{"id":"https://openalex.org/W4412719127","doi":"https://doi.org/10.1109/tase.2025.3592721","title":"Toward Fault Tolerance in Multi-Agent Reinforcement Learning","display_name":"Toward Fault Tolerance in Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412719127","doi":"https://doi.org/10.1109/tase.2025.3592721"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3592721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3592721","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5061800993","display_name":"Yuchen Shi","orcid":"https://orcid.org/0009-0006-2703-1482"},"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":true,"raw_author_name":"Yuchen Shi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067328517","display_name":"Huaxin Pei","orcid":"https://orcid.org/0000-0003-4815-2778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaxin Pei","raw_affiliation_strings":["Qiyuan Lab, Beijing, China","QiYuan Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Qiyuan Lab, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"QiYuan Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048905826","display_name":"Liang Feng","orcid":"https://orcid.org/0000-0002-7586-8424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Feng","raw_affiliation_strings":["Qiyuan Lab, Beijing, China","QiYuan Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Qiyuan Lab, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"QiYuan Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653787","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0001-5526-866X"},"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":"Yi Zhang","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081663090","display_name":"Danya Yao","orcid":"https://orcid.org/0000-0001-5032-6322"},"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":"Danya Yao","raw_affiliation_strings":["Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061800993"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.9698,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95095191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"22","issue":null,"first_page":"19007","last_page":"19024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10270","display_name":"Blockchain Technology Applications and Security","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14011","display_name":"Elevator Systems and Control","score":0.9610000252723694,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6697908043861389},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6619508266448975},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5436527132987976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5188756585121155},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4845251441001892},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3250044286251068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32053524255752563},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.31319141387939453},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.13038885593414307}],"concepts":[{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6697908043861389},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6619508266448975},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5436527132987976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5188756585121155},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4845251441001892},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3250044286251068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32053524255752563},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.31319141387939453},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.13038885593414307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3592721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3592721","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6700000166893005,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G8508485082","display_name":null,"funder_award_id":"62133002","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":59,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2071099085","https://openalex.org/W2105482032","https://openalex.org/W2168359464","https://openalex.org/W2592335154","https://openalex.org/W2598136971","https://openalex.org/W2617547828","https://openalex.org/W2793582886","https://openalex.org/W2811374584","https://openalex.org/W2904455790","https://openalex.org/W2954559956","https://openalex.org/W2963516811","https://openalex.org/W2978292403","https://openalex.org/W2982519995","https://openalex.org/W2997940961","https://openalex.org/W3002200886","https://openalex.org/W3046988891","https://openalex.org/W3127561923","https://openalex.org/W3156501016","https://openalex.org/W3175144487","https://openalex.org/W3200753892","https://openalex.org/W3212604410","https://openalex.org/W4210359878","https://openalex.org/W4213053159","https://