{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:59:09Z","timestamp":1725566349081},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540231059"},{"type":"electronic","value":"9783540301158"}],"license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"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":[[2004]]},"DOI":"10.1007\/978-3-540-30115-8_53","type":"book-chapter","created":{"date-parts":[[2010,9,18]],"date-time":"2010-09-18T03:24:16Z","timestamp":1284780256000},"page":"566-568","source":"Crossref","is-referenced-by-count":0,"title":["Batch Reinforcement Learning with State Importance"],"prefix":"10.1007","author":[{"given":"Lihong","family":"Li","sequence":"first","affiliation":[]},{"given":"Vadim","family":"Bulitko","sequence":"additional","affiliation":[]},{"given":"Russell","family":"Greiner","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Baird, L.: Advantage updating. Technical report, Wright-Patterson Air Force Base (1993)","DOI":"10.21236\/ADA280862"},{"key":"53_CR2","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G., Wang, X.: Batch value function approximation via support vectors. Advances in Neural Information Processing Systems\u00a014 (2002)","DOI":"10.7551\/mitpress\/1120.001.0001"},{"key":"53_CR3","unstructured":"Fan, W., Stolfo, S.J., Zhang, J., Chan, P.K.: AdaCost: Misclassification cost-sensitive boosting. In: Proc. of the 16th Int\u2019l Conf. on Machine Learning (1999)"},{"key":"53_CR4","unstructured":"Fern, A., Yoon, S., Givan, R.: Approximate policy iteration with a policy language bias. Advances in Neural Information Processing Systems\u00a016 (2004)"},{"key":"53_CR5","unstructured":"Kearns, M., Mansour, Y., Ng, A.: Approximate planning in large POMDPs via reusable trajectories. Advances in Neural Information Processing Systems\u00a012 (2000)"},{"key":"53_CR6","unstructured":"Lagoudakis, M., Parr, R.: Reinforcement learning as classification: Leveraging modern classifiers. In: Proc. of the 12th Int\u2019l Conf. on Machine Learning (2003)"},{"key":"53_CR7","unstructured":"Langford, J., Zadrozny, B.: Reducing T-step reinforcement learning to classification. In: Proc. of the Machine Learning Reductions Workshop, Chicago, IL (2003)"},{"key":"53_CR8","unstructured":"Levner, I., Bulitko, V.: Machine learning for adaptive image interpretation. In: Proc. of the 12th Innovative Applications of Artificial Intelligence Conf. (2004)"},{"key":"53_CR9","unstructured":"Li, L.: Focus of attention in reinforcement learning. Master\u2019s thesis, Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada (June 2004)"},{"key":"53_CR10","unstructured":"Ng, A.Y., Jordan, M.: PEGASUS: A policy search method for large MDPs and POMDPs. In: Proc. of the 16th Conf. on Uncertainty in AI (2000)"},{"key":"53_CR11","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 (March 1998)"},{"key":"53_CR12","unstructured":"Yoon, S., Fern, A., Givan, R.: Inductive policy selection for first-order MDPs. In: Proc. of the 18th Conference on Uncertainty in AI (2002)"},{"key":"53_CR13","unstructured":"Zadrozny, B., Langford, J.: Cost-sensitive learning by cost-proportionate example weighting. In: Proc. of the IEEE Int\u2019l Conf. on Data Mining (2003)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2004"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30115-8_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T15:37:59Z","timestamp":1711813079000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30115-8_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540231059","9783540301158"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30115-8_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}