{"id":"https://openalex.org/W4301204068","doi":"https://doi.org/10.1109/icc45855.2022.9838936","title":"Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning","display_name":"Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W4301204068","doi":"https://doi.org/10.1109/icc45855.2022.9838936"},"language":"en","primary_location":{"id":"doi:10.1109/icc45855.2022.9838936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","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/A5027890741","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0003-4564-470X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014842979","display_name":"Rongpeng Li","orcid":"https://orcid.org/0000-0003-4297-5060"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongpeng Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036831868","display_name":"Zhifeng Zhao","orcid":"https://orcid.org/0000-0002-5479-7890"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Zhao","raw_affiliation_strings":["Zhejiang Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Lab","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100626780","display_name":"Honggang Zhang","orcid":"https://orcid.org/0000-0003-1492-1364"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8872,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85966344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9969000220298767,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8843615055084229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906146049499512},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7727447748184204},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6215747594833374},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.551372766494751},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5121722221374512},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5079231858253479},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.493673175573349},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.4579973816871643},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42880675196647644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3822781443595886},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3759489953517914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29519739747047424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15542316436767578},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09909290075302124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0779583752155304}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8843615055084229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906146049499512},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7727447748184204},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6215747594833374},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.551372766494751},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5121722221374512},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5079231858253479},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.493673175573349},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.4579973816871643},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42880675196647644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3822781443595886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3759489953517914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29519739747047424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15542316436767578},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09909290075302124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0779583752155304},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc45855.2022.9838936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc45855.2022.9838936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2022 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2160643434","https://openalex.org/W2702150584","https://openalex.org/W2736601468","https://openalex.org/W2783596173","https://openalex.org/W2793948820","https://openalex.org/W2795242006","https://openalex.org/W2899076365","https://openalex.org/W2900182564","https://openalex.org/W2951896791","https://openalex.org/W2962863496","https://openalex.org/W2963433607","https://openalex.org/W2990382694","https://openalex.org/W3014568570","https://openalex.org/W3025869479","https://openalex.org/W3028270327","https://openalex.org/W3042714073","https://openalex.org/W3100789280","https://openalex.org/W3212066104","https://openalex.org/W4206054900","https://openalex.org/W4214717370","https://openalex.org/W6638018090","https://openalex.org/W6736572398","https://openalex.org/W6740154879","https://openalex.org/W6741002519","https://openalex.org/W6745458143","https://openalex.org/W6749652452","https://openalex.org/W6754143808","https://openalex.org/W6755921573","https://openalex.org/W6756561314","https://openalex.org/W6770593501","https://openalex.org/W6775176089","https://openalex.org/W6778127559","https://openalex.org/W6780526261"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2928233854"],"abstract_inverted_index":{"The":[0],"paper":[1,84,119],"considers":[2],"independent":[3],"reinforcement":[4],"learning":[5,16],"(IRL)":[6],"for":[7,110,125],"multi-agent":[8],"decision-making":[9],"process":[10],"in":[11,30,52,136],"the":[12,25,39,71,77,99,105,111,126,138],"paradigm":[13],"of":[14,28,32,61,98,113],"federated":[15],"(FL).":[17],"We":[18],"show":[19],"that":[20],"FL":[21,109],"can":[22],"clearly":[23],"improve":[24],"policy":[26,40],"performance":[27,74],"IRL":[29],"terms":[31],"training":[33],"efficiency":[34,135],"and":[35,45,75,80,90,129,134,145],"stability.":[36],"However,":[37],"since":[38],"parameters":[41],"are":[42],"trained":[43],"locally":[44],"aggregated":[46],"iteratively":[47],"through":[48,142],"a":[49,58,66,86,92,114],"central":[50],"server":[51],"FL,":[53],"frequent":[54],"information":[55],"exchange":[56,112],"incurs":[57],"large":[59],"amount":[60],"communication":[62,79],"overheads.":[63],"To":[64],"reach":[65],"good":[67],"balance":[68],"between":[69],"improving":[70,137],"model's":[72,115],"convergence":[73,123],"reducing":[76],"required":[78],"computation":[81],"over-heads,":[82],"this":[83],"proposes":[85],"system":[87,139],"utility":[88,140],"function":[89],"develops":[91],"consensus-based":[93],"optimization":[94],"scheme":[95],"on":[96],"top":[97],"periodic":[100],"averaging":[101],"method,":[102,128],"which":[103],"introduces":[104],"consensus":[106],"algorithm":[107],"into":[108],"local":[116],"gradients.":[117],"This":[118],"also":[120],"provides":[121],"novel":[122],"guarantees":[124],"developed":[127],"demonstrates":[130],"its":[131],"superior":[132],"effectiveness":[133],"value":[141],"theoretical":[143],"analyses":[144],"numerical":[146],"simulation":[147],"results.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}