{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T09:54:26Z","timestamp":1760608466739},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540746898"},{"type":"electronic","value":"9783540746904"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-74690-4_12","type":"book-chapter","created":{"date-parts":[[2007,9,13]],"date-time":"2007-09-13T13:03:00Z","timestamp":1189688580000},"page":"109-118","source":"Crossref","is-referenced-by-count":7,"title":["Improving Optimality of Neural Rewards Regression for Data-Efficient Batch Near-Optimal Policy Identification"],"prefix":"10.1007","author":[{"given":"Daniel","family":"Schneega\u00df","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Martinetz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"12_CR1","unstructured":"Schneegass, D., Udluft, S., Martinetz, T.: Neural rewards regression for near-optimal policy identification in markovian and partial observable environments. In: Verleysen, M. (ed.) Proc. of the European Symposium on Artificial Neural Networks, pp. 301\u2013306 (2007)"},{"key":"12_CR2","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/11776420_42","volume-title":"Learning Theory","author":"A. Antos","year":"2006","unstructured":"Antos, A., Szepesv\u00e1ri, C., Munos, R.: Learning near-optimal policies with bellman-residual minimization based fitted policy iteration and a single sample path. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol.\u00a04005, pp. 574\u2013588. Springer, Heidelberg (2006)"},{"key":"12_CR3","unstructured":"Schneegass, D., Udluft, S., Martinetz, T.: Kernel rewards regression: An information efficient batch policy iteration approach. In: Proc. of the IASTED Conference on Artificial Intelligence and Applications, pp. 428\u2013433 (2006)"},{"key":"12_CR4","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":"12_CR5","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., McClelland, J.L., Rumelhart, D.E.: Distributed representations. In: Parallel Distributed Processing, pp. 77\u2013109 (1986)","DOI":"10.7551\/mitpress\/5237.001.0001"},{"key":"12_CR6","volume-title":"Neural Networks : A Comprehensive Foundation","author":"S. Haykin","year":"1994","unstructured":"Haykin, S.: Neural Networks: A Comprehensive Foundation. Macmillan, New York (1994)"},{"key":"12_CR7","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, vol.\u00a012 (2000)"},{"key":"12_CR8","unstructured":"Wang, X., Dietterich, T.: Model-based policy gradient reinforcement learning. In: International Conference on Machine Learning (2003)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Ghavamzadeh, M., Engel, Y.: Bayesian policy gradient algorithms. In: Advances in Neural Information Processing Systems (2006)","DOI":"10.7551\/mitpress\/7503.003.0062"},{"key":"12_CR10","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. Journal of Machine Learning Research, 1107\u20131149 (2003)"},{"key":"12_CR11","unstructured":"Munos, R.: Error bounds for approximate policy iteration. In: Proc. of the International Conference on Machine Learning, pp. 560\u2013567 (2003)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Baird III, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Proc. of the International Conference on Machine Learning, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"issue":"5","key":"12_CR13","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsikilis","year":"1997","unstructured":"Tsitsikilis, J.N., Van Roy, B.: An analysis of temporal difference learning with function approximation. IEEE Transactions on Automatic Control\u00a042(5), 674\u2013690 (1997)","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"5","key":"12_CR14","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1109\/72.410363","volume":"6","author":"B. Pearlmutter","year":"1995","unstructured":"Pearlmutter, B.: Gradient calculations for dynamic recurrent neural networks: A survey. IEEE Transactions on Neural Networks\u00a06(5), 1212\u20131228 (1995)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Baird, L., Klopf, A.: Reinforcement learning with high-dimensional, continuous actions. Technical Report WL-TR-93-1147, Wright Laboratory, Wright-Patterson Air Force Base, OH 45433-7301 (1993)","DOI":"10.21236\/ADA280844"},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S. Geman","year":"1992","unstructured":"Geman, S., Bienenstock, E., Doursat, R.: Neural networks and the bias\/variance dilemma. Neural Computation\u00a04(1), 1\u201358 (1992)","journal-title":"Neural Computation"},{"key":"12_CR17","first-page":"1","volume-title":"ADPRL","author":"S. Timmer","year":"2007","unstructured":"Timmer, S., Riedmiller, M.: Fitted q iteration with cmacs. In: ADPRL. Proceedings of the IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 1\u20138. IEEE Computer Society Press, Los Alamitos (2007)"},{"key":"12_CR18","unstructured":"Tresp, V.: The wet game of chicken. Siemens AG, CT IC 4, Technical Report (1994)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Riedmiller, M.: Neural fitted q-iteration - first experiences with a data efficient neural reinforcement learning method. In: Proceedings of the 16th European Conference on Machine Learning, pp. 317\u2013328 (2005)","DOI":"10.1007\/11564096_32"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Schaefer, A.M., Schneegass, D., Sterzing, V., Udluft, S.: A neural reinforcement learning approach to gas turbine control. In: Proc. of the International Joint Conference on Neural Networks (to appear, 2007)","DOI":"10.1109\/IJCNN.2007.4371212"},{"key":"12_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/3-540-49430-8_18","volume-title":"Neural Networks: Tricks of the Trade","author":"R. Neuneier","year":"1998","unstructured":"Neuneier, R., Zimmermann, H.G.: How to train neural networks. In: Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol.\u00a01524, pp. 373\u2013423. Springer, Heidelberg (1998)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks \u2013 ICANN 2007"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74690-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T21:59:37Z","timestamp":1708207177000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74690-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540746898","9783540746904"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74690-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}