{"id":"https://openalex.org/W4399451134","doi":"https://doi.org/10.1109/tac.2024.3409676","title":"Resilient Multiagent Reinforcement Learning With Function Approximation","display_name":"Resilient Multiagent Reinforcement Learning With Function Approximation","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4399451134","doi":"https://doi.org/10.1109/tac.2024.3409676"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3409676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3409676","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","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/A5043334116","display_name":"Lintao Ye","orcid":"https://orcid.org/0000-0001-8608-5815"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lintao Ye","raw_affiliation_strings":["Key Laboratory of Image Processing and Intelligent Control, Ministry of Education and the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-8608-5815","affiliations":[{"raw_affiliation_string":"Key Laboratory of Image Processing and Intelligent Control, Ministry of Education and the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004299587","display_name":"Martin Figura","orcid":"https://orcid.org/0000-0002-3141-4762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Figura","raw_affiliation_strings":["Fortna, Denver, CO, USA"],"raw_orcid":"https://orcid.org/0000-0002-3141-4762","affiliations":[{"raw_affiliation_string":"Fortna, Denver, CO, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011556437","display_name":"Yixuan Lin","orcid":"https://orcid.org/0000-0002-2251-9474"},"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":"Yixuan Lin","raw_affiliation_strings":["Department of Applied Mathematics and Statistics, Stony Brook University, Centereach, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-2251-9474","affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics and Statistics, Stony Brook University, Centereach, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006828972","display_name":"Mainak Pal","orcid":"https://orcid.org/0000-0002-0206-2112"},"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":"Mainak Pal","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0206-2112","affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083404577","display_name":"P. Das","orcid":"https://orcid.org/0000-0002-2175-3402"},"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":"Pranoy Das","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-2175-3402","affiliations":[{"raw_affiliation_string":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","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, Centereach, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-2871-9888","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stony Brook University, Centereach, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024301984","display_name":"Vijay Gupta","orcid":"https://orcid.org/0000-0001-7060-3956"},"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":"Vijay Gupta","raw_affiliation_strings":["Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-7060-3956","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":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7046,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91175972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"69","issue":"12","first_page":"8497","last_page":"8512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8022000193595886,"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":0.8022000193595886,"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/T10524","display_name":"Traffic control and management","score":0.7200000286102295,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T14011","display_name":"Elevator Systems and Control","score":0.6764000058174133,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8171669244766235},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6739580631256104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5677100419998169},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.514232337474823},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4266829490661621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37566936016082764},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22911638021469116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1269330382347107}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8171669244766235},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6739580631256104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5677100419998169},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.514232337474823},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4266829490661621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37566936016082764},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22911638021469116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1269330382347107},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3409676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3409676","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2393951931","display_name":null,"funder_award_id":"FA9550-21-1-0231","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G289220329","display_name":null,"funder_award_id":"62203179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4700810773","display_name":null,"funder_award_id":"13001364","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5763443098","display_name":null,"funder_award_id":"F.10052139.02.012","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5916025732","display_name":"Collaborative Research: CPS: Medium: Adaptive, Human-centric Demand-side Flexibility Coordination At-scale in Electric Power Networks","funder_award_id":"2300355","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8053630600","display_name":"III: Small: Distributed Reinforcement Learning over Complex Networks","funder_award_id":"2230101","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1639167632","https://openalex.org/W1760770890","https://openalex.org/W1918371733","https://openalex.org/W1973184571","https://openalex.org/W2000219814","https://openalex.org/W2025375132","https://openalex.org/W2146162554","https://openalex.org/W2617547828","https://openalex.org/W2883532348","https://openalex.org/W2962716894","https://openalex.org/W2962775700","https://openalex.org/W3011272463","https://openalex.org/W3045760389","https://openalex.org/W3153787838","https://openalex.org/W3161475465","https://openalex.org/W3161868942","https://openalex.org/W3175144487","https://openalex.org/W3186333353","https://openalex.org/W4210320318","https://openalex.org/W4229706427","https://openalex.org/W4243772471","https://openalex.org/W4252654521","https://openalex.org/W6602332174","https://openalex.org/W6738796088","https://openalex.org/W6743821447","https://openalex.org/W6748268456","https://openalex.org/W6748626757","https://openalex.org/W6749032143","https://openalex.org/W6758960857","https://openalex.org/W6766805167","https://openalex.org/W6771232374","https://openalex.org/W6775464632","https://openalex.org/W6791279797","https://openalex.org/W6802536806","https://openalex.org/W6810201281"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"Adversarial":[0],"attacks":[1,29],"during":[2],"training":[3],"can":[4],"strongly":[5],"influence":[6],"the":[7,25,52,68,76,88,101,104,129,141,144,165,168,171],"performance":[8],"of":[9,27,90,103,143,159,170],"multiagent":[10],"reinforcement":[11],"learning":[12],"algorithms.":[13],"It":[14],"is,":[15],"thus,":[16],"highly":[17],"desirable":[18],"to":[19,80,108,151],"augment":[20],"existing":[21],"algorithms":[22],"such":[23],"that":[24,86,117,131,140,167],"impact":[26],"adversarial":[28,172],"on":[30],"cooperative":[31,105,145],"networks":[32],"is":[33,132],"at":[34,120],"least":[35],"bounded.":[36],"We":[37,57,84],"consider":[38],"a":[39,47,59,109,152,156],"fully":[40],"decentralized":[41],"network,":[42],"where":[43],"each":[44,65],"agent":[45,66],"receives":[46],"local":[48],"reward":[49,70],"and":[50,55,71,74,95],"observes":[51],"global":[53],"state":[54],"action.":[56],"propose":[58],"resilient":[60],"consensus-based":[61],"actor-critic":[62],"algorithm,":[63],"whereby":[64],"estimates":[67,102],"team-average":[69,161],"value":[72,112],"function,":[73],"communicates":[75],"associated":[77],"parameter":[78],"vectors":[79],"its":[81],"immediate":[82],"neighbors.":[83],"show":[85],"in":[87,128],"presence":[89],"Byzantine":[91,126],"agents,":[92],"whose":[93],"estimation":[94],"communication":[96],"strategies":[97],"are":[98,119],"completely":[99],"arbitrary,":[100],"agents":[106,127,146,173],"converge":[107],"bounded":[110,153],"consensus":[111],"with":[113,148],"probability":[114,149],"one,":[115],"provided":[116],"there":[118],"most":[121],"<inline-formula":[122,133],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123,134],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[124,135],"notation=\"LaTeX\">$H$</tex-math></inline-formula>":[125],"network":[130],"notation=\"LaTeX\">$(2H+1)$</tex-math></inline-formula>-robust.":[136],"Furthermore,":[137],"we":[138],"prove":[139],"policy":[142],"converges":[147],"one":[150],"neighborhood":[154],"around":[155],"stationary":[157],"point":[158],"their":[160],"objective":[162],"function":[163],"under":[164],"assumption":[166],"policies":[169],"asymptotically":[174],"become":[175],"stationary.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}