{"id":"https://openalex.org/W7125951379","doi":"https://doi.org/10.1109/smc58881.2025.11343057","title":"Multiagent Safe Reinforcement Learning by Decentralized Event-Triggered Min-Max Optimization","display_name":"Multiagent Safe Reinforcement Learning by Decentralized Event-Triggered Min-Max Optimization","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125951379","doi":"https://doi.org/10.1109/smc58881.2025.11343057"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5124147188","display_name":"Shunsuke Otani","orcid":null},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shunsuke Otani","raw_affiliation_strings":["The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124132318","display_name":"Naoki Hayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Hayashi","raw_affiliation_strings":["The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124126800","display_name":"Masahiro Inuiguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I14314212","display_name":"Osaka University of Economics","ror":"https://ror.org/04g11bp59","country_code":"JP","type":"education","lineage":["https://openalex.org/I14314212"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Inuiguchi","raw_affiliation_strings":["The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"The University of Osaka,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908","https://openalex.org/I14314212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5124147188"],"corresponding_institution_ids":["https://openalex.org/I14314212","https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87233805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6500","last_page":"6505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.858299970626831,"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":0.858299970626831,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0869000032544136,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.006000000052154064,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8557000160217285},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4832000136375427},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43149998784065247},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8557000160217285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144999861717224},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.569100022315979},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28380000591278076}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5454744100570679,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2044212084","https://openalex.org/W2465405765","https://openalex.org/W2790284998","https://openalex.org/W2908261578","https://openalex.org/W2943547141","https://openalex.org/W2963190258","https://openalex.org/W3097422301","https://openalex.org/W3112462371","https://openalex.org/W3173294282","https://openalex.org/W4312899954","https://openalex.org/W4383899648","https://openalex.org/W4385768131","https://openalex.org/W4391919254","https://openalex.org/W4396676069","https://openalex.org/W4401687337"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"decentralized":[3,57,81],"event-triggered":[4],"reinforcement":[5,45,82],"learning":[6,46],"with":[7],"safety":[8,18,40],"constraints.":[9,41],"Each":[10,61],"agent":[11,62],"has":[12,63],"an":[13],"individual":[14],"reward":[15],"function":[16],"and":[17,54,69],"constraints":[19],"that":[20,99],"depend":[21],"on":[22],"the":[23,33,39,44,66,73,79,84,91,100,116],"joint":[24],"actions":[25],"of":[26,72,102,108],"agents.":[27],"The":[28],"objective":[29],"is":[30],"to":[31,105],"maximize":[32],"team\u2019s":[34],"long-term":[35],"return":[36],"while":[37,113],"satisfying":[38],"We":[42,97],"formulate":[43],"problem":[47,53],"as":[48],"a":[49,56,94,106,109],"nonconvex-concave":[50],"min-max":[51,74],"optimization":[52,75],"propose":[55],"policy":[58],"gradient":[59],"algorithm.":[60],"estimations":[64],"for":[65],"optimal":[67,111],"primal":[68],"dual":[70],"solutions":[71],"problem.":[76],"Different":[77],"from":[78],"existing":[80],"learning,":[83],"agents":[85,103],"share":[86],"these":[87],"estimates":[88,101],"only":[89],"when":[90],"error":[92],"exceeds":[93],"predefined":[95],"threshold.":[96],"show":[98],"converge":[104],"neighborhood":[107],"locally":[110],"solution":[112],"effectively":[114],"reducing":[115],"communication":[117],"overhead.":[118]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}