassp48485.2024.10447262","title":"Adaptive Parameter Sharing for Multi-Agent Reinforcement Learning","display_name":"Adaptive Parameter Sharing for Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904017","doi":"https://doi.org/10.1109/icassp48485.2024.10447262"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100680172","display_name":"Dapeng Li","orcid":"https://orcid.org/0000-0002-1584-8528"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Li","raw_affiliation_strings":["University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093511533","display_name":"Na Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Lou","raw_affiliation_strings":["University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392786","display_name":"Bin Zhang","orcid":"https://orcid.org/0000-0001-8080-0478"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628168","display_name":"Zhiwei Xu","orcid":"https://orcid.org/0000-0002-0754-5295"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101572310","display_name":"Guoliang Fan","orcid":"https://orcid.org/0000-0003-2724-2432"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Fan","raw_affiliation_strings":["University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5273,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84467288,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6035","last_page":"6039"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7539506554603577},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7492047548294067},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7414453625679016},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5127955079078674},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5064910650253296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858641028404236},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4418879747390747},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42924314737319946},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.42711713910102844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7539506554603577},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7492047548294067},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7414453625679016},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5127955079078674},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5064910650253296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858641028404236},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4418879747390747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42924314737319946},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.42711713910102844},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2095705004","https://openalex.org/W2153469952","https://openalex.org/W2159723961","https://openalex.org/W2763208138","https://openalex.org/W2768629321","https://openalex.org/W2915117209","https://openalex.org/W2963762747","https://openalex.org/W2964067469","https://openalex.org/W2982316857","https://openalex.org/W4223937247","https://openalex.org/W4224312303","https://openalex.org/W4287774906","https://openalex.org/W4294217238","https://openalex.org/W4299802797","https://openalex.org/W4323066571","https://openalex.org/W4353114823","https://openalex.org/W4367627621","https://openalex.org/W4385488920","https://openalex.org/W4385767524","https://openalex.org/W4385965844","https://openalex.org/W4390872682","https://openalex.org/W6674330103","https://openalex.org/W6692846177","https://openalex.org/W6738796088","https://openalex.org/W6756303580","https://openalex.org/W6766805167","https://openalex.org/W6785173017","https://openalex.org/W6791079441","https://openalex.org/W6810617039","https://openalex.org/W6850900824"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1824242903","https://openalex.org/W1493858311","https://openalex.org/W2155470929","https://openalex.org/W2111125783","https://openalex.org/W2394465510"],"abstract_inverted_index":{"Parameter":[0],"sharing,":[1],"as":[2],"an":[3],"important":[4],"technique":[5],"in":[6,15,58,85,108],"multi-agent":[7],"systems,":[8],"can":[9,91],"effectively":[10],"solve":[11],"the":[12,20,28,56,93],"scalability":[13],"issue":[14],"large-scale":[16],"agent":[17,72],"problems.":[18],"However,":[19],"effectiveness":[21],"of":[22,71,95],"parameter":[23,39,64,119],"sharing":[24,40,65,120],"largely":[25],"depends":[26],"on":[27,81],"environment":[29],"setting.":[30],"When":[31],"agents":[32,99],"have":[33],"different":[34,74,98],"identities":[35],"or":[36],"tasks,":[37],"naive":[38],"makes":[41],"it":[42],"difficult":[43],"to":[44,55,73],"generate":[45],"sufficiently":[46],"differentiated":[47],"strategies":[48,96],"for":[49],"agents.":[50],"Inspired":[51],"by":[52],"research":[53],"pertaining":[54],"brain":[57],"biology,":[59],"we":[60],"propose":[61],"a":[62,77],"novel":[63],"method.":[66],"It":[67],"maps":[68],"each":[69],"type":[70],"regions":[75],"within":[76],"shared":[78],"network":[79],"based":[80],"their":[82],"identity,":[83],"resulting":[84],"distinct":[86],"subnetworks.":[87],"Therefore,":[88],"our":[89,111],"method":[90,112],"increase":[92],"diversity":[94],"among":[97],"without":[100],"introducing":[101],"additional":[102],"training":[103],"parameters.":[104],"Through":[105],"experiments":[106],"conducted":[107],"multiple":[109],"environments,":[110],"has":[113],"shown":[114],"better":[115],"performance":[116],"than":[117],"other":[118],"methods.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
