{"id":"https://openalex.org/W4407949409","doi":"https://doi.org/10.1109/cdc56724.2024.10886168","title":"Towards Fast Rates for Federated and Multi-Task Reinforcement Learning","display_name":"Towards Fast Rates for Federated and Multi-Task Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949409","doi":"https://doi.org/10.1109/cdc56724.2024.10886168"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5009512783","display_name":"Feng Zhu","orcid":"https://orcid.org/0000-0003-0263-6806"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Feng Zhu","raw_affiliation_strings":["North Carolina State University,Dept. of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Dept. of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029812222","display_name":"Robert W. Heath","orcid":"https://orcid.org/0000-0002-4666-5628"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert W. Heath","raw_affiliation_strings":["University of California,Dept. of Electrical and Computer Engineering,San Diego,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Dept. of Electrical and Computer Engineering,San Diego,USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101651422","display_name":"Aritra Mitra","orcid":"https://orcid.org/0000-0002-0472-284X"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aritra Mitra","raw_affiliation_strings":["North Carolina State University,Dept. of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Dept. of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009512783"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35165362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2658","last_page":"2663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9021000266075134,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9021000266075134,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8336737155914307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8009936213493347},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7033602595329285},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39488691091537476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3623086214065552},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07971009612083435}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8336737155914307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009936213493347},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7033602595329285},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39488691091537476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3623086214065552},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07971009612083435},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4000000059604645,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2209913494","https://openalex.org/W3205598877","https://openalex.org/W4319303175","https://openalex.org/W6683204974","https://openalex.org/W6728757088","https://openalex.org/W6754297394","https://openalex.org/W6773817997","https://openalex.org/W6776824048","https://openalex.org/W6778995641","https://openalex.org/W6780486084","https://openalex.org/W6790190981","https://openalex.org/W6798832068","https://openalex.org/W6800755839","https://openalex.org/W6809872370","https://openalex.org/W6810897048","https://openalex.org/W6840065948","https://openalex.org/W6849842201","https://openalex.org/W6873555774"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"We":[0],"consider":[1],"a":[2,16,43,48,90,97,103,125,146,163,168],"setting":[3],"involving":[4],"N":[5],"agents,":[6],"where":[7],"each":[8,140],"agent":[9],"interacts":[10],"with":[11,96,116,133,150],"an":[12],"environment":[13],"modeled":[14],"as":[15],"Markov":[17],"Decision":[18],"Process":[19],"(MDP).":[20],"The":[21,32,60],"agents\u2019":[22],"MDPs":[23],"differ":[24],"in":[25,139],"their":[26],"reward":[27],"functions,":[28],"capturing":[29],"heterogeneous":[30],"objectives/tasks.":[31],"collective":[33],"goal":[34],"of":[35,54,82,131,157],"the":[36,52,129,142,155],"agents":[37,132],"is":[38,144],"to":[39,46,78,145,162,172],"communicate":[40],"intermittently":[41],"via":[42],"central":[44],"server":[45],"find":[47],"policy":[49,93,136,149],"that":[50,108,123,170],"maximizes":[51],"average":[53],"long-term":[55],"cumulative":[56],"rewards":[57],"across":[58],"environments.":[59],"limited":[61],"existing":[62],"work":[63],"on":[64],"this":[65],"topic":[66],"either":[67],"only":[68],"provide":[69],"asymptotic":[70],"rates,":[71],"or":[72,76],"generate":[73],"biased":[74],"policies,":[75],"fail":[77],"establish":[79,160],"any":[80],"benefits":[81],"collaboration.":[83,175],"In":[84,154],"response,":[85],"we":[86,106,159],"propose":[87],"Fast-FedPG":[88],"-":[89],"novel":[91],"federated":[92],"gradient":[94],"algorithm":[95,110],"carefully":[98],"designed":[99],"bias-correction":[100],"mechanism.":[101],"Under":[102],"gradient-domination":[104],"condition,":[105],"prove":[107],"our":[109],"guarantees":[111],"(i)":[112],"fast":[113],"linear":[114,126],"convergence":[115,143,161],"exact":[117],"gradients,":[118],"and":[119],"(ii)":[120],"sublinear":[121],"rates":[122],"enjoy":[124],"speedup":[127],"w.r.t.":[128],"number":[130],"noisy,":[134],"truncated":[135],"gradients.":[137],"Notably,":[138],"case,":[141],"globally":[147],"optimal":[148],"no":[151],"heterogeneity-induced":[152],"bias.":[153],"absence":[156],"gradient-domination,":[158],"first-order":[164],"stationary":[165],"point":[166],"at":[167],"rate":[169],"continues":[171],"benefit":[173],"from":[174]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}