{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:21:46Z","timestamp":1730208106986,"version":"3.28.0"},"reference-count":9,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,7]]},"DOI":"10.1109\/cit.2008.4594682","type":"proceedings-article","created":{"date-parts":[[2008,8,13]],"date-time":"2008-08-13T18:40:13Z","timestamp":1218652813000},"page":"249-254","source":"Crossref","is-referenced-by-count":0,"title":["Learn adaptive dynamic policy under mixed multi-agent environment"],"prefix":"10.1109","author":[{"family":"Zheng Xiao","sequence":"first","affiliation":[]},{"family":"Shiyong Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"3","first-page":"322","article-title":"friend or foe q-learning in general-sum markov games","author":"littman","year":"2001","journal-title":"18th Int Conf on Machine Learning"},{"key":"2","first-page":"242","article-title":"multi-agent reinforcement learning: theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"15th Int Conf on Machine Learning"},{"year":"0","key":"1"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.3166\/ria.20.383-410"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"5","first-page":"541","article-title":"nash convergence of gradient dynamics in general-sum games","author":"singh","year":"2000","journal-title":"Proc Conf Uncertainty Artificial Intelligence"},{"key":"4","first-page":"242","article-title":"correlated q-learning","author":"greenwald","year":"2003","journal-title":"Proc of the 20 th Int Conf on Machine Learning"},{"journal-title":"Multiagent Learning in Adaptive Dynamic Systems Autonomous Agent and Multi-Agent System (AAMAS)","year":"0","author":"burkov","key":"9"},{"key":"8","volume":"16","author":"tesauro","year":"2004","journal-title":"Extending Q-learning to general adaptive multi-agent systems"}],"event":{"name":"2008 8th IEEE International Conference on Computer and Information Technology (CIT)","start":{"date-parts":[[2008,7,8]]},"location":"Sydney, Australia","end":{"date-parts":[[2008,7,11]]}},"container-title":["2008 8th IEEE International Conference on Computer and Information Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4586225\/4594630\/04594682.pdf?arnumber=4594682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T16:33:01Z","timestamp":1489681981000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4594682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,7]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/cit.2008.4594682","relation":{},"subject":[],"published":{"date-parts":[[2008,7]]}}}