{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:51:00Z","timestamp":1785603060705,"version":"3.56.0"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540749578","type":"print"},{"value":"9783540749585","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-74958-5_41","type":"book-chapter","created":{"date-parts":[[2007,9,7]],"date-time":"2007-09-07T16:33:00Z","timestamp":1189182780000},"page":"442-453","source":"Crossref","is-referenced-by-count":14,"title":["Planning and Learning in Environments with Delayed Feedback"],"prefix":"10.1007","author":[{"given":"Thomas J.","family":"Walsh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Nouri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"41_CR1","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, MA (1998)"},{"key":"41_CR2","first-page":"193","volume-title":"Proc. 1992 ACM SIGMETRICS and PERFORMANCE","author":"E. Altman","year":"1992","unstructured":"Altman, E., Nain, P.: Closed-loop control with delayed information. In: Proc. 1992 ACM SIGMETRICS and PERFORMANCE, 1-5 1992, pp. 193\u2013204. ACM Press, New York (1992)"},{"issue":"4","key":"41_CR3","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1287\/opre.20.4.904","volume":"20","author":"D.M. Brooks","year":"1972","unstructured":"Brooks, D.M., Leondes, C.T.: Markov decision processes with state-information lag. Operations Research\u00a020(4), 904\u2013907 (1972)","journal-title":"Operations Research"},{"key":"41_CR4","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1109\/TAC.2003.809799","volume":"48","author":"K.V. Katsikopoulos","year":"2003","unstructured":"Katsikopoulos, K.V., Engelbrecht, S.E.: Markov decision processes with delays and asynchronous cost collection. IEEE Transactions on Automatic Control\u00a048, 568\u2013574 (2003)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"41_CR5","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 2nd edn., vol.\u00a01\/2. Athena Scientific (2001)"},{"key":"41_CR6","doi-asserted-by":"publisher","first-page":"660","DOI":"10.2307\/3010623","volume":"50","author":"J.L. Bander","year":"1999","unstructured":"Bander, J.L., White III, C.C.: Markov decision processes with noise-corrupted and delayed state observations. The Journal of the Operational Research Society\u00a050, 660\u2013668 (1999)","journal-title":"The Journal of the Operational Research Society"},{"key":"41_CR7","doi-asserted-by":"crossref","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. Wiley, New York (1994)"},{"key":"41_CR8","unstructured":"Loch, J., Singh, S.: Using eligibility traces to find the best memoryless policy in partially observable Markov decision processes. In: ICML, pp. 323\u2013331 (1998)"},{"key":"41_CR9","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1162\/153244303765208377","volume":"3","author":"R.I. Brafman","year":"2002","unstructured":"Brafman, R.I., Tennenholtz, M.: R-max\u2013a general polynomial time algorithm for near-optimal reinforcement learning. Journal of Machine Learning Research\u00a03, 213\u2013231 (2002)","journal-title":"Journal of Machine Learning Research"},{"issue":"1-5","key":"41_CR10","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1023\/A:1006511328852","volume":"11","author":"C.G. Atkeson","year":"1997","unstructured":"Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning for control. Artificial Intelligence Review\u00a011(1-5), 75\u2013113 (1997)","journal-title":"Artificial Intelligence Review"},{"issue":"3","key":"41_CR11","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1287\/moor.12.3.441","volume":"12","author":"C.H. Papadimitriou","year":"1987","unstructured":"Papadimitriou, C.H., Tsitsiklis, J.N.: The complexity of Markov decision processes. Mathematics of Operations Research\u00a012(3), 441\u2013450 (1987)","journal-title":"Mathematics of Operations Research"},{"issue":"3","key":"41_CR12","first-page":"227","volume":"16","author":"S.P. Singh","year":"1994","unstructured":"Singh, S.P., Yee, R.C.: An upper bound on the loss from approximate optimal-value functions. Machine Learning\u00a016(3), 227\u2013233 (1994)","journal-title":"Machine Learning"},{"key":"41_CR13","unstructured":"Littman, M.L.: Algorithms for Sequential Decision Making. PhD thesis, Brown University, Providence, RI (1996)"},{"key":"41_CR14","unstructured":"Munos, R., Moore, A.W.: Rates of convergence for variable resolution schemes in optimal control. In: ICML, pp. 647\u2013654 (2000)"},{"key":"41_CR15","unstructured":"Lin, L.J.: Reinforcement Learning for Robots using Neural Networks. PhD thesis, Carnegie Mellon University, Pittsburgh, PA (1993)"},{"key":"41_CR16","unstructured":"Vijayakumar, S., Schaal, S.: Locally weighted projection regression: An o(n) algorithm for incremental real time learning in high dimensional space. In: ICML, pp. 1079\u20131086 (2000)"},{"key":"41_CR17","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. In: NIPS, pp. 369\u2013376 (1995)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2007"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74958-5_41.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:48:38Z","timestamp":1619520518000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74958-5_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540749578","9783540749585"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74958-5_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[]}}