{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:19:53Z","timestamp":1729642793781,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,8]]},"DOI":"10.1109\/coase.2009.5234189","type":"proceedings-article","created":{"date-parts":[[2009,9,11]],"date-time":"2009-09-11T18:10:59Z","timestamp":1252692659000},"page":"627-634","source":"Crossref","is-referenced-by-count":1,"title":["Customized learning algorithms for episodic tasks with acyclic state spaces"],"prefix":"10.1109","author":[{"given":"Theologos","family":"Bountourelis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spyros","family":"Reveliotis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning","year":"2000","author":"sutton","key":"17"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"18"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-007-0014-3"},{"journal-title":"Introduction to Probability Models","year":"2007","author":"ross","key":"16"},{"key":"13","article-title":"markov decision processes","author":"puterman","year":"1994","journal-title":"Wiley Inter-Science"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1080\/07408170600897536"},{"key":"11","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3897.001.0001","author":"kearns","year":"1994","journal-title":"An Introduction to Computational Learning Theory"},{"key":"12","article-title":"selecting the best system","author":"kim","year":"2004","journal-title":"Technical Report"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/WODES.2006.382394"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"2"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"7","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1145\/180139.181019","article-title":"efficient reinforcement learning","author":"fiechter","year":"1994","journal-title":"Proceedings of COLT'94"},{"key":"6","first-page":"1079","article-title":"action elimination and stopping conditions for the mutli-armed bandit and reinforcement learning problems","volume":"7","author":"even-dar","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2006932"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/WODES.2008.4605930"},{"key":"9","first-page":"996","article-title":"finite-sample convergence rates for q-learning and indirect algorithms","volume":"11","author":"kearns","year":"1999","journal-title":"Neural Information Processing Systems"},{"key":"8","first-page":"116","article-title":"expected mistake bound model for on-line reinforcement learning","author":"fiechter","year":"1997","journal-title":"Proceedings of ICML'97"}],"event":{"name":"2009 IEEE International Conference on Automation Science and Engineering (CASE 2009)","start":{"date-parts":[[2009,8,22]]},"location":"Bangalore, India","end":{"date-parts":[[2009,8,25]]}},"container-title":["2009 IEEE International Conference on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5227795\/5234081\/05234189.pdf?arnumber=5234189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,22]],"date-time":"2019-05-22T14:20:31Z","timestamp":1558534831000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5234189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/coase.2009.5234189","relation":{},"subject":[],"published":{"date-parts":[[2009,8]]}}}