{"id":"https://openalex.org/W4414359607","doi":"https://doi.org/10.24963/ijcai.2025/808","title":"Finite-Time Analysis of Heterogeneous Federated Temporal Difference Learning","display_name":"Finite-Time Analysis of Heterogeneous Federated Temporal Difference Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359607","doi":"https://doi.org/10.24963/ijcai.2025/808"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/808","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5100620052","display_name":"Ye Zhu","orcid":"https://orcid.org/0000-0001-8609-0171"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Zhu","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042081570","display_name":"Xiaowen Gong","orcid":"https://orcid.org/0000-0001-5124-7941"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaowen Gong","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112195582","display_name":"Shiwen Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiwen Mao","raw_affiliation_strings":["Auburn University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82497590"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7263","last_page":"7271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5568000078201294,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.5568000078201294,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10057","display_name":"Face and Expression Recognition","score":0.5063999891281128,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/temporal-difference-learning","display_name":"Temporal difference learning","score":0.7681000232696533},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6804999709129333},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6729000210762024},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5174999833106995},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.513700008392334},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4925000071525574},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4471000134944916},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.41440001130104065},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4092999994754791}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.7681000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6804999709129333},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5065000057220459},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4092999994754791},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3946000039577484},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.3472999930381775},{"id":"https://openalex.org/C117898588","wikidata":"https://www.wikidata.org/wiki/Q6664310","display_name":"Local convergence","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2667999863624573},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/808","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Federated":[0],"Temporal":[1],"Difference":[2],"(FTD)":[3],"learning":[4,149],"has":[5],"emerged":[6],"as":[7,39,200],"a":[8,72],"promising":[9],"framework":[10],"for":[11,86,107,132,147,165],"collaboratively":[12],"evaluating":[13],"policies":[14],"without":[15],"sharing":[16],"raw":[17],"data.":[18],"Despite":[19],"its":[20],"potential,":[21],"existing":[22],"approaches":[23],"often":[24],"yield":[25],"biased":[26],"convergence":[27,160,180],"results":[28],"due":[29],"to":[30,100,140,191],"the":[31,102,108,113,122,158,162,166,179,185,192,201],"inherent":[32],"challenges":[33],"of":[34,125,144,161,168,203],"federated":[35,50,74],"reinforcement":[36],"learning,":[37,54],"such":[38],"multiple":[40],"local":[41,83,123,145],"updates":[42],"and":[43,171,195],"environment":[44,110,114],"heterogeneity.":[45],"In":[46],"response,":[47],"we":[48,182],"investigate":[49],"temporal":[51,75],"difference":[52,76],"(TD)":[53],"focusing":[55],"on":[56,151,178],"collaborative":[57],"policy":[58],"evaluation":[59],"with":[60],"linear":[61,198],"function":[62,105],"approximation":[63],"among":[64],"agents":[65,139,204],"operating":[66],"in":[67],"heterogeneous":[68,73,119,153],"environments.":[69],"We":[70,156],"devise":[71],"(HFTD)":[77],"algorithm":[78,91,164,187],"which":[79,111],"iteratively":[80],"aggregates":[81],"agents'":[82,118,126],"stochastic":[84],"gradients":[85,124],"TD":[87,148],"learning.":[88],"The":[89],"HFTD":[90,163,186],"involves":[92],"two":[93],"major":[94],"novel":[95],"contributions:":[96],"1)":[97],"it":[98,137],"aims":[99],"find":[101],"optimal":[103,193],"value":[104],"model":[106,194],"mixture":[109],"is":[112],"randomly":[115],"drawn":[116],"from":[117],"environments,":[120],"using":[121],"mean":[127],"squared":[128],"Bellman":[129],"errors":[130],"(MSBEs)":[131],"their":[133,152],"respective":[134],"environments;":[135],"2)":[136],"allows":[138],"perform":[141],"different":[142],"numbers":[143],"iterations":[146],"based":[150],"computational":[154],"capabilities.":[155],"analyze":[157],"finite-time":[159],"scenarios":[167],"IID":[169],"sampling":[170,173],"Markovian":[172],"respectively.":[174],"By":[175],"characterizing":[176],"bounds":[177],"error,":[181],"show":[183],"that":[184],"can":[188],"exactly":[189],"converge":[190],"also":[196],"achieves":[197],"speedups":[199],"number":[202],"increases.":[205]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}