{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:32:07Z","timestamp":1783009927011,"version":"3.54.5"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1109\/adprl.2013.6614986","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T15:29:28Z","timestamp":1410362968000},"page":"31-38","source":"Crossref","is-referenced-by-count":15,"title":["Exponential moving average Q-learning algorithm"],"prefix":"10.1109","author":[{"given":"Mostafa D.","family":"Awheda","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Howard M.","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"17","first-page":"746","article-title":"Multi-agent learning with policy prediction","author":"zhang","year":"2010","journal-title":"Proceedings of the 24th National Conference on Artificial Intelligence (AAAI10)"},{"key":"15","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"16","first-page":"215","article-title":"Extending q-learning to general adaptive multi-agent systems","volume":"16","author":"tesauro","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1006\/ijhc.1997.0157"},{"key":"14","first-page":"541","article-title":"Nash convergence of gradient dynamics in general-sum games","author":"singh","year":"2000","journal-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1039"},{"key":"12","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"2","article-title":"Convergence and no-regret in multiagent learning","volume":"17","author":"bowling","year":"2005","journal-title":"Advances in neural information processing systems"},{"key":"1","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"10","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"Proceedings Fifteenth International Conference on Machine Learning"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2009.04.003"},{"key":"6","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1613\/jair.2628","article-title":"A multiagent reinforcement learning algorithm with non-linear dynamics","volume":"33","author":"abdallah","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345353"},{"key":"9","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-0143-1"}],"event":{"name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Singapore, Singapore","start":{"date-parts":[[2013,4,16]]},"end":{"date-parts":[[2013,4,19]]}},"container-title":["2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6596003\/6614979\/06614986.pdf?arnumber=6614986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,14]],"date-time":"2019-08-14T17:46:06Z","timestamp":1565804766000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6614986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/adprl.2013.6614986","relation":{},"subject":[],"published":{"date-parts":[[2013,4]]}}}