乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T14:05:19Z","timestamp":1745935519108},"reference-count":26,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2010,5,1]],"date-time":"2010-05-01T00:00:00Z","timestamp":1272672000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Automatica"],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1016\/j.automatica.2010.02.006","type":"journal-article","created":{"date-parts":[[2010,3,12]],"date-time":"2010-03-12T07:52:47Z","timestamp":1268380367000},"page":"804-814","source":"Crossref","is-referenced-by-count":49,"title":["Approximate dynamic programming with a fuzzy parameterization"],"prefix":"10.1016","volume":"46","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":"78","reference":[{"key":"10.1016\/j.automatica.2010.02.006_b1","series-title":"Advances in neural information processing systems: Vol. 20","first-page":"9","article-title":"Fitted Q-iteration in continuous action-space MDPs","author":"Antos","year":"2008"},{"issue":"4","key":"10.1016\/j.automatica.2010.02.006_b2","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TFUZZ.2003.814834","article-title":"A convergent actor-critic-based FRL algorithm with application to power management of wireless transmitters","volume":"11","author":"Berenji","year":"2003","journal-title":"IEEE Transactions on Fuzzy Systems"},{"key":"10.1016\/j.automatica.2010.02.006_b3","series-title":"Dynamic programming and optimal control, Vol. 2","author":"Bertsekas","year":"2007"},{"key":"10.1016\/j.automatica.2010.02.006_b4","series-title":"Neuro-dynamic programming","author":"Bertsekas","year":"1996"},{"key":"10.1016\/j.automatica.2010.02.006_b5","series-title":"Neurofuzzy adaptive modeling and control","author":"Brown","year":"1994"},{"key":"10.1016\/j.automatica.2010.02.006_b6","unstructured":"Bu\u015foniu, L., De Schutter, B., & Babu\u0161ka, R. (2006). Decentralized reinforcement learning control of a robotic manipulator. In Proceedings 9th international conference of control, automation, robotics, and vision, ICARCV-06 (pp. 1347\u20131352). Singapore, 5\u20138 December."},{"key":"10.1016\/j.automatica.2010.02.006_b7","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Ernst, D., De Schutter, B., & Babu\u0161ka, R. (2007). Fuzzy approximation for convergent model-based reinforcement learning. In Proceedings 2007 IEEE international conference on fuzzy systems, FUZZ-IEEE-07 (pp. 968\u2013973). London, UK, 23\u201326 July.","DOI":"10.1109\/FUZZY.2007.4295497"},{"key":"10.1016\/j.automatica.2010.02.006_b8","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Ernst, D., De Schutter, B., & Babu\u0161ka, R. (2008a). Consistency of fuzzy model-based reinforcement learning. In Proceedings 2008 IEEE international conference on fuzzy systems, FUZZ-IEEE-08 (pp. 518\u2013524). Hong Kong, 1\u20136 June.","DOI":"10.1109\/FUZZY.2008.4630417"},{"key":"10.1016\/j.automatica.2010.02.006_b9","series-title":"Adaptive agents and multi-agent systems III","first-page":"27","article-title":"Continuous-state reinforcement learning with fuzzy approximation","volume":"Vol. 4865","author":"Bu\u015foniu","year":"2008"},{"issue":"8","key":"10.1016\/j.automatica.2010.02.006_b10","doi-asserted-by":"crossref","first-page":"898","DOI":"10.1109\/9.133184","article-title":"An optimal one-way multigrid algorithm for discrete-time stochastic control","volume":"36","author":"Chow","year":"1991","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/j.automatica.2010.02.006_b11","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"Ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.automatica.2010.02.006_b12","doi-asserted-by":"crossref","unstructured":"Farahmand, A. M., Ghavamzadeh, M., Szepesv\u00e1ri, Cs., & Mannor, S. (2009). Regularized fitted Q-iteration for planning in continuous-space Markovian decision problems. In Proceedings 2009 American control conference, ACC-09(pp. 725\u2013730). St. Louis, US, 10\u201312 June.","DOI":"10.1109\/ACC.2009.5160611"},{"key":"10.1016\/j.automatica.2010.02.006_b13","unstructured":"Glorennec, P. Y. (2000). Reinforcement learning: An overview. In Proceedings European symposium on intelligent techniques, ESIT-00 (pp. 17\u201335). Aachen, Germany, 14\u201315 September."