{"id":"https://openalex.org/W4362653493","doi":"https://doi.org/10.1109/tpds.2023.3264480","title":"Federated Ensemble Model-Based Reinforcement Learning in Edge Computing","display_name":"Federated Ensemble Model-Based Reinforcement Learning in Edge Computing","publication_year":2023,"publication_date":"2023-04-05","ids":{"openalex":"https://openalex.org/W4362653493","doi":"https://doi.org/10.1109/tpds.2023.3264480"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3264480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3264480","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10871/132961","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100346209","display_name":"Jin Wang","orcid":"https://orcid.org/0000-0003-2487-2148"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jin Wang","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0003-2487-2148","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002896600","display_name":"Jia Hu","orcid":"https://orcid.org/0000-0001-5406-8420"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jia Hu","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5406-8420","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069437128","display_name":"Jed Mills","orcid":"https://orcid.org/0000-0001-6344-9364"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jed Mills","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6344-9364","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770003","display_name":"Geyong Min","orcid":"https://orcid.org/0000-0003-1395-7314"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1395-7314","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560795","display_name":"Ming Xia","orcid":"https://orcid.org/0009-0005-2472-7735"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Xia","raw_affiliation_strings":["Google, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-2472-7735","affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061938280","display_name":"Nektarios Georgalas","orcid":"https://orcid.org/0000-0001-9746-3236"},"institutions":[{"id":"https://openalex.org/I1332878012","display_name":"BT Group (United Kingdom)","ror":"https://ror.org/00kv9pj15","country_code":"GB","type":"company","lineage":["https://openalex.org/I1332878012"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nektarios Georgalas","raw_affiliation_strings":["Applied Research Department, British Telecom, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9746-3236","affiliations":[{"raw_affiliation_string":"Applied Research Department, British Telecom, London, U.K","institution_ids":["https://openalex.org/I1332878012"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7105,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96646265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"34","issue":"6","first_page":"1848","last_page":"1859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9993000030517578,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9993000030517578,"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":0.9919999837875366,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9775000214576721,"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/computer-science","display_name":"Computer science","score":0.8613593578338623},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8065241575241089},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7004861831665039},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.530892550945282},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5226231217384338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45519742369651794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4294247031211853},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4234806299209595},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.41865700483322144},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4182170033454895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613593578338623},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8065241575241089},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7004861831665039},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.530892550945282},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5226231217384338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45519742369651794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4294247031211853},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4234806299209595},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.41865700483322144},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4182170033454895},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2023.3264480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3264480","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:ore.exeter.ac.uk:10871/132961","is_oa":true,"landing_page_url":"http://hdl.handle.net/10871/132961","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:ore.exeter.ac.uk:10871/132961","is_oa":true,"landing_page_url":"http://hdl.handle.net/10871/132961","pdf_url":null,"source":{"id":"https://openalex.org/S4306401998","display_name":"Open Research Exeter (University of Exeter)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I23923803","host_organization_name":"University of Exeter","host_organization_lineage":["https://openalex.org/I23923803"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4406201246","display_name":null,"funder_award_id":"EP/X019160/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2087617385","https://openalex.org/W2102928860","https://openalex.org/W2129202194","https://openalex.org/W2594560857","https://openalex.org/W2736601468","https://openalex.org/W2892060055","https://openalex.org/W2911450448","https://openalex.org/W2912139568","https://openalex.org/W2919115771","https://openalex.org/W2962872206","https://openalex.org/W2968937098","https://openalex.org/W3007279825","https://openalex.org/W3016207298","https://openalex.org/W3042621011","https://openalex.org/W3043527956","https://openalex.org/W3088084782","https://openalex.org/W3105018016","https://openalex.org/W3113024443","https://openalex.org/W3121342653","https://openalex.org/W3158278980","https://openalex.org/W3159649695","https://openalex.org/W3208539921","https://openalex.org/W4205382450","https://openalex.org/W4206320562","https://openalex.org/W4236362309","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6678367057","https://openalex.org/W6680657880","https://openalex.org/W6704571135","https://openalex.org/W6713841817","https://openalex.org/W6728757088","https://openalex.org/W6741002519","https://openalex.org/W6748519856","https://openalex.org/W6751494529","https://openalex.org/W6751620934","https://openalex.org/W6753183898","https://openalex.org/W6756463683","https://openalex.org/W6760405395","https://openalex.org/W6764053384","https://openalex.org/W6765541894","https://openalex.org/W6768537144","https://openalex.org/W6769397037","https://openalex.org/W6773817997","https://openalex.org/W6773976177","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6780224944","https://openalex.org/W6782317661","https://openalex.org/W6785214881"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650"],"abstract_inverted_index":{"Federated":[0],"learning":[1,8,29,33],"(FL)":[2],"is":[3,137],"a":[4,74],"privacy-preserving":[5],"distributed":[6,16],"machine":[7],"paradigm":[9],"that":[10,78,129,144],"enables":[11],"collaborative":[12],"training":[13],"among":[14],"geographically":[15],"and":[17,64,83,97,109,180],"heterogeneous":[18,177],"devices":[19],"without":[20,120],"gathering":[21],"their":[22],"data.":[23],"Extending":[24],"FL":[25,88,96],"beyond":[26],"the":[27,47,70,90,112,117,123,130,134,159,173,186,191],"supervised":[28],"models,":[30],"federated":[31],"reinforcement":[32],"(FRL)":[34],"was":[35],"proposed":[36,135],"to":[37,60,100,153],"handle":[38],"sequential":[39],"decision-making":[40],"problems":[41],"in":[42,158],"edge":[43,166],"computing":[44,167],"systems.":[45],"However,":[46],"existing":[48],"FRL":[49,76,156],"algorithms":[50,157],"directly":[51],"combine":[52],"model-free":[53,155],"RL":[54,82],"with":[55,122],"FL,":[56],"thus":[57],"often":[58],"leading":[59],"high":[61],"sample":[62,150],"complexity":[63],"lacking":[65],"theoretical":[66,196],"guarantees.":[67],"To":[68],"address":[69],"challenges,":[71],"we":[72,94,126],"propose":[73],"novel":[75],"algorithm":[77,136,146],"effectively":[79],"incorporates":[80],"model-based":[81],"ensemble":[84,103,118],"knowledge":[85,98],"distillation":[86,99],"into":[87],"for":[89,107],"first":[91],"time.":[92],"Specifically,":[93],"utilise":[95],"create":[101],"an":[102],"of":[104,133,176,188],"dynamics":[105],"models":[106],"clients,":[108],"then":[110],"train":[111],"policy":[113],"by":[114],"solely":[115],"using":[116],"model":[119,182],"interacting":[121],"environment.":[124],"Furthermore,":[125],"theoretically":[127],"prove":[128],"monotonic":[131],"improvement":[132],"guaranteed.":[138],"The":[139,169],"extensive":[140],"experimental":[141],"results":[142,170],"demonstrate":[143],"our":[145,195],"obtains":[147],"much":[148],"higher":[149],"efficiency":[151],"compared":[152],"classic":[154],"challenging":[160],"continuous":[161],"control":[162],"benchmark":[163],"environments":[164],"under":[165],"settings.":[168],"also":[171],"highlight":[172],"significant":[174],"impact":[175],"client":[178],"data":[179],"local":[181],"update":[183],"steps":[184],"on":[185],"performance":[187],"FRL,":[189],"validating":[190],"insights":[192],"obtained":[193],"from":[194],"analysis.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}