{"id":"https://openalex.org/W7125924841","doi":"https://doi.org/10.1109/smc58881.2025.11342985","title":"Decentralized Reinforcement Learning with Risk Aversion in Multi-Agent Systems","display_name":"Decentralized Reinforcement Learning with Risk Aversion in Multi-Agent Systems","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125924841","doi":"https://doi.org/10.1109/smc58881.2025.11342985"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342985","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/A5069949127","display_name":"Daichi ISHIKAWA","orcid":null},"institutions":[{"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":"Daichi Ishikawa","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124139207","display_name":"Taisei Ichino","orcid":null},"institutions":[{"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":"Taisei Ichino","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124085196","display_name":"Naoki Hayashi","orcid":null},"institutions":[{"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":["Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124094475","display_name":"Masahiro Inuiguchi","orcid":null},"institutions":[{"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":["Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"],"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069949127"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87174795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6506","last_page":"6511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8359000086784363,"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":0.8359000086784363,"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":0.06769999861717224,"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/T11031","display_name":"Game Theory and Applications","score":0.014399999752640724,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9089000225067139},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6032000184059143},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.47999998927116394},{"id":"https://openalex.org/keywords/risk-aversion","display_name":"Risk aversion (psychology)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.34209999442100525},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.33550000190734863}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9089000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6496000289916992},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C129915516","wikidata":"https://www.wikidata.org/wiki/Q17083550","display_name":"Risk aversion (psychology)","level":3,"score":0.4433000087738037},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4092000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C92424840","wikidata":"https://www.wikidata.org/wiki/Q7912772","display_name":"Value of information","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342985","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.43288400769233704}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1647779468","https://openalex.org/W2044212084","https://openalex.org/W2114791779","https://openalex.org/W2763533254","https://openalex.org/W2908261578","https://openalex.org/W2962771678","https://openalex.org/W2963304272","https://openalex.org/W3020195588","https://openalex.org/W3173294282","https://openalex.org/W4285820933","https://openalex.org/W4367292773","https://openalex.org/W4385768131","https://openalex.org/W4391919254","https://openalex.org/W4392114294","https://openalex.org/W4402261074","https://openalex.org/W4402402057","https://openalex.org/W4406921732"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"risk-averse":[3,36,56],"distributed":[4,57],"reinforcement":[5,26,37,58],"learning":[6,38,59],"in":[7,20,108],"multi-agent":[8],"systems,":[9],"where":[10],"agents":[11,69,95],"collaboratively":[12,71],"optimize":[13],"their":[14,73,97],"policies":[15,74],"with":[16,125],"a":[17,55,79,83,109,112],"risk":[18],"index":[19],"the":[21,30,34,63,89,104],"objective":[22],"function.":[23],"Unlike":[24],"conventional":[25],"learning,":[27],"which":[28,67,116],"maximizes":[29],"expected":[31],"cumulative":[32],"reward,":[33],"proposed":[35,90],"incorporates":[39],"Conditional":[40],"Value":[41],"at":[42],"Risk":[43],"(CVaR)":[44],"to":[45,70],"account":[46],"for":[47],"rare":[48],"but":[49],"significant":[50],"adverse":[51],"events.":[52],"We":[53],"propose":[54],"algorithm":[60,91],"based":[61],"on":[62,96],"policy":[64,122],"gradient":[65],"method,":[66],"enables":[68],"update":[72],"by":[75],"sharing":[76],"information":[77],"through":[78],"communication":[80],"network.":[81],"Through":[82],"theoretical":[84],"analysis,":[85],"we":[86,101],"show":[87,102],"that":[88,103,118],"ensures":[92,117],"agreement":[93],"among":[94],"estimated":[98],"policies.":[99],"Moreover,":[100],"consensus":[105],"value":[106],"converges":[107],"neighborhood":[110],"of":[111],"locally":[113],"optimal":[114],"solution,":[115],"each":[119],"agent\u2019s":[120],"learned":[121],"remains":[123],"aligned":[124],"risk-aware":[126],"optimization":[127],"criteria.":[128]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}