{"id":"https://openalex.org/W2904455790","doi":"https://doi.org/10.1609/aaai.v33i01.33014213","title":"Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient","display_name":"Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904455790","doi":"https://doi.org/10.1609/aaai.v33i01.33014213","mag":"2904455790"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014213","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014213","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4327/4205","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4327/4205","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054519421","display_name":"Shihui Li","orcid":"https://orcid.org/0000-0002-4121-9119"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shihui Li","raw_affiliation_strings":["Carnegie Mellon"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101458171","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0003-3838-7418"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Wu","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528159","display_name":"Xinyue Cui","orcid":"https://orcid.org/0009-0008-8991-2132"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Cui","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022753479","display_name":"Honghua Dong","orcid":"https://orcid.org/0009-0006-8298-4059"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghua Dong","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061127138","display_name":"Fei Fang","orcid":"https://orcid.org/0000-0003-2256-8329"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Fang","raw_affiliation_strings":["Carnegie Mellon"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104083277","display_name":"Stuart Russell","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stuart Russell","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5054519421"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":18.6282,"has_fulltext":true,"cited_by_count":281,"citation_normalized_percentile":{"value":0.99263068,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"4213","last_page":"4220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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":0.8654119372367859},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.7314891815185547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950173377990723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6263766288757324},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5034663081169128},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.48833104968070984},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.481708824634552},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42144182324409485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37936222553253174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1674444079399109}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8654119372367859},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.7314891815185547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950173377990723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6263766288757324},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5034663081169128},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.48833104968070984},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.481708824634552},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42144182324409485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37936222553253174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1674444079399109},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014213","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014213","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4327/4205","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014213","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014213","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4327/4205","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904455790.pdf","grobid_xml":"https://content.openalex.org/works/W2904455790.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1513468570","https://openalex.org/W1542941925","https://openalex.org/W1602326725","https://openalex.org/W1945616565","https://openalex.org/W2097498347","https://openalex.org/W2099471712","https://openalex.org/W2099618002","https://openalex.org/W2105078254","https://openalex.org/W2119717200","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2255045308","https://openalex.org/W2257979135","https://openalex.org/W2395575420","https://openalex.org/W2475089067","https://openalex.org/W2594794854","https://openalex.org/W2602275733","https://openalex.org/W2602963933","https://openalex.org/W2604283518","https://openalex.org/W2604763608","https://openalex.org/W2605102758","https://openalex.org/W2617547828","https://openalex.org/W2623431351","https://openalex.org/W2760600531","https://openalex.org/W2766413382","https://openalex.org/W2773691349","https://openalex.org/W2785315072","https://openalex.org/W2786478526","https://openalex.org/W2798511001","https://openalex.org/W2949561945","https://openalex.org/W2962941327","https://openalex.org/W2963000099","https://openalex.org/W2963207607","https://openalex.org/W2963390138","https://openalex.org/W2963627051","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W2964191473","https://openalex.org/W2964338167","https://openalex.org/W2964345382","https://openalex.org/W3101442004","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4295150809","https://openalex.org/W4295846245","https://openalex.org/W4297669414","https://openalex.org/W4297789683","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W4320013936","https://openalex.org/W6675860490","https://openalex.org/W6684205842","https://openalex.org/W6721101288","https://openalex.org/W6744562401"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Despite":[0],"the":[1,20,25,29,50,69,80,86,114,124,139,179],"recent":[2],"advances":[3],"of":[4,71,123],"deep":[5,127],"reinforcement":[6],"learning":[7,82,150],"(DRL),":[8],"agents":[9,75,88,180],"trained":[10,87,181],"by":[11,182],"DRL":[12,33,74],"tend":[13],"to":[14,19,58,144,158],"be":[15,54],"brittle":[16],"and":[17,174,178],"sensitive":[18],"training":[21,47,72],"environment,":[22],"especially":[23],"in":[24,40,79,147,170],"multi-agent":[26,30,81,126,176],"scenarios.":[27],"In":[28,63],"setting,":[31],"a":[32,41,103,120],"agent\u2019s":[34],"policy":[35,52,129,135],"can":[36,89],"easily":[37],"get":[38],"stuck":[39],"poor":[42],"local":[43],"optima":[44],"w.r.t.":[45],"its":[46,93],"partners":[48],"\u2013":[49],"learned":[51],"may":[53],"only":[55],"locally":[56],"optimal":[57],"other":[59],"agents\u2019":[60],"current":[61],"policies.":[62],"this":[64,99],"paper,":[65],"we":[66,101,118,152],"focus":[67],"on":[68],"problem":[70],"robust":[73,134],"with":[76,113],"continuous":[77,140],"actions":[78],"setting":[83],"so":[84],"that":[85],"still":[90],"generalize":[91],"when":[92],"opponents\u2019":[94],"policies":[95],"alter.":[96],"To":[97],"tackle":[98],"problem,":[100],"proposed":[102,162],"new":[104],"algorithm,":[105],"MiniMax":[106],"Multi-agent":[107],"Deep":[108],"Deterministic":[109],"Policy":[110],"Gradient":[111],"(M3DDPG)":[112],"following":[115],"contributions:":[116],"(1)":[117],"introduce":[119],"minimax":[121,149],"extension":[122],"popular":[125],"deterministic":[128],"gradient":[130],"algorithm":[131,169],"(MADDPG),":[132],"for":[133],"learning;":[136],"(2)":[137],"since":[138],"action":[141],"space":[142],"leads":[143],"computational":[145],"intractability":[146],"our":[148,161,167,183],"objective,":[151],"propose":[153],"Multi-Agent":[154],"Adversarial":[155],"Learning":[156],"(MAAL)":[157],"efficiently":[159],"solve":[160],"formulation.":[163],"We":[164],"empirically":[165],"evaluate":[166],"M3DDPG":[168],"four":[171],"mixed":[172],"cooperative":[173],"competitive":[175],"environments":[177],"method":[184],"significantly":[185],"outperforms":[186],"existing":[187],"baselines.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":54},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}