{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:30:01Z","timestamp":1730262601576,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/ieeeconf44664.2019.9049021","type":"proceedings-article","created":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T05:10:33Z","timestamp":1585631433000},"page":"1744-1749","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Q-Learning with Constant Aspirations in Stochastic Games"],"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":"10.1109\/PROC.1980.11718"},{"key":"ref11","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":"ref12","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume":"98","author":"hu","year":"1998","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2004.01.004"},{"journal-title":"Hybrid Learning in Stochastic Games and Its Application in Network Security","year":"2013","author":"lewis","key":"ref14"},{"key":"ref15","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"littman","year":"2001","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/070680199"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2004.09.012"},{"key":"ref28","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume":"80","author":"zhang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/110852462"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7085-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0899-8256(89)90003-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.05.025"},{"key":"ref5","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":"ref8","first-page":"80","volume":"393","author":"fudenberg","year":"1991","journal-title":"Game Theory 1991"},{"key":"ref7","first-page":"89","article-title":"Equilibrium in a stochastic n-person game","volume":"28","author":"fink","year":"1964","journal-title":"Journal of Science in Hiroshima University Series AI"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0729-0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01206560"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref23","article-title":"Learning from Delayed Rewards","author":"watkins","year":"1989","journal-title":"PhD thesis"},{"article-title":"Learning team-optimality for decentralized stochastic control and dynamic games, 2019","year":"2019","author":"yongacoglu","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030158"}],"event":{"name":"2019 53rd Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2019,11,3]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2019,11,6]]}},"container-title":["2019 53rd Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9034466\/9048648\/09049021.pdf?arnumber=9049021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:48:11Z","timestamp":1658094491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9049021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf44664.2019.9049021","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}