{"id":"https://openalex.org/W4412196642","doi":"https://doi.org/10.1109/tnnls.2025.3577259","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","display_name":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","publication_year":2025,"publication_date":"2025-07-09","ids":{"openalex":"https://openalex.org/W4412196642","doi":"https://doi.org/10.1109/tnnls.2025.3577259","pmid":"https://pubmed.ncbi.nlm.nih.gov/40633025"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3577259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3577259","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/A5118966030","display_name":"Simin Li","orcid":"https://orcid.org/0000-0002-7947-6743"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Simin Li","raw_affiliation_strings":["State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102568493","display_name":"Ruixiao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiao Xu","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019851947","display_name":"Jingqiao Xiu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingqiao Xiu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100303448","display_name":"Yuwei Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Zheng","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100900707","display_name":"Pu Feng","orcid":"https://orcid.org/0000-0002-6219-1741"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Feng","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102401031","display_name":"Yuqing Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Ma","raw_affiliation_strings":["State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex and Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Institute of Artificial Intelligence, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011594363","display_name":"Xianglong Liu","orcid":"https://orcid.org/0000-0001-8425-4195"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Liu","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5118966030"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":8.5798,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97325965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"36","issue":"10","first_page":"18118","last_page":"18132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9140999913215637,"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/robustness","display_name":"Robustness (evolution)","score":0.7294442653656006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6874254941940308},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5540489554405212},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.44509750604629517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44210273027420044},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42848047614097595},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.42832261323928833},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41833510994911194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41529107093811035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14347109198570251}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7294442653656006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6874254941940308},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5540489554405212},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.44509750604629517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44210273027420044},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42848047614097595},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.42832261323928833},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41833510994911194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41529107093811035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14347109198570251},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3577259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3577259","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:40633025","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40633025","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":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G158119112","display_name":null,"funder_award_id":"2022ZD0116405","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1986872757","https://openalex.org/W2011418219","https://openalex.org/W2040704490","https://openalex.org/W2092939357","https://openalex.org/W2127234432","https://openalex.org/W2134478553","https://openalex.org/W2146948159","https://openalex.org/W2747213132","https://openalex.org/W2904455790","https://openalex.org/W2964184826","https://openalex.org/W2982316857","https://openalex.org/W2996320484","https://openalex.org/W3104122952","https://openalex.org/W3141248130","https://openalex.org/W3152331843","https://openalex.org/W3200753892","https://openalex.org/W3201885656","https://openalex.org/W4205158356","https://openalex.org/W4220668832","https://openalex.org/W4286748781","https://openalex.org/W4312072401","https://openalex.org/W4319165238","https://openalex.org/W4364322605","https://openalex.org/W4382202823","https://openalex.org/W4384080781","https://openalex.org/W4388240237","https://openalex.org/W4388579659","https://openalex.org/W4394994771","https://openalex.org/W4407376604"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"In":[0,22,66,166],"cooperative":[1,9,185],"multi-agent":[2,23],"reinforcement":[3],"learning":[4],"(MARL),":[5],"ensuring":[6],"robustness":[7,102,128,179],"against":[8],"agents":[10,45,154],"making":[11],"unpredictable":[12],"or":[13,30,53],"worst-case":[14,101,170],"adversarial":[15,141],"actions":[16],"is":[17],"crucial":[18],"for":[19,82,138],"real-world":[20],"deployment.":[21],"settings,":[24],"each":[25],"agent":[26],"may":[27],"be":[28],"perturbed":[29],"unperturbed,":[31],"leading":[32,59],"to":[33,60,157],"an":[34,150],"exponential":[35],"increase":[36],"in":[37,178,187,204,217],"potential":[38],"threat":[39,57,105],"scenarios":[40,106],"as":[41,95,118,133,149],"the":[42,167,199,205,212],"number":[43],"of":[44,77,136,169],"grows.":[46],"Existing":[47],"robust":[48,70,93,119,163],"MARL":[49,94,139],"methods":[50,177],"either":[51],"enumerate,":[52],"approximate":[54],"all":[55,104],"possible":[56,84],"scenarios,":[58],"intense":[61],"computation":[62],"and":[63,99,159,180,183,193,221],"insufficient":[64],"robustness.":[65],"contrast,":[67],"humans":[68],"develop":[69],"behaviors":[71],"by":[72,87,215],"maintaining":[73,184],"a":[74,96,124,134],"general":[75],"level":[76],"caution":[78,137],"rather":[79],"than":[80],"preparing":[81],"every":[83],"threat.":[85],"Inspired":[86],"human":[88],"decision":[89],"making,":[90],"we":[91,113],"frame":[92],"control-as-inference":[97],"problem,":[98],"optimize":[100],"across":[103],"implicitly":[107],"optimized":[108],"through":[109],"off-policy":[110],"evaluation.":[111],"Specifically,":[112],"introduce":[114],"mutual":[115],"information":[116,151],"regularization":[117,120],"(MIR3),":[121],"which":[122],"maximizes":[123],"lower":[125],"bound":[126],"on":[127],"during":[129],"routine":[130],"training,":[131],"serving":[132],"kind":[135],"without":[140],"inputs.":[142],"Further":[143],"insights":[144],"show":[145],"that":[146],"MIR3":[147,173],"acts":[148],"bottleneck,":[152],"preventing":[153],"from":[155],"over-reacting":[156],"others":[158],"aligning":[160],"policies":[161],"with":[162],"action":[164],"priors.":[165],"presence":[168],"adversaries,":[171],"our":[172,208],"significantly":[174],"surpasses":[175],"baseline":[176,214],"training":[181],"efficiency,":[182],"performance":[186],"StarCraft":[188],"II,":[189],"quadrotor":[190],"swarm":[191,195,201],"control,":[192],"robot":[194,200],"control.":[196],"When":[197],"deploying":[198],"control":[202],"algorithm":[203],"real":[206],"world,":[207],"method":[209],"also":[210],"outperforms":[211],"best":[213],"14.29%":[216],"reward.":[218],"See":[219],"code":[220],"demo":[222],"videos":[223],"at":[224],"https://github.com/DIG-Beihang/MIR3.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
