{"id":"https://openalex.org/W4384080781","doi":"https://doi.org/10.1109/tnnls.2023.3292036","title":"Communication-Efficient and Resilient Distributed <i>Q</i>-Learning","display_name":"Communication-Efficient and Resilient Distributed <i>Q</i>-Learning","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384080781","doi":"https://doi.org/10.1109/tnnls.2023.3292036","pmid":"https://pubmed.ncbi.nlm.nih.gov/37436858"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3292036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3292036","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5032150135","display_name":"Yijing Xie","orcid":"https://orcid.org/0000-0002-7899-0484"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yijing Xie","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070733769","display_name":"Shaoshuai Mou","orcid":"https://orcid.org/0000-0002-3698-4238"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoshuai Mou","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076731201","display_name":"Shreyas Sundaram","orcid":"https://orcid.org/0000-0002-5390-2505"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Sundaram","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032150135"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":1.0087,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77032067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"35","issue":"3","first_page":"3351","last_page":"3364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9976000189781189,"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":0.9976000189781189,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991599977016449,"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":0.8036128878593445},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7037451267242432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6939282417297363},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5879389047622681},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5480483174324036},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5401117205619812},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5129591822624207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48378321528434753},{"id":"https://openalex.org/keywords/information-exchange","display_name":"Information exchange","score":0.44899600744247437},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44386690855026245},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.44073230028152466},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43153318762779236},{"id":"https://openalex.org/keywords/telecommunications-network","display_name":"Telecommunications network","score":0.4198479652404785},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3492780327796936},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3418026268482208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2908860743045807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18701666593551636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1339871883392334},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10976621508598328}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8036128878593445},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7037451267242432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6939282417297363},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5879389047622681},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5480483174324036},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5401117205619812},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5129591822624207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48378321528434753},{"id":"https://openalex.org/C189693848","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information exchange","level":2,"score":0.44899600744247437},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44386690855026245},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.44073230028152466},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43153318762779236},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.4198479652404785},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3492780327796936},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3418026268482208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2908860743045807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18701666593551636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1339871883392334},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10976621508598328},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3292036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3292036","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37436858","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37436858","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2701752822","display_name":null,"funder_award_id":"1653684","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309036","display_name":"Purdue University","ror":"https://ror.org/02dqehb95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1918371733","https://openalex.org/W1973184571","https://openalex.org/W1978518835","https://openalex.org/W2099175737","https://openalex.org/W2100953052","https://openalex.org/W2112668583","https://openalex.org/W2560013550","https://openalex.org/W2752784462","https://openalex.org/W2962775700","https://openalex.org/W2963686600","https://openalex.org/W2964339512","https://openalex.org/W2969788501","https://openalex.org/W2991444479","https://openalex.org/W3045760389","https://openalex.org/W3089075644","https://openalex.org/W3101352448","https://openalex.org/W3106753174","https://openalex.org/W3208941461","https://openalex.org/W3210169707","https://openalex.org/W4210320318","https://openalex.org/W4252654521","https://openalex.org/W4301295444","https://openalex.org/W6734565475","https://openalex.org/W6748786018","https://openalex.org/W6749032143","https://openalex.org/W6771232374","https://openalex.org/W6802973543"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W4281791088","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"This":[0],"article":[1],"investigates":[2],"the":[3,55,60,78,129,136,141,149,157,193,196,208,212,230],"problem":[4],"of":[5,21,54,66,83,131,140,186,195,200],"communication-efficient":[6],"and":[7,29,45,59,153,168,181],"resilient":[8,179],"multiagent":[9],"reinforcement":[10],"learning":[11,104,126,159],"(MARL).":[12],"Specifically,":[13],"we":[14,91,100,134,222],"consider":[15,92,135],"a":[16,19,26,40,47,52,74,115,163,178],"setting":[17],"where":[18,106,138],"set":[20],"agents":[22,71,107,142,172,227],"are":[23,173,216],"interconnected":[24],"over":[25],"given":[27],"network,":[28],"can":[30,143,228],"only":[31,108],"exchange":[32,109],"information":[33,110],"with":[34,111],"their":[35,85,112],"neighbors.":[36],"Each":[37],"agent":[38],"observes":[39],"common":[41],"Markov":[42],"Decision":[43],"Process":[44],"has":[46],"local":[48],"cost":[49],"which":[50],"is":[51,68,119],"function":[53,199],"current":[56],"system":[57],"state":[58],"applied":[61],"control":[62],"action.":[63],"The":[64],"goal":[65],"MARL":[67,97],"for":[69,219],"all":[70,84,187,201,225],"to":[72,95,192],"learn":[73,229],"policy":[75,232],"that":[76,123,224],"optimizes":[77],"infinite":[79],"horizon":[80],"discounted":[81],"average":[82],"costs.":[86],"Within":[87],"this":[88,124],"general":[89],"setting,":[90],"two":[93],"extensions":[94],"existing":[96],"algorithms.":[98],"First,":[99],"provide":[101],"an":[102],"event-triggered":[103],"rule":[105],"neighbors":[113],"if":[114],"certain":[116,205],"triggering":[117],"condition":[118],"satisfied.":[120],"We":[121,161,175],"show":[122,182,223],"enables":[125],"while":[127],"reducing":[128],"amount":[130],"communication.":[132],"Next,":[133],"scenario":[137],"some":[139],"be":[144],"adversarial":[145],"(as":[146],"captured":[147],"by":[148],"Byzantine":[150,171],"attack":[151],"model),":[152],"arbitrarily":[154],"deviate":[155],"from":[156],"prescribed":[158],"algorithm.":[160,235],"establish":[162],"fundamental":[164],"trade-off":[165],"between":[166],"optimality":[167],"resilience":[169],"when":[170],"present.":[174],"then":[176],"create":[177],"algorithm":[180],"almost":[183],"sure":[184],"convergence":[185],"reliable":[188,202,226],"agents'":[189],"value":[190,198],"functions":[191],"neighborhood":[194],"optimal":[197,213,231],"agents,":[203],"under":[204,233],"conditions":[206],"on":[207],"network":[209],"topology.":[210],"When":[211],"Q":[214],"-values":[215],"sufficiently":[217],"separated":[218],"different":[220],"actions,":[221],"our":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-07-13T00:00:00"}