{"id":"https://openalex.org/W4401687328","doi":"https://doi.org/10.1109/tmc.2024.3445583","title":"Learning to Optimize State Estimation in Multi-Agent Reinforcement Learning-Based Collaborative Detection","display_name":"Learning to Optimize State Estimation in Multi-Agent Reinforcement Learning-Based Collaborative Detection","publication_year":2024,"publication_date":"2024-08-19","ids":{"openalex":"https://openalex.org/W4401687328","doi":"https://doi.org/10.1109/tmc.2024.3445583"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2024.3445583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3445583","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/A5113021029","display_name":"Tianlong Zhou","orcid":"https://orcid.org/0009-0002-0713-5218"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Zhou","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086231942","display_name":"Tianyi Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Shi","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-3626-6807","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100877031","display_name":"Hongye Gao","orcid":"https://orcid.org/0009-0008-2953-7596"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Gao","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016210851","display_name":"Weixiong Rao","orcid":"https://orcid.org/0000-0001-6644-0349"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiong Rao","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6644-0349","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.5557,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71205838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"23","issue":"12","first_page":"14330","last_page":"14343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.8722000122070312,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.8722000122070312,"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/T12594","display_name":"Collaboration in agile enterprises","score":0.8346999883651733,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8720235824584961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811109185218811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517461359500885},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49819159507751465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4621677100658417},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4383890628814697},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.42497518658638},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4145444631576538},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.11047589778900146},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09050324559211731}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8720235824584961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811109185218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517461359500885},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49819159507751465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4621677100658417},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4383890628814697},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.42497518658638},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4145444631576538},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.11047589778900146},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09050324559211731},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2024.3445583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2024.3445583","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W187063775","https://openalex.org/W1198835323","https://openalex.org/W1489154522","https://openalex.org/W2016448024","https://openalex.org/W2020934227","https://openalex.org/W2072931689","https://openalex.org/W2098846072","https://openalex.org/W2106131716","https://openalex.org/W2143927862","https://openalex.org/W2212012417","https://openalex.org/W2335829695","https://openalex.org/W2503126809","https://openalex.org/W2584265939","https://openalex.org/W2768629321","https://openalex.org/W2777032727","https://openalex.org/W2890955732","https://openalex.org/W2925947534","https://openalex.org/W2954742730","https://openalex.org/W2962769637","https://openalex.org/W2964162338","https://openalex.org/W3011589233","https://openalex.org/W3036931094","https://openalex.org/W3043426275","https://openalex.org/W3046091798","https://openalex.org/W3100191104","https://openalex.org/W3118614357","https://openalex.org/W3142421752","https://openalex.org/W3167705651","https://openalex.org/W3183282730","https://openalex.org/W3203682130","https://openalex.org/W3207450959","https://openalex.org/W4200136078","https://openalex.org/W4255133955","https://openalex.org/W4287728517","https://openalex.org/W4385286177","https://openalex.org/W4386066213","https://openalex.org/W4387544212","https://openalex.org/W6607574120","https://openalex.org/W6629244416","https://openalex.org/W6733472783","https://openalex.org/W6766224423","https://openalex.org/W6779824286","https://openalex.org/W6780252837","https://openalex.org/W6796861069","https://openalex.org/W6803731244"],"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/W4391331176"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,92],"study":[4],"the":[5,43,59,136,160],"collaborative":[6],"detection":[7],"problem":[8],"in":[9],"a":[10,95],"multi-agent":[11,129],"environment.":[12],"By":[13],"exploiting":[14],"onboard":[15],"range-bearing":[16],"sensors,":[17],"mobile":[18],"agents":[19],"make":[20,84],"sequential":[21],"control":[22,86],"decisions":[23],"such":[24,46,90],"as":[25,47,142],"moving":[26],"directions":[27],"to":[28,118,148],"gather":[29],"information":[30],"of":[31],"movable":[32,150],"targets.":[33,151],"To":[34,88],"estimate":[35,74],"target":[36,39,75,122,138],"states,":[37],"i.e.,":[38,72],"location":[40],"and":[41,51,67,82,124,140,144,166],"velocity,":[42],"classic":[44],"works":[45],"Kalman":[48,53],"Filter":[49,54,109],"(KF)":[50],"Extended":[52],"(EKF)":[55],"impractically":[56],"assume":[57],"that":[58,156],"underlying":[60],"state":[61,98],"space":[62],"model":[63,133],"is":[64],"fully":[65],"known,":[66],"some":[68],"recent":[69],"learning-based":[70],"works,":[71],"KalmanNet,":[73],"states":[76,123,139],"alone":[77],"but":[78],"without":[79],"estimation":[80,125],"uncertainty,":[81],"cannot":[83],"robust":[85,146],"decision.":[87],"tackle":[89],"issues,":[91],"first":[93],"propose":[94],"neural":[96],"network-based":[97],"estimator,":[99],"namely":[100],"T<underline":[101],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[102,105,107,112,115],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">W</u>o-phase":[103],"K<underline":[104],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">AL</u>ma<underline":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">n</u>":[108],"with":[110],"<underline":[111],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">U</u>ncertainty":[113],"quan<underline":[114],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</u>ification":[116],"(WALNUT),":[117],"explicitly":[119],"give":[120],"both":[121],"uncertainty.":[126],"The":[127],"developed":[128],"reinforcement":[130],"learning":[131],"(MARL)":[132],"then":[134],"takes":[135],"learned":[137],"uncertainty":[141],"input":[143],"makes":[145],"actions":[147],"track":[149],"Our":[152],"extensive":[153],"experiments":[154],"demonstrate":[155],"our":[157],"work":[158],"outperforms":[159],"state-of-the-art":[161],"by":[162],"higher":[163],"tracking":[164],"ability":[165],"lower":[167],"localization":[168],"error.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}