{"id":"https://openalex.org/W3163894240","doi":"https://doi.org/10.1109/tcns.2021.3078100","title":"Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning","display_name":"Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-06","ids":{"openalex":"https://openalex.org/W3163894240","doi":"https://doi.org/10.1109/tcns.2021.3078100","mag":"3163894240"},"language":"en","primary_location":{"id":"doi:10.1109/tcns.2021.3078100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2021.3078100","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-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/A5100783476","display_name":"Tianyi Chen","orcid":"https://orcid.org/0000-0003-3477-1439"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Chen","raw_affiliation_strings":["Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3477-1439","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410441","display_name":"Kaiqing Zhang","orcid":"https://orcid.org/0000-0002-7446-7581"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqing Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-7446-7581","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026758314","display_name":"Georgios B. Giannakis","orcid":"https://orcid.org/0000-0002-0196-0260"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgios B. Giannakis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Digital Technology Center, University of Minnesota, Minneapolis, MN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0196-0260","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Digital Technology Center, University of Minnesota, Minneapolis, MN, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604570","display_name":"Tamer Ba\u015far","orcid":"https://orcid.org/0000-0003-4406-7875"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamer Basar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-4406-7875","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.297,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97010953,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"9","issue":"2","first_page":"917","last_page":"929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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/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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7839875221252441},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7443247437477112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6969945430755615},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6221968531608582},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5451991558074951},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5441473722457886},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45749199390411377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45103323459625244},{"id":"https://openalex.org/keywords/distributed-algorithm","display_name":"Distributed algorithm","score":0.4414592385292053},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09507232904434204}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7839875221252441},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7443247437477112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6969945430755615},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6221968531608582},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5451991558074951},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5441473722457886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45749199390411377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45103323459625244},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.4414592385292053},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09507232904434204},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/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/tcns.2021.3078100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcns.2021.3078100","pdf_url":null,"source":{"id":"https://openalex.org/S2502544478","display_name":"IEEE Transactions on Control of Network Systems","issn_l":"2325-5870","issn":["2325-5870","2372-2533"],"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 Control of Network Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1637379582","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G3253248596","display_name":null,"funder_award_id":"1 509 040","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5415358960","display_name":null,"funder_award_id":"1 711 471","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G7690748309","display_name":null,"funder_award_id":"1 508 993","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W27434444","https://openalex.org/W32403112","https://openalex.org/W1013628759","https://openalex.org/W1488636191","https://openalex.org/W1560074431","https://openalex.org/W1658008008","https://openalex.org/W1697545848","https://openalex.org/W1771410628","https://openalex.org/W1918371733","https://openalex.org/W1991888757","https://openalex.org/W2060393849","https://openalex.org/W2088956500","https://openalex.org/W2104602264","https://openalex.org/W2130801532","https://openalex.org/W2138243089","https://openalex.org/W2144446635","https://openalex.org/W2147492008","https://openalex.org/W2152083440","https://openalex.org/W2155027007","https://openalex.org/W2156666755","https://openalex.org/W2156737235","https://openalex.org/W2165732930","https://openalex.org/W2167183308","https://openalex.org/W2179284380","https://openalex.org/W2530849036","https://openalex.org/W2736601468","https://openalex.org/W2739805727","https://openalex.org/W2753569380","https://openalex.org/W2768629321","https://openalex.org/W2769644379","https://openalex.org/W2777638777","https://openalex.org/W2783291400","https://openalex.org/W2788115019","https://openalex.org/W2904435756","https://openalex.org/W2951896791","https://openalex.org/W2963179579","https://openalex.org/W2963773265","https://openalex.org/W2963864421","https://openalex.org/W2964005211","https://openalex.org/W2964043796","https://openalex.org/W2964231067","https://openalex.org/W2964339512","https://openalex.org/W3004732066","https://openalex.org/W3092621452","https://openalex.org/W3105630790","https://openalex.org/W3109546547","https://openalex.org/W4206686222","https://openalex.org/W4214717370","https://openalex.org/W4241811150","https://openalex.org/W4289760659","https://openalex.org/W4292084264","https://openalex.org/W4299802797","https://openalex.org/W4301311528","https://openalex.org/W4301501993","https://openalex.org/W4302570325","https://openalex.org/W4318619660","https://openalex.org/W6628981685","https://openalex.org/W6633472260","https://openalex.org/W6636881020","https://openalex.org/W6637454738","https://openalex.org/W6638018090","https://openalex.org/W6665801690","https://openalex.org/W6675811377","https://openalex.org/W6679257226","https://openalex.org/W6680402377","https://openalex.org/W6682459407","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685388067","https://openalex.org/W6692846177","https://openalex.org/W6728757088","https://openalex.org/W6729806161","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743613440","https://openalex.org/W6746015766","https://openalex.org/W6746200960","https://openalex.org/W6747133071","https://openalex.org/W6749032143","https://openalex.org/W6751921135","https://openalex.org/W6751961731","https://openalex.org/W6751972096","https://openalex.org/W6752191696","https://openalex.org/W6757082500","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"This":[0],"article":[1],"deals":[2],"with":[3],"distributed":[4,58,92,140],"policy":[5,85,100,134],"optimization":[6],"in":[7,26,144],"reinforcement":[8,34],"learning,":[9],"which":[10],"involves":[11],"a":[12,16,83,125,158],"central":[13],"controller":[14,52],"and":[15,37,50,71,105],"group":[17],"of":[18,75,131,146,152],"learners.":[19],"In":[20],"particular,":[21],"two":[22],"typical":[23],"settings":[24],"encountered":[25],"several":[27],"applications":[28],"are":[29,53,142],"considered:":[30],"<italic":[31,38],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32,39],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">multiagent":[33],"learning</i>":[35],"(RL)":[36],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">parallel":[40],"RL</i>":[41],",":[42],"where":[43],"frequent":[44,66],"information":[45],"exchanges":[46,68],"between":[47],"the":[48,51,61,73,76,99,108,121,132,139,150,168,173],"learners":[49,141],"required.":[54],"For":[55],"many":[56],"practical":[57],"systems,":[59],"however,":[60],"overhead":[62,110],"caused":[63],"by":[64,172],"these":[65],"communication":[67,102,109,153,169],"is":[69,88,116,162],"considerable,":[70],"becomes":[72],"bottleneck":[74],"overall":[77],"performance.":[78,114],"To":[79],"address":[80],"this":[81],"challenge,":[82],"novel":[84,95,122,174],"gradient":[86,101],"approach":[87,96],"developed":[89],"for":[90],"solving":[91],"RL.":[93],"The":[94],"adaptively":[97],"skips":[98],"during":[103],"iterations,":[104],"can":[106],"reduce":[107],"without":[111],"degrading":[112],"learning":[113,160],"It":[115],"established":[117],"analytically":[118],"that:":[119],"i)":[120],"algorithm":[123,175],"has":[124],"convergence":[126],"rate":[127],"identical":[128],"to":[129,156,177],"that":[130],"plain-vanilla":[133],"gradient;":[135],"while":[136],"ii)":[137],"if":[138],"heterogeneous":[143],"terms":[145],"their":[147],"reward":[148],"functions,":[149],"number":[151],"rounds":[154],"needed":[155],"achieve":[157],"desirable":[159],"accuracy":[161],"markedly":[163],"reduced.":[164],"Numerical":[165],"experiments":[166],"corroborate":[167],"reduction":[170],"attained":[171],"compared":[176],"alternatives.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}