{"id":"https://openalex.org/W4404132874","doi":"https://doi.org/10.1109/tmc.2024.3492272","title":"Noise Distribution Decomposition Based Multi-Agent Distributional Reinforcement Learning","display_name":"Noise Distribution Decomposition Based Multi-Agent Distributional Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4404132874","doi":"https://doi.org/10.1109/tmc.2024.3492272"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2024.3492272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3492272","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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/A5111985635","display_name":"Wei Geng","orcid":"https://orcid.org/0009-0001-8898-4176"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Geng","raw_affiliation_strings":["Zhejiang Lab, Zhejiang, China","Zhejiang Lab, China"],"raw_orcid":"https://orcid.org/0009-0001-8898-4176","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038569685","display_name":"Baidi Xiao","orcid":"https://orcid.org/0009-0004-5913-1109"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baidi Xiao","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","College of Information Science and Electronic Engineering, Zhejiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","College of Information Science and Electronic Engineering, Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-4297-5060","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Wei","orcid":"https://orcid.org/0009-0000-6045-8994"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Wei","raw_affiliation_strings":["Zhejiang Lab, Zhejiang, China","Zhejiang Lab, China"],"raw_orcid":"https://orcid.org/0009-0000-6045-8994","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391447","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-1257-8905"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Research Institute of China Telecom, Beijing, China","Research Institute of China Telecom, China"],"raw_orcid":"https://orcid.org/0000-0002-1257-8905","affiliations":[{"raw_affiliation_string":"Research Institute of China Telecom, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]},{"raw_affiliation_string":"Research Institute of China Telecom, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang Lab, Zhejiang, China","Zhejiang Lab, China"],"raw_orcid":"https://orcid.org/0000-0002-5479-7890","affiliations":[{"raw_affiliation_string":"Zhejiang Lab, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21770025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"3","first_page":"2301","last_page":"2314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8136000037193298,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8136000037193298,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.7630924582481384},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7325187921524048},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5812591910362244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5576006174087524},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4479573965072632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41461318731307983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10759422183036804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630924582481384},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7325187921524048},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5812591910362244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5576006174087524},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4479573965072632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41461318731307983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10759422183036804},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2024.3492272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3492272","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G5459816226","display_name":"\u57fa\u4e8e\u4e1a\u52a1\u611f\u77e5\u7684\u5185\u751f\u667a\u80fd\u901a\u4fe1\u7f51\u7edc\u7814\u7a76","funder_award_id":"62071425","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1542941925","https://openalex.org/W1978844375","https://openalex.org/W1987864653","https://openalex.org/W1998172110","https://openalex.org/W2041946752","https://openalex.org/W2053984877","https://openalex.org/W2089855386","https://openalex.org/W2091983238","https://openalex.org/W2096904991","https://openalex.org/W2101124704","https://openalex.org/W2171153629","https://openalex.org/W2522489477","https://openalex.org/W2588790649","https://openalex.org/W2602275733","https://openalex.org/W2747213132","https://openalex.org/W2754517384","https://openalex.org/W2765302304","https://openalex.org/W2783268317","https://openalex.org/W2799899844","https://openalex.org/W2903083210","https://openalex.org/W2919115771","https://openalex.org/W2987602118","https://openalex.org/W2997398560","https://openalex.org/W2998116579","https://openalex.org/W3004928757","https://openalex.org/W3049278490","https://openalex.org/W3099689767","https://openalex.org/W3152878473","https://openalex.org/W3153842551","https://openalex.org/W3189632814","https://openalex.org/W3212516020","https://openalex.org/W4248262852","https://openalex.org/W4251616545","https://openalex.org/W4300672471","https://openalex.org/W4386932528","https://openalex.org/W4387126838","https://openalex.org/W4393147227","https://openalex.org/W6637967152","https://openalex.org/W6679045638","https://openalex.org/W6683300800","https://openalex.org/W6683517036","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6751629939","https://openalex.org/W6757310144","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6779823529","https://openalex.org/W6784152626","https://openalex.org/W6791043475","https://openalex.org/W6795288823","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6840380725","https://openalex.org/W6841549819","https://openalex.org/W6846490732","https://openalex.org/W6849861922","https://openalex.org/W6853024844","https://openalex.org/W6854569276"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Generally,":[0],"Reinforcement":[1,51],"Learning":[2,52],"(RL)":[3],"agent":[4,126],"updates":[5],"its":[6],"policy":[7],"by":[8,99,106],"repetitively":[9],"interacting":[10],"with":[11,123,203],"the":[12,16,26,41,46,61,72,81,101,116,148,158,161,177,180,193,196,216],"environment,":[13],"contingent":[14],"on":[15],"received":[17],"rewards":[18,35],"to":[19,31,57,60,70,78,146,186,214],"observed":[20],"states":[21],"and":[22,36,112,171],"undertaken":[23],"actions.":[24],"However,":[25],"environmental":[27],"disturbance,":[28],"commonly":[29],"leading":[30],"noisy":[32,85,104,204],"observations":[33],"(e.g.,":[34],"states),":[37],"could":[38],"significantly":[39],"shape":[40],"performance":[42,48],"of":[43,49,74,84,118,150,160,179,195,218],"agent.":[44],"Furthermore,":[45,157],"learning":[47,155],"Multi-Agent":[50],"(MARL)":[53],"is":[54,139,165,183],"more":[55],"susceptible":[56],"noise":[58],"due":[59],"interference":[62],"among":[63],"intelligent":[64],"agents.":[65],"Therefore,":[66],"it":[67,114],"becomes":[68],"imperative":[69],"revolutionize":[71],"design":[73,178],"MARL,":[75],"so":[76],"as":[77],"capably":[79],"ameliorate":[80],"annoying":[82],"impact":[83],"rewards.":[86,205],"In":[87],"this":[88],"paper,":[89],"we":[90],"propose":[91],"a":[92,107,135],"novel":[93],"decomposition-based":[94],"multi-agent":[95],"distributional":[96,120,132,219],"RL":[97,220],"method":[98,198],"approximating":[100],"globally":[102],"shared":[103],"reward":[105,142,162],"Gaussian":[108],"Mixture":[109],"Model":[110,137],"(GMM)":[111],"decomposing":[113],"into":[115],"combination":[117],"individual":[119],"local":[121],"rewards,":[122],"which":[124],"each":[125],"can":[127],"be":[128],"updated":[129],"locally":[130],"through":[131,199],"RL.":[133],"Moreover,":[134],"Diffusion":[136],"(DM)":[138],"leveraged":[140],"for":[141,154],"generation":[143],"in":[144,212,221],"order":[145,213],"mitigate":[147],"issue":[149],"costly":[151],"interaction":[152],"expenditure":[153],"distributions.":[156],"monotonicity":[159],"distribution":[163],"decomposition":[164,188],"theoretically":[166],"validated":[167],"under":[168],"nonnegative":[169],"weights":[170],"increasing":[172],"distortion":[173],"risk":[174],"function,":[175],"while":[176],"loss":[181],"function":[182],"carefully":[184],"calibrated":[185],"avoid":[187],"ambiguity.":[189],"We":[190],"also":[191],"verify":[192],"effectiveness":[194],"proposed":[197],"extensive":[200],"simulation":[201],"experiments":[202],"Besides,":[206],"different":[207,222],"risk-sensitive":[208],"policies":[209],"are":[210],"evaluated":[211],"demonstrate":[215],"superiority":[217],"MARL":[223],"tasks.":[224]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}