{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:08:39Z","timestamp":1763644119853,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"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":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383194","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"5008-5013","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous Decentralized Q-Learning in Stochastic Games"],"prefix":"10.1109","author":[{"given":"Bora","family":"Yongacoglu","sequence":"first","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G\u00fcrdal","family":"Arslan","sequence":"additional","affiliation":[{"name":"University of Hawaii at Manoa,Department of Electrical Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serdar","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Queen's University,Department of Mathematics and Statistics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"journal-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","year":"2017","author":"Hernandez-Leal","key":"ref2"},{"key":"ref3","first-page":"310","article-title":"A generalized reinforcement-learning model: Convergence and applications","volume":"96","author":"Littman","year":"1996","journal-title":"ICML"},{"key":"ref4","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"Littman","year":"2001","journal-title":"ICML"},{"key":"ref5","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"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":"ref8","first-page":"18320","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3121228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/22m1515112"},{"journal-title":"Asynchronous decentral-ized Q-learning: Two timescale analysis by persistence","year":"2023","author":"Yongacoglu","key":"ref11"},{"key":"ref12","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multi agent systems","volume-title":"Proceedings of the Tenth Innovative Applications of Artificial Intelligence Conference, Madison, Wisconsin","author":"Claus","year":"1998"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/s0269888912000057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4171\/icm2022\/152"},{"journal-title":"Dealing with non-stationarity in de-centralized cooperative multi -agent deep reinforcement learning via multi-timescale learning","year":"2023","author":"Nekoei","key":"ref15"},{"key":"ref16","first-page":"341","article-title":"Regret testing: Learning to play Nash equilibrium without knowing you have an opponent","volume":"1","author":"Foster","year":"2006","journal-title":"Theoretical Economics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2006.06.001"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/070680199"},{"journal-title":"Independent and decentralized learning in markov potential games","year":"2022","author":"Maheshwari","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.32917\/hmj\/1206139508"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199269181.001.0001"},{"key":"ref22","first-page":"7688","article-title":"Learning in nonzero-sum stochastic games with potentials","volume-title":"International Conference on Machine Learning","author":"Mguni","year":"2021"},{"journal-title":"Global con-vergence of multi-agent policy gradient in Markov potential games","year":"2021","author":"Leonardos","key":"ref23"},{"journal-title":"Gradient play in multi-agent Markov stochastic games: Stationary points and convergence","year":"2021","author":"Zhang","key":"ref24"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383194.pdf?arnumber=10383194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:34:06Z","timestamp":1706027646000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383194","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}