{"id":"https://openalex.org/W4312858357","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891948","title":"Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning","display_name":"Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312858357","doi":"https://doi.org/10.1109/ijcnn55064.2022.9891948"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9891948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891948","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5041120260","display_name":"Guangkai Yang","orcid":null},"institutions":[{"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"]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangkai Yang","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353673","display_name":"Hao Chen","orcid":"https://orcid.org/0009-0001-6480-7976"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Junge Zhang","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083652259","display_name":"Qiyue Yin","orcid":"https://orcid.org/0000-0002-3442-6275"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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"]},{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Yin","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiqi Huang","raw_affiliation_strings":["CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, P.R.China"],"affiliations":[{"raw_affiliation_string":"CRISE, Institute of Automation, Chinese Academy of Sciences,Beijing,P.R.China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041120260"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44252316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9922000169754028,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9883999824523926,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8218610286712646},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.801067054271698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.741777777671814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724408626556396},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.527755081653595},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46424850821495056},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4509730041027069},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.42820724844932556},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4227392077445984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3922056555747986},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38232746720314026},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3209832012653351},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09488913416862488}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8218610286712646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.801067054271698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741777777671814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724408626556396},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.527755081653595},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46424850821495056},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4509730041027069},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.42820724844932556},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4227392077445984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3922056555747986},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38232746720314026},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3209832012653351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09488913416862488},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9891948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9891948","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G1960823227","display_name":null,"funder_award_id":"QYZDB-SSWJSC006","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G852446924","display_name":null,"funder_award_id":"61876181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1959608418","https://openalex.org/W2039522160","https://openalex.org/W2047229728","https://openalex.org/W2108738385","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2164411961","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2344786740","https://openalex.org/W2623491082","https://openalex.org/W2626637010","https://openalex.org/W2724169821","https://openalex.org/W2747213132","https://openalex.org/W2765302304","https://openalex.org/W2766447205","https://openalex.org/W2803308811","https://openalex.org/W2949963774","https://openalex.org/W2963007936","https://openalex.org/W2963864421","https://openalex.org/W2989847975","https://openalex.org/W3035569762","https://openalex.org/W3045080532","https://openalex.org/W3091650971","https://openalex.org/W3094349299","https://openalex.org/W3110392801","https://openalex.org/W3118210634","https://openalex.org/W3131743514","https://openalex.org/W3172702028","https://openalex.org/W3195351287","https://openalex.org/W3199614200","https://openalex.org/W4214717370","https://openalex.org/W4288091739","https://openalex.org/W4288594419","https://openalex.org/W4293845400","https://openalex.org/W4295598622","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W4312609624","https://openalex.org/W6627932998","https://openalex.org/W6637967152","https://openalex.org/W6640963894","https://openalex.org/W6676077707","https://openalex.org/W6682849425","https://openalex.org/W6683300800","https://openalex.org/W6684488266","https://openalex.org/W6684921986","https://openalex.org/W6688325169","https://openalex.org/W6695011786","https://openalex.org/W6739193204","https://openalex.org/W6739516088","https://openalex.org/W6740092555","https://openalex.org/W6740422405","https://openalex.org/W6746216111","https://openalex.org/W6746717914","https://openalex.org/W6749304979","https://openalex.org/W6751629939","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6779109570","https://openalex.org/W6781702133","https://openalex.org/W6784046417","https://openalex.org/W6784171646","https://openalex.org/W6790451431","https://openalex.org/W6800500506"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W3099153698","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2807018115"],"abstract_inverted_index":{"Cooperative":[0],"multi-agent":[1,28,113,138,190],"reinforcement":[2],"learning":[3,39],"has":[4,57],"been":[5,58],"considered":[6],"promising":[7],"to":[8,42,60,64,149,162,176,208],"complete":[9],"many":[10],"complex":[11,68],"cooperative":[12],"tasks":[13],"in":[14,53,67,111],"the":[15,80,96,103,112,119,124,129,145,152,171,183,187,195,210,215],"real":[16],"world":[17],"such":[18,73],"as":[19,36,74,179,181],"coordination":[20],"of":[21,98,154,185,217],"robot":[22],"swarms":[23],"and":[24,45,50,76,106,115,157,213],"self-driving.":[25],"To":[26,122],"promote":[27],"cooperation,":[29],"Centralized":[30],"Training":[31],"with":[32,85,159],"Decentralized":[33],"Execution":[34],"emerges":[35],"a":[37,134],"popular":[38],"paradigm":[40,72],"due":[41],"partial":[43,104],"observability":[44,105],"communication":[46],"constraints":[47],"during":[48],"execution":[49],"computational":[51],"complexity":[52],"training.":[54],"Value":[55],"decomposition":[56],"known":[59],"produce":[61],"competitive":[62],"performance":[63,207],"other":[65],"methods":[66],"environment":[69,200],"within":[70],"this":[71],"VDN":[75],"QMIX,":[77],"which":[78],"approximates":[79],"global":[81],"joint":[82],"Q-value":[83,89],"function":[84],"multiple":[86,99],"local":[87],"individual":[88],"functions.":[90],"However,":[91],"existing":[92],"works":[93],"often":[94],"neglect":[95],"uncertainty":[97,139,153],"agents":[100,156,175,188],"resulting":[101],"from":[102],"very":[107],"large":[108],"action":[109],"space":[110],"setting":[114],"can":[116],"only":[117],"obtain":[118],"sub-optimal":[120],"policy.":[121],"alleviate":[123],"limitations":[125],"above,":[126],"building":[127],"upon":[128],"value":[130],"decomposition,":[131],"we":[132,169],"propose":[133],"novel":[135],"method":[136,143],"called":[137],"sharing":[140],"(MAUS).":[141],"This":[142],"utilizes":[144],"Bayesian":[146],"neural":[147],"network":[148],"explicitly":[150],"capture":[151],"all":[155,186],"combines":[158],"Thompson":[160],"sampling":[161],"select":[163],"actions":[164],"for":[165,189],"policy":[166],"learning.":[167],"Besides,":[168],"impose":[170],"uncertainty-sharing":[172],"mechanism":[173],"among":[174],"stabilize":[177],"training":[178],"well":[180],"coordinate":[182],"behaviors":[184],"cooperation.":[191],"Extensive":[192],"experiments":[193],"on":[194],"StarCraft":[196],"Multi-Agent":[197],"Challenge":[198],"(SMAC)":[199],"demonstrate":[201],"that":[202],"our":[203,218],"approach":[204],"achieves":[205],"significant":[206],"exceed":[209],"prior":[211],"baselines":[212],"verify":[214],"effectiveness":[216],"method.":[219]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}