{"id":"https://openalex.org/W4379051467","doi":"https://doi.org/10.1109/tnnls.2023.3278715","title":"A Robust Mean-Field Actor-Critic Reinforcement Learning Against Adversarial Perturbations on Agent States","display_name":"A Robust Mean-Field Actor-Critic Reinforcement Learning Against Adversarial Perturbations on Agent States","publication_year":2023,"publication_date":"2023-06-05","ids":{"openalex":"https://openalex.org/W4379051467","doi":"https://doi.org/10.1109/tnnls.2023.3278715","pmid":"https://pubmed.ncbi.nlm.nih.gov/37276092"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3278715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3278715","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/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":true,"raw_author_name":"Ziyuan Zhou","raw_affiliation_strings":["Department of Computer Science, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, 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":["Department of Computer Science, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081318069","display_name":"MengChu Zhou","orcid":"https://orcid.org/0000-0002-5408-8752"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengchu Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043926144"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":4.7203,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95987062,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"35","issue":"10","first_page":"14370","last_page":"14381"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9957000017166138,"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":0.9957000017166138,"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":0.9491000175476074,"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":0.8884469270706177},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8415772914886475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.591042697429657},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5885783433914185},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.5399999022483826},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5358203053474426},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.507918655872345},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.489505410194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44407832622528076},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42278972268104553},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4159148633480072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2509733736515045},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12476876378059387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8884469270706177},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8415772914886475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.591042697429657},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5885783433914185},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.5399999022483826},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5358203053474426},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.507918655872345},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.489505410194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44407832622528076},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42278972268104553},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4159148633480072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2509733736515045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12476876378059387},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3278715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3278715","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:37276092","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37276092","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":[],"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/G7384271597","display_name":null,"funder_award_id":"22511105500","funder_id":"https://openalex.org/F4320311779","funder_display_name":"Shanghai Association for Science and Technology"},{"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/F4320311779","display_name":"Shanghai Association for Science and Technology","ror":"https://ror.org/05j0k2q54"},{"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":57,"referenced_works":["https://openalex.org/W1907356258","https://openalex.org/W1945616565","https://openalex.org/W2145339207","https://openalex.org/W2771114757","https://openalex.org/W2796202072","https://openalex.org/W2898963688","https://openalex.org/W2904455790","https://openalex.org/W2949103145","https://openalex.org/W2963762747","https://openalex.org/W2963934958","https://openalex.org/W2977117446","https://openalex.org/W2997293639","https://openalex.org/W2998367975","https://openalex.org/W2999905431","https://openalex.org/W3019142787","https://openalex.org/W3034126795","https://openalex.org/W3088310808","https://openalex.org/W3116666954","https://openalex.org/W3120778962","https://openalex.org/W3123514128","https://openalex.org/W3133540327","https://openalex.org/W3196700921","https://openalex.org/W3200753892","https://openalex.org/W3200885897","https://openalex.org/W3212436340","https://openalex.org/W4200498145","https://openalex.org/W4210693780","https://openalex.org/W4250739957","https://openalex.org/W4254547512","https://openalex.org/W4281255644","https://openalex.org/W4283030109","https://openalex.org/W4285060338","https://openalex.org/W4288775196","https://openalex.org/W4293846201","https://openalex.org/W4296437512","https://openalex.org/W4308480055","https://openalex.org/W4312403563","https://openalex.org/W4312616886","https://openalex.org/W4313484984","https://openalex.org/W4377111731","https://openalex.org/W6640425456","https://openalex.org/W6733049761","https://openalex.org/W6738796088","https://openalex.org/W6746428009","https://openalex.org/W6747941106","https://openalex.org/W6752380930","https://openalex.org/W6755069753","https://openalex.org/W6755480234","https://openalex.org/W6759058519","https://openalex.org/W6766805167","https://openalex.org/W6774966973","https://openalex.org/W6781541518","https://openalex.org/W6781750019","https://openalex.org/W6789484704","https://openalex.org/W6838398471","https://openalex.org/W6840380725","https://openalex.org/W6852997558"],"related_works":["https://openalex.org/W4214835929","https://openalex.org/W4226086326","https://openalex.org/W3119014777","https://openalex.org/W1570906179","https://openalex.org/W3212428133","https://openalex.org/W4282936078","https://openalex.org/W1607392272","https://openalex.org/W2236801283","https://openalex.org/W2110018584","https://openalex.org/W1499304752"],"abstract_inverted_index":{"Multiagent":[0],"deep":[1],"reinforcement":[2,32,69],"learning":[3,33,70],"(DRL)":[4],"makes":[5],"optimal":[6],"decisions":[7],"dependent":[8],"on":[9,18,98,114,171],"system":[10],"states":[11,101,118,161],"observed":[12],"by":[13],"agents,":[14],"but":[15],"any":[16],"uncertainty":[17],"the":[19,37,59,93,109,125,129,150,163],"observations":[20],"may":[21,155],"mislead":[22],"agents":[23],"to":[24,52,92,132,160,167],"take":[25],"wrong":[26],"actions.":[27],"The":[28],"mean-field":[29],"actor-critic":[30],"(MFAC)":[31],"is":[34,50,90,178],"well-known":[35],"in":[36,162,188],"multiagent":[38],"field":[39],"since":[40],"it":[41,49],"can":[42,56],"effectively":[43],"handle":[44],"a":[45,65,76,85,121,140,144],"scalability":[46],"problem.":[47],"However,":[48],"sensitive":[51],"state":[53],"perturbations":[54,159,182],"that":[55,71,89,107,176],"significantly":[57],"degrade":[58],"team":[60],"rewards.":[61],"This":[62],"work":[63,138],"proposes":[64,139],"Robust":[66],"MFAC":[67],"(RoMFAC)":[68],"has":[72],"two":[73],"innovations:":[74],"1)":[75],"new":[77],"objective":[78],"function":[79,88,106],"of":[80,84,124,153],"training":[81],"actors,":[82],"composed":[83],"policy":[86],"gradient":[87],"related":[91],"expected":[94],"cumulative":[95],"discount":[96],"reward":[97],"sampled":[99],"clean":[100,115],"and":[102,116,119],"an":[103],"action":[104,126],"loss":[105],"represents":[108],"difference":[110],"between":[111],"actions":[112],"taken":[113],"adversarial":[117,158,181],"2)":[120],"repetitive":[122],"regularization":[123],"loss,":[127],"ensuring":[128],"trained":[130],"actors":[131],"obtain":[133],"excellent":[134],"performance.":[135],"Furthermore,":[136],"this":[137],"game":[141,147],"model":[142],"named":[143],"state-adversarial":[145],"stochastic":[146],"(SASG).":[148],"Despite":[149],"Nash":[151],"equilibrium":[152],"SASG":[154],"not":[156],"exist,":[157],"RoMFAC":[164,177],"are":[165],"proven":[166],"be":[168],"defensible":[169],"based":[170],"SASG.":[172],"Experimental":[173],"results":[174],"show":[175],"robust":[179],"against":[180],"while":[183],"maintaining":[184],"its":[185],"competitive":[186],"performance":[187],"environments":[189],"without":[190],"perturbations.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}