{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:13:49Z","timestamp":1752671629622,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/Crown.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9030158","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T00:43:11Z","timestamp":1584060191000},"page":"5556-5561","source":"Crossref","is-referenced-by-count":7,"title":["Reinforcement Learning for Decentralized Stochastic Control"],"prefix":"10.1109","author":[{"given":"Bora","family":"Yongacoglu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gurdal","family":"Arslan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serdar","family":"Yuksel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/070680199"},{"key":"ref11","first-page":"426","article-title":"Learning to coordinate without sharing information","author":"sen","year":"1994","journal-title":"Proceedings of the 12th National Conference on Artificial Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.02.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref16","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","author":"wang","year":"2002","journal-title":"Proceedings of the 15th International Conference on Neural Information Processing Systems NIPS’02"},{"key":"ref17","article-title":"Learning from Delayed Rewards","author":"watkins","year":"1989","journal-title":"PhD thesis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"article-title":"Learning Team-Optimality for Decentralized Stochastic Control and Dynamic Games","year":"2019","author":"yongacoglu","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/1101006"},{"key":"ref3","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proceedings of the Tenth Conference on Artificial Intelligence for Applications"},{"key":"ref6","first-page":"1039","article-title":"Nash Q-learning for generalsum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0729-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref7","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/110852462"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref9","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"littman","year":"2001","journal-title":"ICML"},{"key":"ref20","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","start":{"date-parts":[[2019,12,11]]},"location":"Nice, France","end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09030158.pdf?arnumber=9030158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T16:18:43Z","timestamp":1658247523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9030158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9030158","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}