{"id":"https://openalex.org/W4407949038","doi":"https://doi.org/10.1109/cdc56724.2024.10885965","title":"Federated TD Learning in Heterogeneous Environments with Average Rewards: A Two-timescale Approach with Polyak-Ruppert Averaging","display_name":"Federated TD Learning in Heterogeneous Environments with Average Rewards: A Two-timescale Approach with Polyak-Ruppert Averaging","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949038","doi":"https://doi.org/10.1109/cdc56724.2024.10885965"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10885965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885965","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/A5111136248","display_name":"Ankur Naskar","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ankur Naskar","raw_affiliation_strings":["Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047138399","display_name":"Gugan Thoppe","orcid":"https://orcid.org/0000-0001-5066-6589"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gugan Thoppe","raw_affiliation_strings":["Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083059964","display_name":"Abbasali Koochakzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abbasali Koochakzadeh","raw_affiliation_strings":["Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Dept. of Computer Science and Automation,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024301984","display_name":"Vijay Gupta","orcid":"https://orcid.org/0000-0001-7060-3956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay Gupta","raw_affiliation_strings":["Purdue University,Dept. of Electrical and Computer Engineering,IN,USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Dept. of Electrical and Computer Engineering,IN,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111136248"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71317845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"387","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.987500011920929,"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/T12676","display_name":"Machine Learning and ELM","score":0.987500011920929,"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/T10320","display_name":"Neural Networks and Applications","score":0.9861000180244446,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9843000173568726,"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":0.6718411445617676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44768524169921875},{"id":"https://openalex.org/keywords/statistical-learning","display_name":"Statistical learning","score":0.4411667585372925},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.41337448358535767},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37838014960289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23764920234680176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718411445617676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44768524169921875},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.4411667585372925},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.41337448358535767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37838014960289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23764920234680176}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10885965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10885965","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2047078272","https://openalex.org/W2075268401","https://openalex.org/W2086161653","https://openalex.org/W2094364653","https://openalex.org/W2822752092","https://openalex.org/W2964123095","https://openalex.org/W2968937098","https://openalex.org/W2980304492","https://openalex.org/W2996964934","https://openalex.org/W3047304572","https://openalex.org/W3205598877","https://openalex.org/W4381735122","https://openalex.org/W4384806855","https://openalex.org/W6677916085","https://openalex.org/W6683204974","https://openalex.org/W6728757088","https://openalex.org/W6750027077","https://openalex.org/W6759226220","https://openalex.org/W6768785780","https://openalex.org/W6773140934","https://openalex.org/W6773268965","https://openalex.org/W6776438516","https://openalex.org/W6797949073","https://openalex.org/W6803871076","https://openalex.org/W6810897048","https://openalex.org/W6846327033","https://openalex.org/W6987391319"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Federated":[0],"Reinforcement":[1],"Learning":[2],"(FRL)":[3],"provides":[4],"a":[5,46,70,83,120,127,148],"promising":[6],"way":[7],"to":[8,36,50,82,90,147],"speedup":[9,48,122],"training":[10],"in":[11,21,64,69],"reinforcement":[12],"learning":[13],"using":[14],"multiple":[15],"edge":[16,32],"devices":[17,33,54],"that":[18,28,44,61,114,152],"can":[19],"operate":[20],"parallel.":[22],"Recently,":[23],"it":[24,79],"has":[25,45,87],"been":[26,88],"shown":[27],"even":[29,125],"when":[30],"these":[31],"have":[34],"access":[35],"different":[37],"dynamic":[38],"models,":[39],"an":[40],"optimal":[41,116],"convergence":[42,117],"rate":[43,118],"linear":[47,121],"proportional":[49],"the":[51,62,65,74,115,133,142],"number":[52],"of":[53,132],"is":[55,123],"achievable.":[56],"However,":[57],"this":[58,100],"result":[59],"requires":[60],"stepsize":[63,129],"algorithm":[66],"be":[67],"chosen":[68],"manner":[71],"dependent":[72],"on":[73],"unknown":[75],"model":[76],"parameters.":[77],"Also,":[78],"applies":[80],"only":[81],"discounted":[84],"setting,":[85],"which":[86],"argued":[89],"fit":[91],"episodic":[92],"tasks":[93],"better":[94],"than":[95],"continuing":[96],"control":[97],"tasks.":[98],"In":[99],"paper,":[101],"we":[102,140],"obtain":[103],"finite-time":[104],"bounds":[105],"for":[106],"heterogeneous":[107],"FRL":[108,145],"with":[109,119,126],"average":[110],"rewards.":[111],"We":[112],"show":[113],"possible":[124],"universal":[128],"choice,":[130],"independent":[131],"underlying":[134],"dynamics.":[135],"To":[136],"achieve":[137],"our":[138],"result,":[139],"modify":[141],"existing":[143],"one-timescale":[144],"method":[146],"novel":[149],"two-timescale":[150],"variant":[151],"additionally":[153],"incorporates":[154],"iterate":[155],"averaging.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}