},{"key":"10.1016\/j.automatica.2010.02.006_b14","doi-asserted-by":"crossref","unstructured":"Gordon, G. (1995). Stable function approximation in dynamic programming. In Proceedings 12th international conference on machine learning, ICML-95(pp. 261\u2013268). Tahoe City, US, 9\u201312 July.","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"10.1016\/j.automatica.2010.02.006_b15","doi-asserted-by":"crossref","unstructured":"Horiuchi, T., Fujino, A., Katai, O., & Sawaragi, T. (1996). Fuzzy interpolation-based Q-learning with continuous states and actions. In Proceedings 5th IEEE international conference on fuzzy systems, FUZZ-IEEE-96 (pp. 594\u2013600). New Orleans, US, 8\u201311 September.","DOI":"10.1109\/FUZZY.1996.551807"},{"key":"10.1016\/j.automatica.2010.02.006_b16","series-title":"Fixed point theory: An introduction","author":"Istratescu","year":"2002"},{"issue":"3","key":"10.1016\/j.automatica.2010.02.006_b17","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1109\/5326.704563","article-title":"Fuzzy inference system learning by reinforcement methods","volume":"28","author":"Jouffe","year":"1998","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics\u2014Part C: Applications and Reviews"},{"key":"10.1016\/j.automatica.2010.02.006_b18","series-title":"Foundations of fuzzy systems","author":"Kruse","year":"1994"},{"key":"10.1016\/j.automatica.2010.02.006_b19","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"Lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"10.1016\/j.automatica.2010.02.006_b20","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/S0165-0114(02)00299-3","article-title":"A reinforcement learning adaptive fuzzy controller for robots","volume":"137","author":"Lin","year":"2003","journal-title":"Fuzzy Sets and Systems"},{"issue":"2\u20133","key":"10.1016\/j.automatica.2010.02.006_b21","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1023\/A:1017992615625","article-title":"Variable-resolution discretization in optimal control","volume":"49","author":"Munos","year":"2002","journal-title":"Machine Learning"},{"key":"10.1016\/j.automatica.2010.02.006_b22","first-page":"815","article-title":"Finite time bounds for fitted value iteration","volume":"9","author":"Munos","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"10.1016\/j.automatica.2010.02.006_b23","doi-asserted-by":"crossref","first-page":"409","DOI":"10.2307\/2998564","article-title":"Analysis of a numerical dynamic programming algorithm applied to economic models","volume":"66","author":"Santos","year":"1998","journal-title":"Econometrica"},{"key":"10.1016\/j.automatica.2010.02.006_b24","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"1998"},{"key":"10.1016\/j.automatica.2010.02.006_b25","doi-asserted-by":"crossref","unstructured":"Szepesv\u00e1ri, Cs., & Smart, W. D. (2004). Interpolation-based Q-learning. In Proceedings 21st international conference on machine learning, ICML-04(pp. 791\u2013798). Bannf, Canada, 4\u20138 July.","DOI":"10.1145\/1015330.1015445"},{"issue":"1\u20133","key":"10.1016\/j.automatica.2010.02.006_b26","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/BF00114724","article-title":"Feature-based methods for large scale dynamic programming","volume":"22","author":"Tsitsiklis","year":"1996","journal-title":"Machine Learning"}],"container-title":["Automatica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0005109810000592?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0005109810000592?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,5,26]],"date-time":"2019-05-26T18:42:14Z","timestamp":1558896134000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0005109810000592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2010,5]]}},"alternative-id":["S0005109810000592"],"URL":"https:\/\/doi.org\/10.1016\/j.automatica.2010.02.006","relation":{},"ISSN":["0005-1098"],"issn-type":[{"value":"0005-1098","type":"print"}],"subject":[],"published":{"date-parts":[[2010,5]]}}}