{"id":"https://openalex.org/W4409796470","doi":"https://doi.org/10.1109/tsmc.2025.3561276","title":"Robust Training in Multiagent Deep Reinforcement Learning Against Optimal Adversary","display_name":"Robust Training in Multiagent Deep Reinforcement Learning Against Optimal Adversary","publication_year":2025,"publication_date":"2025-04-25","ids":{"openalex":"https://openalex.org/W4409796470","doi":"https://doi.org/10.1109/tsmc.2025.3561276"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3561276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3561276","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","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/A5101303108","display_name":"Weiran Guo","orcid":"https://orcid.org/0009-0008-1626-8745"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiran Guo","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072386697","display_name":"Guanjun Liu","orcid":"https://orcid.org/0000-0002-7523-4827"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjun Liu","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043926144","display_name":"Ziyuan Zhou","orcid":"https://orcid.org/0000-0002-2649-8666"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyuan Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108025258","display_name":"Jiacun Wang","orcid":"https://orcid.org/0000-0001-6601-3515"},"institutions":[{"id":"https://openalex.org/I141450709","display_name":"Monmouth University","ror":"https://ror.org/01d6qxv05","country_code":"US","type":"education","lineage":["https://openalex.org/I141450709"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiacun Wang","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Monmouth University, West Long Branch, NJ, USA","institution_ids":["https://openalex.org/I141450709"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086134377","display_name":"Ying Tang","orcid":"https://orcid.org/0000-0001-6064-1908"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Tang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ, USA","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343762","display_name":"Miaomiao Wang","orcid":"https://orcid.org/0000-0001-7498-5162"},"institutions":[{"id":"https://openalex.org/I4210089040","display_name":"Beijing Institute of Optoelectronic Technology","ror":"https://ror.org/0099d6q96","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaomiao Wang","raw_affiliation_strings":["Space Optoelectronic Measurement and Perception Lab, Beijing Institute of Control Engineering, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Space Optoelectronic Measurement and Perception Lab, Beijing Institute of Control Engineering, Beijing, China","institution_ids":["https://openalex.org/I4210089040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101303108"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":2.8843,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9056505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"55","issue":"7","first_page":"4957","last_page":"4968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9814000129699707,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9814000129699707,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9057999849319458,"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":0.7355960011482239},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.664612352848053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5220434665679932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5077530145645142},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47451987862586975},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4361177384853363},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.26586151123046875},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19796103239059448},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06955462694168091},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04810458421707153}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7355960011482239},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.664612352848053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220434665679932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5077530145645142},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47451987862586975},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4361177384853363},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26586151123046875},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19796103239059448},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06955462694168091},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04810458421707153},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3561276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3561276","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5788605144","display_name":null,"funder_award_id":"62172299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8592490694","display_name":null,"funder_award_id":"62032019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2747213132","https://openalex.org/W2781800156","https://openalex.org/W3116666954","https://openalex.org/W3194459689","https://openalex.org/W4224874620","https://openalex.org/W4293846201","https://openalex.org/W4312572320","https://openalex.org/W4312616886","https://openalex.org/W4379051467","https://openalex.org/W4381733136","https://openalex.org/W4385068279","https://openalex.org/W4386065468","https://openalex.org/W4387171533","https://openalex.org/W4387682207","https://openalex.org/W4390618715","https://openalex.org/W4393147110","https://openalex.org/W4396599460","https://openalex.org/W4399282679","https://openalex.org/W4403210289","https://openalex.org/W6640425456","https://openalex.org/W6737897983","https://openalex.org/W6746973458","https://openalex.org/W6752380930","https://openalex.org/W6752420067","https://openalex.org/W6758846586","https://openalex.org/W6774966973","https://openalex.org/W6779101081","https://openalex.org/W6781755612","https://openalex.org/W6789484704","https://openalex.org/W6796436736","https://openalex.org/W6797106545","https://openalex.org/W6838398471","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W4388150944","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291"],"abstract_inverted_index":{"Industry":[0,29,131],"5.0":[1,132],"enhances":[2],"manufacturing":[3],"ability":[4],"through":[5],"efficient":[6],"human-machine":[7],"interaction,":[8],"combining":[9],"human":[10],"resources":[11],"and":[12,19,47,56,133,161,166],"robots":[13],"to":[14,84,130,171],"complete":[15],"tasks":[16],"more":[17,114],"accurately":[18],"effectively.":[20],"Artificial":[21],"intelligence":[22],"(AI)":[23],"plays":[24],"an":[25,66,92,101],"essential":[26],"role":[27],"in":[28,34,44,59,120,140,155],"5.0.":[30],"As":[31],"a":[32,52,134],"branch":[33],"AI,":[35],"multiagent":[36],"deep":[37],"reinforcement":[38],"learning":[39],"(MADRL)":[40],"attracts":[41],"vast":[42],"attention":[43],"both":[45],"academia":[46],"industry.":[48],"However,":[49],"there":[50],"is":[51,91,118,149],"gap":[53],"between":[54],"virtual":[55],"physical":[57],"environments":[58],"terms":[60],"of":[61,80,88,124,175],"how":[62,83],"<italic":[63],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">clean</i>":[65],"observed":[67],"state":[68,72,104],"is.":[69],"In":[70,96],"addition,":[71],"adversarial":[73,147],"attacks":[74],"can":[75],"seriously":[76],"impact":[77],"the":[78,86,111,121,145,156,173],"performance":[79],"MADRL.":[81],"Hence,":[82],"improve":[85],"robustness":[87,142],"MADRL":[89,112,152],"algorithms":[90,153],"important":[93],"research":[94],"topic.":[95],"this":[97],"article,":[98],"we":[99],"propose":[100],"optimal":[102,146],"policy-based":[103],"adversary":[105],"attack":[106,148],"method":[107],"that":[108],"would":[109],"make":[110],"algorithm":[113],"robust":[115],"when":[116],"it":[117],"applied":[119],"training":[122,143,160],"process":[123],"agents.":[125],"Two":[126],"case":[127,136],"studies":[128],"related":[129],"general":[135],"study":[137],"are":[138],"presented":[139],"which":[141],"against":[144],"tested.":[150],"The":[151],"involved":[154],"experiments":[157],"include":[158],"centralized":[159],"decentralized":[162],"execution":[163],"(CTDE)":[164],"framework":[165],"shared":[167],"experience":[168],"actor-critic":[169],"(SEAC)":[170],"demonstrate":[172],"universality":[174],"our":[176],"method.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}