{"id":"https://openalex.org/W4416961304","doi":"https://doi.org/10.1109/ton.2025.3637043","title":"FOVA: Offline Federated Reinforcement Learning With Mixed-Quality Data","display_name":"FOVA: Offline Federated Reinforcement Learning With Mixed-Quality Data","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416961304","doi":"https://doi.org/10.1109/ton.2025.3637043"},"language":null,"primary_location":{"id":"doi:10.1109/ton.2025.3637043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2025.3637043","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","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/A5083156932","display_name":"Nan Qiao","orcid":"https://orcid.org/0009-0006-3917-267X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nan Qiao","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101752867","display_name":"Sheng Yue","orcid":"https://orcid.org/0009-0001-3416-8181"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Yue","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015419107","display_name":"Ju Ren","orcid":"https://orcid.org/0000-0003-2782-183X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Ren","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083156932"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20423136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"2031","last_page":"2046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4341999888420105,"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":0.4341999888420105,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.11379999667406082,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.052799999713897705,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8737999796867371},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6861000061035156},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6281999945640564},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49239999055862427},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4796999990940094}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8737999796867371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452999949455261},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4787999987602234},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ton.2025.3637043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ton.2025.3637043","pdf_url":null,"source":{"id":"https://openalex.org/S5407042750","display_name":"IEEE Transactions on Networking","issn_l":"2998-4157","issn":["2998-4157"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2107726111","https://openalex.org/W2109169869","https://openalex.org/W2158782408","https://openalex.org/W2952627098","https://openalex.org/W2953901595","https://openalex.org/W2979766322","https://openalex.org/W2991236681","https://openalex.org/W3009175007","https://openalex.org/W3009247246","https://openalex.org/W3016207298","https://openalex.org/W3088084782","https://openalex.org/W3089075644","https://openalex.org/W3127561923","https://openalex.org/W3165469371","https://openalex.org/W3205598877","https://openalex.org/W4205797172","https://openalex.org/W4224220194","https://openalex.org/W4296880271","https://openalex.org/W4319303175","https://openalex.org/W4360584316","https://openalex.org/W4383988738","https://openalex.org/W4387185205","https://openalex.org/W4387880053","https://openalex.org/W4388505123","https://openalex.org/W4390778260","https://openalex.org/W4391473131","https://openalex.org/W4391528168","https://openalex.org/W4391590983","https://openalex.org/W4400876897","https://openalex.org/W4401507995","https://openalex.org/W4401717545","https://openalex.org/W4404237407"],"related_works":[],"abstract_inverted_index":{"Offline":[0],"Federated":[1],"Reinforcement":[2],"Learning":[3],"(FRL),":[4],"a":[5,64,74],"marriage":[6],"of":[7,28,91,119,152],"federated":[8],"learning":[9,97],"and":[10,109,117,128],"offline":[11,31,67],"reinforcement":[12],"learning,":[13],"has":[14],"attracted":[15],"increasing":[16],"interest":[17],"recently.":[18],"Albeit":[19],"with":[20,38,52],"some":[21],"advancement,":[22],"we":[23,105,122],"find":[24],"that":[25,41,131],"the":[26,43,88,115,132,142,148],"performance":[27,150],"most":[29],"existing":[30,157],"FRL":[32,68],"methods":[33],"drops":[34],"dramatically":[35],"when":[36],"provided":[37],"mixed-quality":[39],"data,":[40],"is,":[42],"logging":[44],"behaviors":[45,93],"(offline":[46],"data)":[47],"are":[48],"collected":[49],"by":[50,135],"policies":[51],"varying":[53],"qualities":[54],"across":[55],"clients.":[56],"To":[57],"overcome":[58],"this":[59,61],"limitation,":[60],"paper":[62],"introduces":[63],"new":[65],"vote-based":[66],"framework,":[69],"named":[70],"FOVA.":[71,120],"It":[72],"exploits":[73],"<italic":[75],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[76],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">vote":[77],"mechanism</i>":[78],"to":[79],"identify":[80],"high-return":[81],"actions":[82],"during":[83],"local":[84,96,108],"policy":[85,133,139],"evaluation,":[86],"alleviating":[87],"negative":[89],"effect":[90],"low-quality":[92],"from":[94],"diverse":[95],"policies.":[98],"Besides,":[99],"building":[100],"on":[101,159],"advantage-weighted":[102],"regression":[103],"(AWR),":[104],"construct":[106],"consistent":[107],"global":[110],"training":[111],"objectives,":[112],"significantly":[113],"enhancing":[114],"efficiency":[116],"stability":[118],"Further,":[121],"conduct":[123],"an":[124],"extensive":[125],"theoretical":[126],"analysis":[127],"rigorously":[129],"show":[130],"learned":[134],"FOVA":[136],"enjoys":[137],"strict":[138],"improvement":[140],"over":[141,156],"behavioral":[143],"policy.":[144],"Extensive":[145],"experiments":[146],"corroborate":[147],"significant":[149],"gains":[151],"our":[153],"proposed":[154],"algorithm":[155],"baselines":[158],"widely":[160],"used":[161],"benchmarks.":[162]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-03T00:00:00"}