{"id":"https://openalex.org/W2958874452","doi":"https://doi.org/10.1109/iccw.2019.8756984","title":"The Application of Multi-Agent Reinforcement Learning in UAV Networks","display_name":"The Application of Multi-Agent Reinforcement Learning in UAV Networks","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2958874452","doi":"https://doi.org/10.1109/iccw.2019.8756984","mag":"2958874452"},"language":"en","primary_location":{"id":"doi:10.1109/iccw.2019.8756984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccw.2019.8756984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","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/A5054496135","display_name":"Jingjing Cui","orcid":"https://orcid.org/0000-0002-8850-358X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jingjing Cui","raw_affiliation_strings":["Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076863392","display_name":"Yuanwei Liu","orcid":"https://orcid.org/0000-0002-6389-8941"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuanwei Liu","raw_affiliation_strings":["Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002265731","display_name":"Arumugam Nallanathan","orcid":"https://orcid.org/0000-0001-8337-5884"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arumugam Nallanathan","raw_affiliation_strings":["Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054496135"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":7.5374,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96902349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11133","display_name":"UAV Applications and Optimization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9976999759674072,"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/T11489","display_name":"Air Traffic Management and Optimization","score":0.957099974155426,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9076113700866699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678537368774414},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.6813632845878601},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4836653172969818},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.47484996914863586},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4616938829421997},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.45869749784469604},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45258697867393494},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.45245441794395447},{"id":"https://openalex.org/keywords/resource-management","display_name":"Resource management (computing)","score":0.4387873113155365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43606099486351013},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41559889912605286},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1473190188407898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08922034502029419}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9076113700866699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678537368774414},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.6813632845878601},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4836653172969818},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.47484996914863586},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4616938829421997},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.45869749784469604},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45258697867393494},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.45245441794395447},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.4387873113155365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43606099486351013},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41559889912605286},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1473190188407898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08922034502029419},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1109/iccw.2019.8756984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccw.2019.8756984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Communications Workshops (ICC Workshops)","raw_type":"proceedings-article"},{"id":"pmh:oai:hub.hku.hk:10722/349343","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/349343","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference_Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W103885025","https://openalex.org/W1528676759","https://openalex.org/W2062379507","https://openalex.org/W2068115726","https://openalex.org/W2073144514","https://openalex.org/W2092507086","https://openalex.org/W2093124599","https://openalex.org/W2096145798","https://openalex.org/W2121863487","https://openalex.org/W2165131254","https://openalex.org/W2483325812","https://openalex.org/W2783635063","https://openalex.org/W2783729004","https://openalex.org/W2791092156","https://openalex.org/W2892078410","https://openalex.org/W2962691117","https://openalex.org/W2963061782","https://openalex.org/W2963555336","https://openalex.org/W2963615009","https://openalex.org/W4214717370","https://openalex.org/W4252284432","https://openalex.org/W6748160691"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"This":[0],"article":[1],"investigates":[2],"autonomous":[3],"resource":[4,29,45],"allocation":[5,30,46],"of":[6,15,23],"multiple":[7],"UAVs":[8],"enabled":[9],"communication":[10],"networks":[11],"with":[12,119],"the":[13,21,27,54,108,117],"goal":[14],"maximizing":[16],"long-term":[17,28],"rewards.":[18],"To":[19],"model":[20],"uncertainty":[22],"environments,":[24],"we":[25,57,81],"formulate":[26],"problem":[31],"as":[32],"a":[33,40,59,91,97],"stochastic":[34],"game,":[35],"where":[36],"each":[37,44,66],"UAV":[38],"becomes":[39],"learning":[41,62],"agent":[42,67],"and":[43],"solution":[47],"corresponds":[48],"to":[49,73,116],"an":[50,83],"action":[51],"taken":[52],"by":[53],"UAVs.":[55,124],"Furthermore,":[56],"propose":[58,82],"multi-agent":[60],"reinforcement":[61],"(MARL)":[63],"framework":[64],"that":[65,107],"discovers":[68],"its":[69,74],"best":[70],"strategy":[71],"according":[72],"local":[75],"observations":[76],"using":[77],"learning.":[78],"More":[79],"specifically,":[80],"agent-independent":[84],"method,":[85],"for":[86],"which":[87],"all":[88],"agents":[89],"conduct":[90],"decision":[92],"algorithm":[93,111],"independently":[94],"but":[95],"share":[96],"common":[98],"structure":[99],"based":[100],"on":[101],"Q-learning.":[102],"Finally,":[103],"simulation":[104],"results":[105],"reveal":[106],"proposed":[109],"MARL":[110],"provides":[112],"acceptable":[113],"performance":[114],"compared":[115],"case":[118],"complete":[120],"information":[121],"exchanges":[122],"among":[123]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}