{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T02:07:45Z","timestamp":1725502065851},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540779476"},{"type":"electronic","value":"9783540779490"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-77949-0_3","type":"book-chapter","created":{"date-parts":[[2008,2,8]],"date-time":"2008-02-08T04:01:52Z","timestamp":1202443312000},"page":"27-43","source":"Crossref","is-referenced-by-count":11,"title":["Continuous-State Reinforcement Learning with Fuzzy Approximation"],"prefix":"10.1007","author":[{"given":"Lucian","family":"Bu\u015foniu","sequence":"first","affiliation":[]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[]},{"given":"Bart","family":"De Schutter","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Babu\u0161ka","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_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 (1998)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 2nd edn., vol.\u00a02. Athena Scientific (2001)","DOI":"10.1007\/0-306-48332-7_333"},{"key":"3_CR3","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"3_CR4","unstructured":"Glorennec, P.Y.: Reinforcement learning: An overview. In: ESIT 2000. Proceedings European Symposium on Intelligent Techniques, Aachen, Germany, September 14\u201315, 2000, pp. 17\u201335 (2000)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Horiuchi, T., Fujino, A., Katai, O., Sawaragi, T.: Fuzzy interpolation-based Q-learning with continuous states and actions. In: FUZZ-IEEE 1996. Proceedings 5th IEEE International Conference on Fuzzy Systems, New Orleans, US, September 8\u201311, 1996, pp. 594\u2013600 (1996)","DOI":"10.1109\/FUZZY.1996.551807"},{"issue":"3","key":"3_CR6","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1109\/5326.704563","volume":"28","author":"L. Jouffe","year":"1998","unstructured":"Jouffe, L.: Fuzzy inference system learning by reinforcement methods. IEEE Transactions on Systems, Man, and Cybernetics\u2014Part C: Applications and Reviews\u00a028(3), 338\u2013355 (1998)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics\u2014Part C: Applications and Reviews"},{"issue":"5","key":"3_CR7","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1109\/72.159061","volume":"3","author":"H.R. Berenji","year":"1992","unstructured":"Berenji, H.R., Khedkar, P.: Learning and tuning fuzzy logic controllers through reinforcements. IEEE Transactions on Neural Networks\u00a03(5), 724\u2013740 (1992)","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"4","key":"3_CR8","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/TFUZZ.2003.814834","volume":"11","author":"H.R. Berenji","year":"2003","unstructured":"Berenji, H.R., Vengerov, D.: A convergent actor-critic-based FRL algorithm with application to power management of wireless transmitters. IEEE Transactions on Fuzzy Systems\u00a011(4), 478\u2013485 (2003)","journal-title":"IEEE Transactions on Fuzzy Systems"},{"issue":"4","key":"3_CR9","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/TSMCB.2005.846001","volume":"35","author":"D. Vengerov","year":"2005","unstructured":"Vengerov, D., Bambos, N., Berenji, H.R.: A fuzzy reinforcement learning approach to power control in wireless transmitters. IEEE Transactions on Systems, Man, and Cybernetics\u2014Part B: Cybernetics\u00a035(4), 768\u2013778 (2005)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics\u2014Part B: Cybernetics"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/S0165-0114(02)00299-3","volume":"137","author":"C.K. Lin","year":"2003","unstructured":"Lin, C.K.: A reinforcement learning adaptive fuzzy controller for robots. Fuzzy Sets and Systems\u00a0137, 339\u2013352 (2003)","journal-title":"Fuzzy Sets and Systems"},{"issue":"1\u20133","key":"3_CR11","first-page":"59","volume":"22","author":"J.N. Tsitsiklis","year":"1996","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Feature-based methods for large scale dynamic programming. Machine Learning\u00a022(1\u20133), 59\u201394 (1996)","journal-title":"Machine Learning"},{"key":"3_CR12","unstructured":"Szepesv\u00e1ri, C., Munos, R.: Finite time bounds for sampling based fitted value iteration. In: ICML 2005. Proceedings Twenty-Second International Conference on Machine Learning, Bonn, Germany, August 7\u201311, 2005, pp. 880\u2013887 (2005)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Gordon, G.: Stable function approximation in dynamic programming. In: ICML 1995. Proceedings Twelfth International Conference on Machine Learning, Tahoe City, US, July 9\u201312, 1995, pp. 261\u2013268 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"3_CR14","series-title":"Lecture Notes in Artificial Intelligence","first-page":"477","volume-title":"ECML 2004","author":"M. Wiering","year":"2004","unstructured":"Wiering, M.: Convergence and divergence in standard and averaging reinforcement learning. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol.\u00a03201, pp. 477\u2013488. Springer, Heidelberg (2004)"},{"issue":"2\u20133","key":"3_CR15","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1017928328829","volume":"49","author":"D. Ormoneit","year":"2002","unstructured":"Ormoneit, D., Sen, S.: Kernel-based reinforcement learning. Machine Learning\u00a049(2\u20133), 161\u2013178 (2002)","journal-title":"Machine Learning"},{"key":"3_CR16","first-page":"503","volume":"6","author":"D. Ernst","year":"2005","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research\u00a06, 503\u2013556 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"3_CR17","unstructured":"Szepesv\u00e1ri, C., Smart, W.D.: Interpolation-based Q-learning. In: ICML 2004. Proceedings Twenty-First International Conference on Machine Learning, Bannf, Canada, July 4\u20138, 2004 (2004)"},{"key":"3_CR18","unstructured":"Singh, S.P., Jaakkola, T., Jordan, M.I.: Reinforcement learning with soft state aggregation. In: NIPS 1994. Advances in Neural Information Processing Systems 7, Denver, US, pp. 361\u2013368 (1994)"},{"key":"3_CR19","unstructured":"Ernst, D.: Near Optimal Closed-loop Control. Application to Electric Power Systems. PhD thesis, University of Li\u00e8ge, Belgium (March 2003)"},{"issue":"2-3","key":"3_CR20","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1017992615625","volume":"49","author":"R. Munos","year":"2002","unstructured":"Munos, R., Moore, A.: Variable-resolution discretization in optimal control. Machine Learning\u00a049(2\u20133), 291\u2013323 (2002)","journal-title":"Machine Learning"},{"key":"3_CR21","series-title":"Lecture Notes in Artificial Intelligence","first-page":"194","volume-title":"SARA 2005","author":"A. Sherstov","year":"2005","unstructured":"Sherstov, A., Stone, P.: Function approximation via tile coding: Automating parameter choice. In: Zucker, J.-D., Saitta, L. (eds.) SARA 2005. LNCS (LNAI), vol.\u00a03607, pp. 194\u2013205. Springer, Heidelberg (2005)"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77949-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T11:56:46Z","timestamp":1684238206000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77949-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540779476","9783540779490"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77949-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}