{"id":"https://openalex.org/W4386352787","doi":"https://doi.org/10.1109/apwcs60142.2023.10233966","title":"Quantum Reinforcement Learning for Large-Scale Multi-Agent Decision-Making in Autonomous Aerial Networks","display_name":"Quantum Reinforcement Learning for Large-Scale Multi-Agent Decision-Making in Autonomous Aerial Networks","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4386352787","doi":"https://doi.org/10.1109/apwcs60142.2023.10233966"},"language":"en","primary_location":{"id":"doi:10.1109/apwcs60142.2023.10233966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apwcs60142.2023.10233966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)","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/A5100724796","display_name":"Soohyun Park","orcid":"https://orcid.org/0000-0002-6556-9746"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soohyun Park","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015771","display_name":"Joongheon Kim","orcid":"https://orcid.org/0000-0002-1794-6076"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9782000184059143,"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":0.9782000184059143,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9735999703407288,"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"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.953499972820282,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8463751077651978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670793533325195},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6160647869110107},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5344224572181702},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5039703249931335},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4994521141052246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4716797471046448},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.42639344930648804},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.42089152336120605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1069604754447937}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8463751077651978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670793533325195},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6160647869110107},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5344224572181702},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5039703249931335},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4994521141052246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4716797471046448},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.42639344930648804},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.42089152336120605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1069604754447937},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/apwcs60142.2023.10233966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apwcs60142.2023.10233966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 VTS Asia Pacific Wireless Communications Symposium (APWCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2982169647","https://openalex.org/W3045093737","https://openalex.org/W3093944484","https://openalex.org/W4205161126","https://openalex.org/W4226266263","https://openalex.org/W4307929343","https://openalex.org/W4312694312","https://openalex.org/W4379382644","https://openalex.org/W6803246989","https://openalex.org/W6846271532"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"a":[3,48],"new":[4],"quantum":[5,17],"computing-based":[6],"multi-agent":[7],"reinforcement":[8],"learning":[9],"(QMARL)":[10],"algorithm":[11,33,61,95],"which":[12],"is":[13,34,55,62],"inspired":[14],"by":[15],"the":[16,30,36,45,70,92],"neural":[18],"network":[19],"(QNN)-based":[20],"centralized":[21],"critic":[22],"and":[23],"multiple":[24],"actor":[25],"networks.":[26,84],"The":[27],"benefit":[28],"of":[29,73],"proposed":[31,59,93],"QMARL-based":[32,60,74,94],"in":[35,78],"action":[37],"control":[38],"dimension":[39],"reduction":[40],"where":[41],"it":[42],"can":[43,96],"reduce":[44],"size":[46],"into":[47],"logarithmic-scale":[49],"when":[50,99],"project":[51],"value":[52],"measure":[53],"(PVM)":[54],"utilized.":[56,104],"Therefore,":[57],"our":[58,86],"beneficial":[63],"for":[64],"massive-agent":[65],"MARL":[66],"training":[67],"convergence.":[68],"Moreover,":[69],"various":[71],"applications":[72],"algorithms":[75],"are":[76],"presented":[77],"massive-scale":[79],"unmanned":[80],"aerial":[81],"vehicle":[82],"(UAV)":[83],"Lastly,":[85],"performance":[87],"evaluation":[88],"results":[89],"verify":[90],"that":[91],"successfully":[97],"converge":[98],"massive-action":[100],"dimensions":[101],"should":[102],"be":[103]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}