{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:53:22Z","timestamp":1729666402905,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,9]]},"DOI":"10.1109\/isic.2010.5612911","type":"proceedings-article","created":{"date-parts":[[2010,11,10]],"date-time":"2010-11-10T11:37:51Z","timestamp":1289389071000},"page":"789-794","source":"Crossref","is-referenced-by-count":5,"title":["Convergence of multiagent Q-learning: Multi action replay process approach"],"prefix":"10.1109","author":[{"given":"Han-Eol","family":"Kim","sequence":"first","affiliation":[]},{"given":"Hyo-Sung","family":"Ahn","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"746","article-title":"The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems","author":"claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref3","first-page":"310","article-title":"A Generalized Reinforcement-Learning Model: Convergence and Applications","author":"littman","year":"1996","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-9352-8","article-title":"Stochastic approximation methods for constrained and unconstrained systems","author":"kushner","year":"1978"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1073\/pnas.36.1.48","article-title":"Equilibrium points in n-person games","volume":"36","author":"john","year":"1950","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref5","first-page":"242","article-title":"Correlated-Q learning","author":"greenwald","year":"2003","journal-title":"AAAI Spring Symp"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016070"},{"key":"ref9","article-title":"Multi-agent Reinforcement Learning: a Critical Survey","author":"shoham","year":"2004","journal-title":"Technical Report"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"}],"event":{"name":"Control (MSC)","start":{"date-parts":[[2010,9,8]]},"location":"Yokohama, Japan","end":{"date-parts":[[2010,9,10]]}},"container-title":["2010 IEEE International Symposium on Intelligent Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5604772\/5612700\/05612911.pdf?arnumber=5612911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T11:59:47Z","timestamp":1497873587000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5612911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,9]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/isic.2010.5612911","relation":{},"subject":[],"published":{"date-parts":[[2010,9]]}}}