{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T04:04:46Z","timestamp":1749787486547,"version":"3.41.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[1999,4,1]],"date-time":"1999-04-01T00:00:00Z","timestamp":922924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1999,4,1]],"date-time":"1999-04-01T00:00:00Z","timestamp":922924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Processing Letters"],"published-print":{"date-parts":[[1999,4]]},"DOI":"10.1023\/a:1018669223478","type":"journal-article","created":{"date-parts":[[2003,2,19]],"date-time":"2003-02-19T20:24:24Z","timestamp":1045686264000},"page":"119-127","source":"Crossref","is-referenced-by-count":1,"title":["Training Reinforcement Neurocontrollers Using the Polytope Algorithm"],"prefix":"10.1007","volume":"9","author":[{"given":"Aristidis","family":"Likas","sequence":"first","affiliation":[]},{"given":"Isaac E.","family":"Lagaris","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"193642_CR1","unstructured":"C.W. Anderson, Strategy learning with multilayer connectionist representations, Technical Report TR87-509.3, GTE Labs, Waltham, MA."},{"key":"193642_CR2","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/37.24809","volume":"2","author":"C.W. Anderson","year":"1989","unstructured":"C.W. Anderson, \u201cLearning to control an inverted pendulum using neural networks\u201d, IEEE Control Systems Magazine, Vol. 2, pp. 31\u201337, 1989.","journal-title":"IEEE Control Systems Magazine"},{"key":"193642_CR3","first-page":"835","volume":"13","author":"A.G. Barto","year":"1983","unstructured":"A.G. Barto, R.S. Sutton and C.W. Anderson, C.W., \u201cNeuronlike elements that can solve difficult control problems\u201d, IEEE Trans. on Systems,Man and Cybernetics, Vol. 13, pp. 835\u2013846, 1983.","journal-title":"IEEE Trans. on Systems,Man and Cybernetics"},{"key":"193642_CR4","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1109\/72.159061","volume":"3","author":"H.R. Berenji","year":"1992","unstructured":"H.R. Berenji and P. Khedkar, \u201cLearning and tuning fuzzy logic controllers using reinforcements\u201d, IEEE Trans. on Neural Networks, Vol. 3, pp. 724\u2013740, 1992.","journal-title":"IEEE Trans. on Neural Networks"},{"key":"193642_CR5","first-page":"223","volume":"52","author":"C.S. Chassapis","year":"1989","unstructured":"C.S. Chassapis, D.G. Papageorgiou, and I.E. Lagaris, MCL - \u201cOptimization oriented programming language, computer physics communications\u201d, Vol. 52, pp. 223\u2013239, 1989.","journal-title":"MCL - \u201cOptimization oriented programming language, computer physics communications\u201d"},{"key":"193642_CR6","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/0010-4655(87)90094-4","volume":"46","author":"G.A. Evangelakis","year":"1987","unstructured":"G.A. Evangelakis, J.P. Rizos, I.E. Lagaris and I.N. Demetropoulos, Merlin - \u201cA portable system for multidimensional minimization\u201d, Computer Physics Communications, Vol. 46, pp. 402\u2013412, 1987.","journal-title":"Computer Physics Communications"},{"key":"193642_CR7","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/0010-4655(89)90007-6","volume":"52","author":"D.G. Papageorgiou","year":"1989","unstructured":"D.G. Papageorgiou, C.S. Chassapis and I.E. Lagaris, \u201cMERLIN-2.0 - Enhanced and programmable version\u201d, Computer Physics Communications, Vol. 52, pp. 241\u2013247, 1989.","journal-title":"Computer Physics Communications"},{"key":"193642_CR8","unstructured":"P. Gil, W. Murray, and M. Wright, Practical Optimization, Academic Press, 1989."},{"key":"193642_CR9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. Kaelbing","year":"1996","unstructured":"L. Kaelbing, M. Littman and A. Moore, \u201cReinforcement learning: A survey\u201d, Journal of Artificial Intelligence Research, Vol. 4, pp. 237\u2013285, 1996.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"193642_CR10","doi-asserted-by":"crossref","unstructured":"D. Kontoravdis, A. Likas and A. Stafylopatis, \u201cEfficient reinforcement learning strategies for the pole balancing problem\u201d, in M. Marinaro and P. Morasso (eds), Proc. ICANN'94, pp. 659\u2013662, Springer-Verlag, 1994.","DOI":"10.1007\/978-1-4471-2097-1_155"},{"key":"193642_CR11","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1109\/72.501728","volume":"7","author":"C-J. Lin","year":"1996","unstructured":"C-J. Lin and C-T. Lin, \u201cReinforcement learning for an ART-based fuzzy adaptive learning control network\u201d, IEEE Trans. on Neural Networks, Vol. 7, pp. 709\u2013731, 1996.","journal-title":"IEEE Trans. on Neural Networks"},{"key":"193642_CR12","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1093\/comjnl\/7.4.308","volume":"7","author":"J.A. Nelder","year":"1965","unstructured":"J.A. Nelder and R. Mead, \u201cA simplex method for function minimization\u201d, Computer Journal, Vol. 7, pp. 308\u2013313, 1965.","journal-title":"Computer Journal"},{"key":"193642_CR13","unstructured":"S. Nash and A. Sofer, Linear and Nonlinear Programming, McGraw-Hill, 1996."},{"key":"193642_CR14","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1080\/00401706.1962.10490033","volume":"4","author":"W. Spendley","year":"1962","unstructured":"W. Spendley, G. Hext and F. Himsworth, \u201cSequential application of simplex designs in optimization and evolutionary operation\u201d, Technometrics, Vol. 4, pp. 441\u2013461, 1962.","journal-title":"Technometrics"},{"key":"193642_CR15","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"C. Watkins and P. Dayan, \u201cLearning from delayed rewards\u201d,Machine Learning, Vol. 8, pp. 279\u2013292, 1992.","journal-title":"Machine Learning"},{"key":"193642_CR16","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1023\/A:1022674030396","volume":"13","author":"D. Whitley","year":"1993","unstructured":"D. Whitley, S. Dominic, R. Das and C.W. Anderson, \u201cGenetic reinforcement learning for neurocontrol problems\u201d, Machine Learning, Vol. 13, pp. 259\u2013284, 1993.","journal-title":"Machine Learning"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018669223478.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1018669223478\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018669223478.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T09:12:20Z","timestamp":1749719540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1018669223478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,4]]},"references-count":16,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1999,4]]}},"alternative-id":["193642"],"URL":"https:\/\/doi.org\/10.1023\/a:1018669223478","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[1999,4]]}}}