{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:30:21Z","timestamp":1770845421194,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342985","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6506-6511","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Reinforcement Learning with Risk Aversion in Multi-Agent Systems"],"prefix":"10.1109","author":[{"given":"Daichi","family":"Ishikawa","sequence":"first","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"}]},{"given":"Taisei","family":"Ichino","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"}]},{"given":"Naoki","family":"Hayashi","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"}]},{"given":"Masahiro","family":"Inuiguchi","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Toyonaka, Osaka,Japan,560-8531"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2698261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2989281"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3192316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2023.2206501"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2025.3535578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/512"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.02.003"},{"key":"ref10","volume-title":"Reinforcement Learning: An Introduction.","author":"Sutton","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"key":"ref12","first-page":"1522","article-title":"Risk-sensitive and robust decision-making: A cvar optimization approach","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems","author":"Chow"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref14","first-page":"40 425","article-title":"On the global convergence of risk-averse policy gradient methods with expected conditional risk measures","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Yu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17062"},{"key":"ref17","first-page":"138 698","article-title":"Scalable constrained policy optimization for safe multi-agent reinforcement learning","volume":"37","author":"Zhang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Scalable safe multi-agent reinforcement learning for multi-agent system","author":"Du","year":"2025"},{"key":"ref19","first-page":"23 049","article-title":"RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents","volume":"34","author":"Qiu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/ACC60939.2024.10644829"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342985.pdf?arnumber=11342985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:43Z","timestamp":1770843043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342985","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}