{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:07:10Z","timestamp":1725732430182},"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_8","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T10:56:40Z","timestamp":1377687400000},"page":"113-128","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Multi-step Sample Trajectories for Approximate Value Iteration"],"prefix":"10.1007","author":[{"given":"Robert","family":"Wright","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Loscalzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Dexter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","unstructured":"Antos, A., Munos, R., Szepesv\u00e1ri, C.: Fitted Q-iteration in continuous action-space mdps. In: NIPS (2007)"},{"issue":"5","key":"8_CR2","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B.D. Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst.\u00a057(5), 469\u2013483 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"8_CR3","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. In: Advances in Neural Information Processing Systems 7, pp. 369\u2013376. MIT Press (1995)"},{"key":"8_CR4","first-page":"503","volume":"6","author":"D. Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L., Littman, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research\u00a06, 503\u2013556 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"8_CR5","unstructured":"Kolter, J.Z.Z.: The fixed points of off-policy td. In: Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 24, pp. 2169\u20132177 (2011)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Osentoski, S., Thomas, P.S.: Value function approximation in reinforcement learning using the Fourier basis. In: Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, pp. 380\u2013385 (August 2011)","DOI":"10.1609\/aaai.v25i1.7903"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Mahadevan, S.: Representation discovery in sequential decision making. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. AAAI Press (2010)","DOI":"10.1609\/aaai.v24i1.7766"},{"key":"8_CR8","unstructured":"Munos, R.: Error bounds for approximate value iteration. In: Proceedings of the 20th National Conference on Artificial Intelligence, AAAI 2005, vol.\u00a02, pp. 1006\u20131011. AAAI Press (2005)"},{"key":"8_CR9","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1613\/jair.898","volume":"19","author":"B. Price","year":"2003","unstructured":"Price, B., Boutilier, C.: Accelerating reinforcement learning through implicit imitation. Journal of Artificial Intelligence Research\u00a019, 569\u2013629 (2003)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"8_CR10","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming, vol.\u00a0414. Wiley-Interscience (2009)"},{"key":"8_CR11","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/11564096_32","volume-title":"Machine Learning: ECML 2005","author":"M. Riedmiller","year":"2005","unstructured":"Riedmiller, M.: Neural fitted Q iteration - first experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol.\u00a03720, pp. 317\u2013328. Springer, Heidelberg (2005)"},{"key":"8_CR12","unstructured":"Schaal, S.: Learning from demonstration. In: Advances in Neural Information Processing Systems 9. MIT Press (1997)"},{"issue":"2","key":"8_CR13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1162\/106365602320169811","volume":"10","author":"K.O. Stanley","year":"2002","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation\u00a010(2), 99\u2013127 (2002)","journal-title":"Evolutionary Computation"},{"key":"8_CR14","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning). The MIT Press (March 1998)"},{"key":"8_CR15","first-page":"2133","volume":"10","author":"B. Tanner","year":"2009","unstructured":"Tanner, B., White, A.: RL-Glue: Language-independent software for reinforcement-learning experiments. Journal of Machine Learning Research\u00a010, 2133\u20132136 (2009)","journal-title":"Journal of Machine Learning Research"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T04:36:11Z","timestamp":1688445371000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}