{"id":"https://openalex.org/W4312240927","doi":"https://doi.org/10.1109/mlsp55214.2022.9943500","title":"Data-Driven Robust Multi-Agent Reinforcement Learning","display_name":"Data-Driven Robust Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4312240927","doi":"https://doi.org/10.1109/mlsp55214.2022.9943500"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55214.2022.9943500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55214.2022.9943500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5100705266","display_name":"Yudan Wang","orcid":"https://orcid.org/0000-0003-4262-8819"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudan Wang","raw_affiliation_strings":["University at Buffalo,Department of Electrical Engineering","Department of Electrical Engineering, University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo,Department of Electrical Engineering","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Electrical Engineering, University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372089","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0146-7262"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["University at Buffalo,Department of Electrical Engineering","Department of Electrical Engineering, University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo,Department of Electrical Engineering","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Electrical Engineering, University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101704070","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-3982-9145"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["University of Utah,Department of Electrical and Computer Engineering","Department of Electrical and Computer Engineering, University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067109059","display_name":"Alvaro Velasquez","orcid":"https://orcid.org/0000-0001-6757-105X"},"institutions":[{"id":"https://openalex.org/I1280414376","display_name":"United States Air Force Research Laboratory","ror":"https://ror.org/02e2egq70","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280414376","https://openalex.org/I1330347796","https://openalex.org/I4210102105","https://openalex.org/I4389425425"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvaro Velasquez","raw_affiliation_strings":["Information Directorate, Air Force Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Directorate, Air Force Research Laboratory","institution_ids":["https://openalex.org/I1280414376"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012545205","display_name":"Shaofeng Zou","orcid":"https://orcid.org/0000-0002-2821-6941"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaofeng Zou","raw_affiliation_strings":["University at Buffalo,Department of Electrical Engineering","Department of Electrical Engineering, University at Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo,Department of Electrical Engineering","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Electrical Engineering, University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1686,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43942557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.984000027179718,"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":0.8632934093475342},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7266285419464111},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6954602003097534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6919199228286743},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.600059986114502},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5517138242721558},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5177121162414551},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4914432764053345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45079711079597473},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42782387137413025},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.421791136264801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3717763423919678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17256543040275574}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8632934093475342},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7266285419464111},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6954602003097534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919199228286743},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.600059986114502},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5517138242721558},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5177121162414551},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4914432764053345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45079711079597473},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42782387137413025},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.421791136264801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3717763423919678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17256543040275574},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55214.2022.9943500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55214.2022.9943500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G4713624018","display_name":"Collaborative Research: CIF: Medium: Emerging Directions in Robust Learning and Inference","funder_award_id":"2106560","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W20510943","https://openalex.org/W41554520","https://openalex.org/W1542941925","https://openalex.org/W2014002306","https://openalex.org/W2145339207","https://openalex.org/W2151685478","https://openalex.org/W2168565265","https://openalex.org/W2169186423","https://openalex.org/W2507578125","https://openalex.org/W2530849036","https://openalex.org/W2594794854","https://openalex.org/W2602963933","https://openalex.org/W2746553466","https://openalex.org/W2773525213","https://openalex.org/W2788115019","https://openalex.org/W2941205169","https://openalex.org/W2977813751","https://openalex.org/W2991046523","https://openalex.org/W3028683606","https://openalex.org/W3101572197","https://openalex.org/W3130610232","https://openalex.org/W3196526668","https://openalex.org/W3207876914","https://openalex.org/W3214274533","https://openalex.org/W4221153150","https://openalex.org/W4280543789","https://openalex.org/W4297729153","https://openalex.org/W4301501993","https://openalex.org/W4301602852","https://openalex.org/W6684892534","https://openalex.org/W6735011893","https://openalex.org/W6735677848","https://openalex.org/W6739506316","https://openalex.org/W6747027214","https://openalex.org/W6749032143","https://openalex.org/W6767434776","https://openalex.org/W6778053572","https://openalex.org/W6781640943","https://openalex.org/W6785517317","https://openalex.org/W6800181308","https://openalex.org/W6802038118","https://openalex.org/W6809658055","https://openalex.org/W6838734048"],"related_works":["https://openalex.org/W1970303738","https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W2097562045","https://openalex.org/W4281812492","https://openalex.org/W2315999538","https://openalex.org/W3105579180","https://openalex.org/W2990709181"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"in":[4,42],"the":[5,16,22,35,47,52,56,61,65,102,107,121],"collaborative":[6],"setting":[7],"aims":[8],"to":[9,40,50,106,120],"find":[10],"a":[11,77,87],"joint":[12],"policy":[13],"that":[14,101],"maximizes":[15],"accumulated":[17],"reward":[18],"averaged":[19],"over":[20,55],"all":[21],"agents.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27],"focus":[28],"on":[29],"MARL":[30],"under":[31,128],"model":[32,129],"uncertainty,":[33],"where":[34,64],"transition":[36],"kernel":[37],"is":[38,49,93],"assumed":[39],"be":[41,82],"an":[43,70],"uncertainty":[44,57,130],"set,":[45],"and":[46,95,111,135],"goal":[48],"optimize":[51],"worst-case":[53],"performance":[54],"set.":[58],"We":[59,85,98],"investigate":[60],"model-free":[62,94],"setting,":[63],"uncertain":[66],"set":[67],"centers":[68],"around":[69],"unknown":[71],"Markov":[72],"decision":[73],"process":[74],"from":[75],"which":[76,92],"single":[78],"sample":[79,115],"trajectory":[80],"can":[81],"obtained":[83],"sequentially.":[84],"develop":[86],"robust":[88,109],"multi-agent":[89,123],"Q-learning":[90],"algorithm,":[91,118],"fully":[96],"decentralized.":[97],"theoretically":[99],"prove":[100],"proposed":[103],"algorithm":[104],"converges":[105],"minimax":[108],"policy,":[110],"further":[112],"characterize":[113],"its":[114],"complexity.":[116],"Our":[117],"comparing":[119],"vanilla":[122],"Q-learning,":[124],"offers":[125],"provable":[126],"robustness":[127],"without":[131],"incurring":[132],"additional":[133],"computational":[134],"memory":[136],"cost.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}