{"id":"https://openalex.org/W4391496502","doi":"https://doi.org/10.1109/wcsp58612.2023.10404257","title":"Decomposition-based Multi-Agent Distributional Reinforcement Learning for Task-Oriented UAV Collaboration with Noisy Rewards","display_name":"Decomposition-based Multi-Agent Distributional Reinforcement Learning for Task-Oriented UAV Collaboration with Noisy Rewards","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4391496502","doi":"https://doi.org/10.1109/wcsp58612.2023.10404257"},"language":"en","primary_location":{"id":"doi:10.1109/wcsp58612.2023.10404257","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wcsp58612.2023.10404257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Wireless Communications and Signal Processing (WCSP)","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/A5101530798","display_name":"Wei Geng","orcid":"https://orcid.org/0009-0008-0655-0325"},"institutions":[{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Geng","raw_affiliation_strings":["UCAS,Hangzhou Institute for Advanced Study","Hangzhou Institute for Advanced Study, UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCAS,Hangzhou Institute for Advanced Study","institution_ids":["https://openalex.org/I4210137766"]},{"raw_affiliation_string":"Hangzhou Institute for Advanced Study, UCAS","institution_ids":["https://openalex.org/I4210137766"]}]},{"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":["Zhejiang University,College of Information Science and Electronic Engineering","College of Information Science and Electronic Engineering, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Information Science and Electronic Engineering","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University","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":["Zhejiang University,College of Information Science and Electronic Engineering","College of Information Science and Electronic Engineering, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Information Science and Electronic Engineering","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090212300","display_name":"Ning Wei","orcid":"https://orcid.org/0000-0002-3936-7526"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626780","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0003-1492-1364"},"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":"Honggang Zhang","raw_affiliation_strings":["Zhejiang Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.23542432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"342","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9975000023841858,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9868000149726868,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8440028429031372},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.7555608749389648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7097722887992859},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6709170341491699},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6362504959106445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5317738652229309},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5082854628562927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41067203879356384},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1377127468585968},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07044675946235657}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8440028429031372},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.7555608749389648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7097722887992859},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6709170341491699},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6362504959106445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317738652229309},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5082854628562927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41067203879356384},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1377127468585968},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07044675946235657},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/wcsp58612.2023.10404257","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wcsp58612.2023.10404257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Wireless Communications and Signal Processing (WCSP)","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":24,"referenced_works":["https://openalex.org/W2588790649","https://openalex.org/W2602275733","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2765302304","https://openalex.org/W2963762747","https://openalex.org/W2998116579","https://openalex.org/W3004928757","https://openalex.org/W3099689767","https://openalex.org/W4212774754","https://openalex.org/W4287755265","https://openalex.org/W4289147358","https://openalex.org/W4300672471","https://openalex.org/W6683300800","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6751629939","https://openalex.org/W6757310144","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6784152626","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W2366903352"],"abstract_inverted_index":{"Collaborated":[0],"unmanned":[1],"aerial":[2],"vehicles":[3],"(UAVs)":[4],"are":[5],"often":[6],"deployed":[7],"to":[8,26,45,53,127],"perform":[9],"complex":[10],"tasks":[11],"on":[12],"the":[13,21,35,47,56,76,90,109,112,119,129,135,138],"basis":[14],"of":[15,37,49,59,92,111,121,137],"multi-agent":[16,70],"reinforcement":[17],"learning":[18],"(MARL).":[19],"However,":[20],"environmental":[22],"disturbance,":[23],"commonly":[24],"leading":[25],"noisy":[27,60,79,146],"observations":[28],"(e.g.,":[29],"rewards,":[30,96],"states),":[31],"could":[32],"significantly":[33],"shape":[34],"performance":[36],"task-oriented":[38],"UAV":[39],"collaboration.":[40],"Therefore,":[41],"it":[42,88],"becomes":[43],"imperative":[44],"revolutionize":[46],"design":[48,120],"MARL,":[50],"so":[51],"as":[52],"capably":[54],"ameliorate":[55],"annoying":[57],"impact":[58],"rewards.":[61,147],"In":[62],"this":[63],"paper,":[64],"we":[65],"propose":[66],"a":[67,82],"novel":[68],"decomposition-based":[69],"distributional":[71,94,106,113],"RL":[72],"method":[73,140],"by":[74,81],"approximating":[75],"globally":[77],"shared":[78],"reward":[80],"Gaussian":[83],"mixture":[84],"model":[85],"and":[86],"decomposing":[87],"into":[89],"combination":[91],"individual":[93],"local":[95],"with":[97,145],"which":[98],"each":[99],"agent":[100],"can":[101],"be":[102],"updated":[103],"locally":[104],"through":[105,141],"RL.":[107],"Besides,":[108],"optimality":[110],"decomposition":[114,130],"is":[115,124],"theoretically":[116],"validated,":[117],"while":[118],"loss":[122],"functions":[123],"carefully":[125],"calibrated":[126],"tackle":[128],"ambiguity.":[131],"We":[132],"also":[133],"verify":[134],"effectiveness":[136],"proposed":[139],"extensive":[142],"simulation":[143],"experiments":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}