{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:24:24Z","timestamp":1781587464581,"version":"3.54.5"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"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":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10155828","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"72-77","source":"Crossref","is-referenced-by-count":5,"title":["Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games"],"prefix":"10.23919","author":[{"given":"Awni","family":"Altabaa","sequence":"first","affiliation":[{"name":"Yale University,Department of Statistics and Data Science,New Haven,CT,United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bora","family":"Yongacoglu","sequence":"additional","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serdar","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics,Kingston,ON,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Convergence of finite memory Q-learning for POMDPs and near optimality of learned policies under filter stability","author":"kara","year":"2021"},{"key":"ref12","article-title":"Q-learning for MDPs with general spaces: Convergence and near optimality via quantization under weak continuity","author":"kara","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/18M1221382"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551232"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2016.0832"},{"key":"ref10","first-page":"341","article-title":"Regret testing: learning to play Nash equilibrium without knowing you have an opponent","author":"foster","year":"2006","journal-title":"Theoretical Economics"},{"key":"ref2","article-title":"Decentralized multiagent reinforcement learning for continuous-space stochastic games","author":"altabaa","year":"2023","journal-title":"Available on ArXiv"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2613902"},{"key":"ref8","article-title":"Satisficing paths and independent multi-agent reinforcement learning in stochastic games","author":"yongacoglu","year":"2021"},{"key":"ref7","first-page":"5527","article-title":"Independent policy gradient methods for competitive reinforcement learning","volume":"33","author":"daskalakis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3121228"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2010-0206"},{"key":"ref3","first-page":"2","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref6","first-page":"18 320","article-title":"Decentralized Q-learning in zero-sum Markov games","volume":"34","author":"sayin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Independent learning in stochastic games","author":"ozdaglar","year":"2021"}],"event":{"name":"2023 American Control Conference (ACC)","location":"San Diego, CA, USA","start":{"date-parts":[[2023,5,31]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10155828.pdf?arnumber=10155828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:30:42Z","timestamp":1690219842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":16,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10155828","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}