{"id":"https://openalex.org/W4401753223","doi":"https://doi.org/10.1109/icccn61486.2024.10637582","title":"Decentralized Multi-agent Reinforcement Learning for Large-scale Mobile Wireless Sensor Network Control Using Mean Field Games","display_name":"Decentralized Multi-agent Reinforcement Learning for Large-scale Mobile Wireless Sensor Network Control Using Mean Field Games","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401753223","doi":"https://doi.org/10.1109/icccn61486.2024.10637582"},"language":"en","primary_location":{"id":"doi:10.1109/icccn61486.2024.10637582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn61486.2024.10637582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd International Conference on Computer Communications and Networks (ICCCN)","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/A5088809666","display_name":"Zejian Zhou","orcid":"https://orcid.org/0000-0002-0252-6765"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zejian Zhou","raw_affiliation_strings":["University of Wyoming,Dept. of EECS,Laramie,Wyoming"],"affiliations":[{"raw_affiliation_string":"University of Wyoming,Dept. of EECS,Laramie,Wyoming","institution_ids":["https://openalex.org/I12834331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085031765","display_name":"Lijun Qian","orcid":"https://orcid.org/0000-0003-1577-3359"},"institutions":[{"id":"https://openalex.org/I250520410","display_name":"Prairie View A&M University","ror":"https://ror.org/0449kf092","country_code":"US","type":"education","lineage":["https://openalex.org/I250520410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Qian","raw_affiliation_strings":["Prairie View A&M University,CREDIT Center,Prairie View,Texas"],"affiliations":[{"raw_affiliation_string":"Prairie View A&M University,CREDIT Center,Prairie View,Texas","institution_ids":["https://openalex.org/I250520410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079038912","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0001-7237-7905"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["University of Nevada,Dept. of EBME,Reno Reno,Nevada"],"affiliations":[{"raw_affiliation_string":"University of Nevada,Dept. of EBME,Reno Reno,Nevada","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088809666"],"corresponding_institution_ids":["https://openalex.org/I12834331"],"apc_list":null,"apc_paid":null,"fwci":1.4653,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83224404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.8105999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.8105999827384949,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.777999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8615584969520569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726528525352478},{"id":"https://openalex.org/keywords/wireless-sensor-network","display_name":"Wireless sensor network","score":0.714062511920929},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.54615718126297},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4757775366306305},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4668353796005249},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.46161186695098877},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.438541442155838},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.4368695616722107},{"id":"https://openalex.org/keywords/mobile-agent","display_name":"Mobile agent","score":0.42511945962905884},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3774232566356659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3506969213485718},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15995171666145325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0895201563835144},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07187062501907349}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8615584969520569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726528525352478},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.714062511920929},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.54615718126297},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4757775366306305},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4668353796005249},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.46161186695098877},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.438541442155838},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.4368695616722107},{"id":"https://openalex.org/C84875433","wikidata":"https://www.wikidata.org/wiki/Q3277848","display_name":"Mobile agent","level":2,"score":0.42511945962905884},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3774232566356659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3506969213485718},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15995171666145325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0895201563835144},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07187062501907349},{"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccn61486.2024.10637582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccn61486.2024.10637582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 33rd International Conference on Computer Communications and Networks (ICCCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1505317658","https://openalex.org/W1549607761","https://openalex.org/W1808956822","https://openalex.org/W2026814250","https://openalex.org/W2058006523","https://openalex.org/W2116708147","https://openalex.org/W2152161277","https://openalex.org/W2787973432","https://openalex.org/W2946347233","https://openalex.org/W3014009018","https://openalex.org/W3044915901","https://openalex.org/W3087412462","https://openalex.org/W3130631955","https://openalex.org/W4206486921","https://openalex.org/W4390075132","https://openalex.org/W6801755041"],"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/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2908230797"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,55,67,74,80,105,116,125,151,155,166,174,177],"real-time":[4],"optimal":[5,75,81,107,118,152],"transmission":[6,76,108,121],"power":[7,109,122],"control":[8,77,110,123],"problem":[9,78,83],"is":[10,61,101],"investigated":[11],"for":[12],"large-scale":[13,20,48,160],"mobile":[14,37,49],"wireless":[15,38],"sensor":[16],"networks":[17],"(MWSN).":[18],"Controlling":[19],"MWSN":[21],"has":[22],"two":[23,91],"novel":[24,56,95],"challenges,":[25,54],"i.e.,":[26,154],"1)":[27],"increasing":[28],"navigation":[29,82,119],"complexity":[30],"due":[31],"to":[32,103,147,150,172],"a":[33,94],"large":[34],"number":[35],"of":[36,176],"sensors,":[39],"and":[40,63,79,111,120,129],"2)":[41],"limited":[42],"energy":[43],"prohibits":[44],"peer-to-peer":[45],"communication":[46],"between":[47],"sensors.":[50],"To":[51,114],"overcome":[52],"these":[53],"mean":[57,87,136],"field":[58,88,137],"game":[59,138],"theory":[60],"adopted":[62],"integrated":[64],"along":[65],"with":[66,90,159],"emerging":[68],"decentralized":[69,106,117,142],"reinforcement":[70,98],"learning":[71,99],"technique.":[72],"Specifically,":[73],"are":[84,133],"formulated":[85],"as":[86],"games":[89],"objectives.":[92],"Then,":[93],"Actor-Critic-Mass":[96],"multi-agent":[97],"algorithm":[100],"developed":[102],"learn":[104,115],"motion":[112],"control.":[113],"policies,":[124],"coupled":[126],"Hamiltonian-Jacobian-Bellman":[127],"(HJB)":[128],"Fokker-Planck-Kolmogorov":[130],"(FPK)":[131],"equations":[132],"derived":[134],"in":[135,162],"formulation.":[139],"The":[140],"learned":[141],"policies":[143],"can":[144],"be":[145],"guaranteed":[146],"converge":[148],"close":[149],"value,":[153],"Nash":[156],"Equilibrium,":[157],"even":[158],"MWSNs":[161],"uncertain":[163],"environments.":[164],"Finally,":[165],"numerical":[167],"simulations":[168],"have":[169],"been":[170],"provided":[171],"demonstrate":[173],"effectiveness":[175],"proposed":[178],"design.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}