{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T23:03:29Z","timestamp":1743980609537},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387081"},{"type":"electronic","value":"9783642387098"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40988-2_7","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T10:56:40Z","timestamp":1377687400000},"page":"97-112","source":"Crossref","is-referenced-by-count":5,"title":["Regret Bounds for Reinforcement Learning with Policy Advice"],"prefix":"10.1007","author":[{"given":"Mohammad Gheshlaghi","family":"Azar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Lazaric","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emma","family":"Brunskill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"7_CR1","unstructured":"Bartlett, P.L., Tewari, A.: Regal: A regularization based algorithm for reinforcement learning in weakly communicating mdps. In: UAI, pp. 35\u201342 (2009)"},{"key":"7_CR2","unstructured":"Brunskill, E.: Bayes-optimal reinforcement learning for discrete uncertainty domains. In: Abstract. Proceedings of the International Conference on Autonomous Agents and Multiagent System (2012)"},{"issue":"3","key":"7_CR3","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1145\/258128.258179","volume":"44","author":"N. Cesa-Bianchi","year":"1997","unstructured":"Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D.P., Schapire, R.E., Warmuth, M.K.: How to use expert advice. Journal of the ACM\u00a044(3), 427\u2013485 (1997)","journal-title":"Journal of the ACM"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Diuk, C., Li, L., Leffler, B.R.: The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning. In: ICML (2009)","DOI":"10.1145\/1553374.1553406"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Dyagilev, K., Mannor, S., Shimkin, N.: Efficient reinforcement learning in parameterized models: Discrete parameter case. In: European Workshop on Reinforcement Learning (2008)","DOI":"10.4108\/icst.valuetools.2008.56"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, F., Veloso, M.M.: Probabilistic policy reuse in a reinforcement learning agent. In: AAMAS, pp. 720\u2013727 (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"7_CR7","first-page":"1563","volume":"11","author":"T. Jaksch","year":"2010","unstructured":"Jaksch, T., Ortner, R., Auer, P.: Near-optimal regret bounds for reinforcement learning. Journal of Machine Learning Research\u00a011, 1563\u20131600 (2010)","journal-title":"Journal of Machine Learning Research"},{"key":"7_CR8","unstructured":"Maillard, O., Nguyen, P., Ortner, R., Ryabko, D.: Optimal regret bounds for selecting the state representation in re inforcement learning. In: ICML, JMLR W&CP, Atlanta, USA, vol. 28(1), pp. 543\u2013551 (2013)"},{"key":"7_CR9","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-642-34106-9_19","volume-title":"Algorithmic Learning Theory","author":"R. Ortner","year":"2012","unstructured":"Ortner, R., Ryabko, D., Auer, P., Munos, R.: Regret bounds for restless markov bandits. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS (LNAI), vol.\u00a07568, pp. 214\u2013228. Springer, Heidelberg (2012)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Poupart, P., Vlassis, N., Hoey, J., Regan, K.: An analytic solution to discrete bayesian reinforcement learning. In: ICML (2006)","DOI":"10.1145\/1143844.1143932"},{"key":"7_CR11","unstructured":"Pucci de Farias, D., Megiddo, N.: Exploration-exploitation tradeoffs for experts algorithms in reactive environments. In: Advances in Neural Information Processing Systems\u00a017, pp. 409\u2013416 (2004)"},{"key":"7_CR12","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. John Wiley & Sons, Inc., New York (1994)","edition":"1"},{"key":"7_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"7_CR14","unstructured":"Talvitie, E., Singh, S.: An experts algorithm for transfer learning. In: IJCAI (2007)"},{"issue":"8","key":"7_CR15","doi-asserted-by":"publisher","first-page":"5588","DOI":"10.1109\/TIT.2012.2198613","volume":"58","author":"C. Tekin","year":"2012","unstructured":"Tekin, C., Liu, M.: Online learning of rested and restless bandits. IEEE Transactions on Information Theory\u00a058(8), 5588\u20135611 (2012)","journal-title":"IEEE Transactions on Information Theory"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40988-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T23:41:06Z","timestamp":1558050066000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}