{"id":"https://openalex.org/W3045760389","doi":"https://doi.org/10.23919/acc45564.2020.9147381","title":"Toward Resilient Multi-Agent Actor-Critic Algorithms for Distributed Reinforcement Learning","display_name":"Toward Resilient Multi-Agent Actor-Critic Algorithms for Distributed Reinforcement Learning","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045760389","doi":"https://doi.org/10.23919/acc45564.2020.9147381","mag":"3045760389"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147381","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","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/A5100314961","display_name":"Yixuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixuan Lin","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058553647","display_name":"Shripad Gade","orcid":"https://orcid.org/0000-0003-3400-749X"},"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":"Shripad Gade","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070821128","display_name":"Romeil Sandhu","orcid":"https://orcid.org/0000-0002-7659-7590"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Romeil Sandhu","raw_affiliation_strings":["Departments of Bioinformatics and Computer Science, Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Departments of Bioinformatics and Computer Science, Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396338","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0003-2871-9888"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100314961"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":1.0605,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8209963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3953","last_page":"3958"},"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":0.9944000244140625,"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/T11031","display_name":"Game Theory and Applications","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7046669125556946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770358085632324},{"id":"https://openalex.org/keywords/distributed-learning","display_name":"Distributed learning","score":0.5472679734230042},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.47175198793411255},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.45491766929626465},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4536225199699402},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.42319726943969727},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40151020884513855},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36046773195266724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32156839966773987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2214677333831787}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7046669125556946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770358085632324},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.5472679734230042},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.47175198793411255},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.45491766929626465},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4536225199699402},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.42319726943969727},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40151020884513855},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36046773195266724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32156839966773987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2214677333831787},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc45564.2020.9147381","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","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":48,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1521003796","https://openalex.org/W1560074431","https://openalex.org/W1918371733","https://openalex.org/W1970903385","https://openalex.org/W1973039793","https://openalex.org/W1976195538","https://openalex.org/W1991888757","https://openalex.org/W2077274021","https://openalex.org/W2094387729","https://openalex.org/W2120846115","https://openalex.org/W2145067550","https://openalex.org/W2156737235","https://openalex.org/W2162655762","https://openalex.org/W2165469059","https://openalex.org/W2395575420","https://openalex.org/W2752689052","https://openalex.org/W2788115019","https://openalex.org/W2788308444","https://openalex.org/W2788816110","https://openalex.org/W2789911054","https://openalex.org/W2887374384","https://openalex.org/W2904435756","https://openalex.org/W2914861167","https://openalex.org/W2947958009","https://openalex.org/W2951896791","https://openalex.org/W2963028406","https://openalex.org/W2966757932","https://openalex.org/W3011272463","https://openalex.org/W3137092842","https://openalex.org/W3153787838","https://openalex.org/W4299802797","https://openalex.org/W6631137000","https://openalex.org/W6633472260","https://openalex.org/W6678168664","https://openalex.org/W6681342480","https://openalex.org/W6683195989","https://openalex.org/W6712181171","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6743821447","https://openalex.org/W6748268456","https://openalex.org/W6748786018","https://openalex.org/W6749032143","https://openalex.org/W6757082500","https://openalex.org/W6760018431","https://openalex.org/W6760825779","https://openalex.org/W6762191990"],"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/W2964765435"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"a":[3,18,41,59,105,126],"distributed":[4,80],"reinforcement":[5],"learning":[6],"problem":[7],"in":[8,56],"the":[9,45,63,73,99,109,114,131],"presence":[10],"of":[11,17,44,62,88,113],"Byzantine":[12,49],"agents.":[13,78],"The":[14,32,52,92,121],"system":[15],"consists":[16],"central":[19],"coordinating":[20],"authority":[21],"called":[22,29],"\"master":[23],"agent\"":[24],"and":[25,76],"multiple":[26],"computational":[27],"entities":[28],"\"worker":[30],"agents\".":[31],"master":[33,74,110],"agent":[34,75],"is":[35,83,95,136],"assumed":[36],"to":[37,102,108],"be":[38,48],"reliable,":[39],"while,":[40],"small":[42],"fraction":[43],"workers":[46,53],"can":[47],"(malicious)":[50],"adversaries.":[51],"are":[54],"interested":[55],"cooperatively":[57],"maximize":[58],"convex":[60],"combination":[61],"honest":[64],"(non-malicious)":[65],"worker":[66,77,100],"agents'":[67],"long-term":[68],"returns":[69],"through":[70],"communication":[71],"between":[72],"A":[79],"actor-critic":[81],"algorithm":[82,123],"studied":[84],"which":[85],"makes":[86],"use":[87],"entry-wise":[89],"trimmed":[90,127],"mean.":[91],"algorithm's":[93],"communication-efficiency":[94],"improved":[96,122],"by":[97],"allowing":[98],"agents":[101],"send":[103],"only":[104,130],"scalar-valued":[106,133],"variable":[107],"agent,":[111],"instead":[112],"entire":[115],"parameter":[116],"vector,":[117],"at":[118],"each":[119],"iteration.":[120],"involves":[124],"computing":[125],"mean":[128],"over":[129],"received":[132],"variable.":[134],"It":[135],"shown":[137],"that":[138],"both":[139],"algorithms":[140],"converge":[141],"almost":[142],"surely.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}