{"id":"https://openalex.org/W4406858125","doi":"https://doi.org/10.1109/tcds.2025.3533744","title":"MAST: Multiagent Safe Transformer for Reinforcement Learning","display_name":"MAST: Multiagent Safe Transformer for Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-27","ids":{"openalex":"https://openalex.org/W4406858125","doi":"https://doi.org/10.1109/tcds.2025.3533744"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3533744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3533744","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental 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":null,"display_name":"Suhang Wei","orcid":"https://orcid.org/0009-0004-6667-7222"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Suhang Wei","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai"],"raw_orcid":"https://orcid.org/0009-0004-6667-7222","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianwei Wang","orcid":"https://orcid.org/0009-0006-7520-2522"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianwei Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai"],"raw_orcid":"https://orcid.org/0009-0006-7520-2522","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050493033","display_name":"Xiang Feng","orcid":"https://orcid.org/0000-0001-6083-3440"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Feng","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai"],"raw_orcid":"https://orcid.org/0000-0001-6083-3440","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058941949","display_name":"Huiqun Yu","orcid":"https://orcid.org/0000-0002-1899-1135"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiqun Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai"],"raw_orcid":"https://orcid.org/0000-0002-1899-1135","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":8.693,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.96909254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"17","issue":"4","first_page":"976","last_page":"986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7757999897003174,"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":0.7757999897003174,"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/computer-science","display_name":"Computer science","score":0.7657357454299927},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7228091359138489},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6025348901748657},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.514500617980957},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3217991590499878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25632795691490173},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12993785738945007},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09647342562675476},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0853574275970459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657357454299927},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7228091359138489},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6025348901748657},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.514500617980957},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3217991590499878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25632795691490173},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12993785738945007},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09647342562675476},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0853574275970459},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3533744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3533744","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G686699220","display_name":null,"funder_award_id":"62276097","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2291649624","https://openalex.org/W2617547828","https://openalex.org/W2968526727","https://openalex.org/W3093528669","https://openalex.org/W3098094428","https://openalex.org/W3134671698","https://openalex.org/W3173294282","https://openalex.org/W3177920269","https://openalex.org/W3185083385","https://openalex.org/W3195968524","https://openalex.org/W3201315469","https://openalex.org/W3201466613","https://openalex.org/W3205848726","https://openalex.org/W3211667558","https://openalex.org/W3212907084","https://openalex.org/W4213190850","https://openalex.org/W4250589301","https://openalex.org/W4307958658","https://openalex.org/W4315649305","https://openalex.org/W4318821241","https://openalex.org/W4327571609","https://openalex.org/W4367595583","https://openalex.org/W4383892299","https://openalex.org/W4384207043","https://openalex.org/W4385245566","https://openalex.org/W4386918877","https://openalex.org/W6638018090","https://openalex.org/W6737893269","https://openalex.org/W6738796088","https://openalex.org/W6771280675","https://openalex.org/W6779109570","https://openalex.org/W6788898170","https://openalex.org/W6790978476","https://openalex.org/W6795908048","https://openalex.org/W6796289742","https://openalex.org/W6800682094","https://openalex.org/W6802002411","https://openalex.org/W6810738896","https://openalex.org/W6840380725","https://openalex.org/W6843754643","https://openalex.org/W6853465110","https://openalex.org/W6854030435","https://openalex.org/W6858013149"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Safety":[0],"remains":[1],"a":[2,71,118,159],"crucial":[3],"challenge":[4],"in":[5,55,125,162,168],"the":[6,32,51,59,92,98,105,138,172],"application":[7],"of":[8,35,53],"reinforcement":[9,13,74],"learning.":[10],"Multiagent":[11],"safe":[12,23,73,139],"learning":[14,75],"(MASRL)":[15],"is":[16,41,85,115],"an":[17,88,165],"emerging":[18],"field":[19],"aiming":[20],"to":[21,180],"learn":[22],"control":[24],"policies":[25],"that":[26,145],"maximize":[27],"cumulative":[28],"rewards":[29,163],"while":[30,129],"satisfying":[31],"safety":[33,156,169],"constraints":[34],"multiagent":[36,72,99,140],"systems.":[37],"However,":[38],"existing":[39],"research":[40],"limited":[42],"and":[43,50,63,109,155,164],"faces":[44],"challenges":[45],"such":[46],"as":[47],"environmental":[48],"nonstationarity":[49],"curse":[52],"dimensionality":[54],"action":[56],"spaces,":[57],"hindering":[58],"balance":[60],"between":[61,107],"performance":[62,176],"safety.":[64],"To":[65],"address":[66],"these,":[67],"this":[68],"article":[69],"proposes":[70],"algorithm":[76],"based":[77],"on":[78,137],"Transformer":[79],"(MAST).":[80],"The":[81],"constrained":[82],"optimization":[83],"problem":[84],"transformed":[86],"into":[87],"unconstrained":[89],"one":[90],"using":[91],"Lagrangian":[93],"method.":[94],"We":[95],"also":[96],"propose":[97],"total":[100],"advantage":[101],"decomposition":[102],"theorem,":[103],"establishing":[104],"connection":[106],"MASRL":[108],"sequence":[110],"models.":[111],"A":[112],"Transformer-based":[113,119,173],"framework":[114],"proposed,":[116],"where":[117],"actor":[120,174],"network":[121],"generates":[122],"joint":[123],"actions":[124,131],"parallel":[126],"during":[127,133],"training":[128],"producing":[130],"autoregressively":[132],"inference.":[134],"Empirical":[135],"evaluations":[136],"MuJoCo":[141],"(MAMuJoCo)":[142],"benchmark":[143],"show":[144],"MAST":[146],"outperforms":[147],"state-of-the-art":[148],"algorithms":[149],"by":[150,177],"13.06%.":[151],"Our":[152],"attention-based":[153],"reward":[154],"critics":[157],"achieve":[158],"22.10%":[160],"increase":[161],"83.58%":[166],"reduction":[167],"costs.":[170],"Additionally,":[171],"improves":[175],"53.60%\u2013111.93%":[178],"compared":[179],"RNN-based":[181],"methods.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}