openalex.org/W4226436200","https://openalex.org/W4288118072","https://openalex.org/W4289147358","https://openalex.org/W4313591421","https://openalex.org/W4315574176","https://openalex.org/W4322730824","https://openalex.org/W4385245566","https://openalex.org/W4385473944","https://openalex.org/W4385834387","https://openalex.org/W4389065375","https://openalex.org/W4392309410","https://openalex.org/W4396909955","https://openalex.org/W4402834495","https://openalex.org/W4403635709","https://openalex.org/W4404985202","https://openalex.org/W4407950249","https://openalex.org/W4409723333","https://openalex.org/W4409723389","https://openalex.org/W6682137061","https://openalex.org/W6683204974","https://openalex.org/W6687681856","https://openalex.org/W6738796088","https://openalex.org/W6749304979","https://openalex.org/W6752963931","https://openalex.org/W6755069753","https://openalex.org/W6757310144","https://openalex.org/W6764943343","https://openalex.org/W6767579722","https://openalex.org/W6785517317","https://openalex.org/W6840380725","https://openalex.org/W6848782485","https://openalex.org/W6849054939","https://openalex.org/W6852739845","https://openalex.org/W6855512891","https://openalex.org/W6866723962"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2144438995","https://openalex.org/W1577886464","https://openalex.org/W2164896586","https://openalex.org/W1593559483","https://openalex.org/W2108334564","https://openalex.org/W2111125783","https://openalex.org/W2100367016"],"abstract_inverted_index":{"Agent":[0],"faults":[1,42,165,171],"pose":[2],"a":[3,52,74,109,134,226],"significant":[4,254],"threat":[5],"to":[6,23,51,92,105,114,119,177,197,217,232,243,275,278],"the":[7,28,44,63,87,102,145,154,214,260,269,273],"performance":[8,192],"of":[9,66,147,156,163,191,262],"multi-agent":[10],"reinforcement":[11],"learning":[12],"(MARL)":[13],"algorithms,":[14],"introducing":[15],"two":[16],"key":[17],"challenges.":[18],"First,":[19],"agents":[20],"often":[21],"struggle":[22],"extract":[24],"critical":[25,118,234],"information":[26,98],"from":[27,236],"chaotic":[29],"state":[30],"space":[31],"created":[32],"by":[33,68],"unexpected":[34,198],"faults.":[35,199],"Second,":[36],"transitions":[37,117],"recorded":[38],"before":[39],"and":[40,89,94,99,132,170,285],"after":[41],"in":[43,127,159,167,189,204,256],"replay":[45],"buffer":[46],"affect":[47],"training":[48,76,121,245],"unevenly,":[49],"leading":[50],"sample":[53,116],"imbalance":[54],"problem.":[55],"To":[56,123,200],"overcome":[57],"these":[58],"challenges,":[59],"this":[60,128],"paper":[61],"enhances":[62],"fault":[64,97,202,251,257],"tolerance":[65,203],"MARL":[67,182],"combining":[69],"optimized":[70],"model":[71],"architecture":[72],"with":[73],"tailored":[75],"data":[77],"sampling":[78,228],"strategy.":[79],"Specifically,":[80],"an":[81,209],"attention":[82,103,210],"mechanism":[83,111,211],"is":[84,112,230],"incorporated":[85],"into":[86],"actor":[88],"critic":[90],"networks":[91],"effectively":[93],"automatically":[95],"detect":[96],"dynamically":[100,218],"regulate":[101],"given":[104],"faulty":[106],"agents.":[107],"Additionally,":[108,225],"prioritization":[110,227],"introduced":[113],"selectively":[115],"current":[120,244],"needs.":[122,246],"further":[124],"support":[125],"research":[126],"area,":[129],"we":[130,207],"design":[131],"open-source":[133],"highly":[135,195],"decoupled":[136],"code":[137],"platform":[138],"for":[139],"fault-tolerant":[140],"MARL,":[141],"aimed":[142],"at":[143,173],"improving":[144],"efficiency":[146],"studying":[148],"related":[149],"problems.":[150],"Experimental":[151,247],"results":[152,248],"demonstrate":[153,253],"effectiveness":[155],"our":[157,263],"method":[158,271],"handling":[160],"various":[161,250],"types":[162,252],"faults,":[164],"occurring":[166],"any":[168],"agent,":[169],"arising":[172],"random":[174],"times.":[175],"Note":[176],"Practitioners\u2014Multi-agent":[178],"systems":[179,284],"based":[180],"on":[181,222],"outperform":[183],"those":[184],"using":[185],"traditional":[186],"control":[187],"methods":[188],"terms":[190],"but":[193],"remain":[194],"vulnerable":[196],"improve":[201],"such":[205,281],"systems,":[206],"introduce":[208],"that":[212,239,268],"enables":[213],"neural":[215],"network":[216],"adjust":[219],"its":[220],"focus":[221],"fault-related":[223],"information.":[224],"strategy":[229],"employed":[231],"select":[233],"samples":[235],"collected":[237],"experiences":[238],"are":[240],"most":[241],"relevant":[242],"across":[249],"improvements":[255],"tolerance,":[258],"validating":[259],"robustness":[261],"approach.":[264],"These":[265],"findings":[266],"suggest":[267],"proposed":[270],"has":[272],"potential":[274],"be":[276],"applied":[277],"real-world":[279],"scenarios,":[280],"as":[282],"multi-robot":[283],"autonomous":[286],"vehicle":[287],"fleets.":[288]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-07-29T00:00:00"}
