{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:55:13Z","timestamp":1767138913230,"version":"build-2238731810"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319388830","type":"print"},{"value":"9783319388847","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-38884-7_4","type":"book-chapter","created":{"date-parts":[[2016,4,22]],"date-time":"2016-04-22T06:23:15Z","timestamp":1461306195000},"page":"43-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Solving an Infinite-Horizon Discounted Markov Decision Process by DC Programming and DCA"],"prefix":"10.1007","author":[{"given":"Vinh Thanh","family":"Ho","sequence":"first","affiliation":[]},{"given":"Hoai An","family":"Le Thi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,23]]},"reference":[{"issue":"3","key":"4_CR1","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1057\/jors.1995.50","volume":"46","author":"T Archibald","year":"1995","unstructured":"Archibald, T., McKinnon, K., Thomas, L.: On the generation of markov decision processes. J. Oper. Res. Soc. 46(3), 354\u2013361 (1995)","journal-title":"J. Oper. Res. Soc."},{"key":"4_CR2","volume-title":"Dynamic Programming","author":"RE Bellman","year":"1957","unstructured":"Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"4_CR3","volume-title":"Dynamic Programming: Deterministic and Stochastic Models","year":"1987","unstructured":"Bertsekas, D.P. (ed.): Dynamic Programming: Deterministic and Stochastic Models. Prentice-Hall Inc, Upper Saddle River (1987)"},{"key":"4_CR4","volume-title":"Introduction to Reinforcement Learning","year":"1998","unstructured":"Bertsekas, D.P. (ed.): Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"4_CR5","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N. (eds.): Neuro-Dynamic Programming. Athena Scientific (1996)"},{"key":"4_CR6","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/3-540-48317-9_5","volume-title":"Artificial Intelligence Today","author":"Craig Boutilier","year":"1999","unstructured":"Boutilier, C.: Knowledge representation for stochastic decision processes. In: Wooldridge, M.J., Veloso, M. (eds.) Artificial Intelligence Today, Lecture Notes in Computer Science, vol. 1600, pp. 111\u2013152. Springer, Berlin (1999). http:\/\/dx.doi.org\/10.1007\/3-540-48317-9_5"},{"key":"4_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.575","volume":"11","author":"C Boutilier","year":"1999","unstructured":"Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: structural assumptions and computational leverage. J. Artif. Intell. Res. 11, 1\u201394 (1999)","journal-title":"J. Artif. Intell. Res."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Vasconcelos, N., Lanckriet, G.R.G.: Direct convex relaxations of sparse svm. In: Langley, P. (ed.) Proceedings of the 24th International Conference on Machine Learning, pp. 145\u2013153. ACM, New York, NY, USA (2007)","DOI":"10.1145\/1273496.1273515"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Collobert, R., Sinz, F.H., Weston, J., Bottou, L.: Trading convexity for scalability. In: ICML. pp. 201\u2013208 (2006)","DOI":"10.1145\/1143844.1143870"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"4_CR11","unstructured":"Klein, E., Geist, M., Piot, B., Pietquin, O.: Inverse reinforcement learning through structured classification. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems 25, pp. 1007\u20131015. Curran Associates, Inc. (2012)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Krause, N., Singer, Y.: Leveraging the margin more carefully. In: ICML\u201904: Proceedings of the twenty-first international conference on Machine learning. pp. 63. ACM Press, New York, NY, USA (2004)","DOI":"10.1145\/1015330.1015344"},{"key":"4_CR13","unstructured":"Le Thi, H.A.: DC programming and DCA (2012). http:\/\/www.lita.univ-lorraine.fr\/~lethi"},{"issue":"1","key":"4_CR14","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s10957-012-0197-0","volume":"161","author":"HA Le Thi","year":"2014","unstructured":"Le Thi, H.A., Moeini, M.: Long-short portfolio optimization under cardinality constraints by difference of convex functions algorithm. J. Optim. Theory Appl. 161(1), 199\u2013224 (2014)","journal-title":"J. Optim. Theory Appl."},{"issue":"3","key":"4_CR15","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1023\/A:1008288411710","volume":"11","author":"HA Le Thi","year":"1997","unstructured":"Le Thi, H.A., Pham Dinh, T.: Solving a class of linearly constrained indefinite quadratic problems by D.C. algorithms. J. Glob. Optim. 11(3), 253\u2013285 (1997)","journal-title":"J. Glob. Optim."},{"issue":"1\u20134","key":"4_CR16","first-page":"23","volume":"133","author":"HA Le Thi","year":"2005","unstructured":"Le Thi, H.A., Pham Dinh, T.: The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems. Ann. Oper. Res. 133(1\u20134), 23\u201346 (2005)","journal-title":"Ann. Oper. Res."},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Le Thi, H.A., Vo, X.T., Pham Dinh, T.: Robust Feature Selection for SVMs under Uncertain Data. In: Perner, P. (ed.) Advances in Data Mining. Applications and Theoretical Aspects, pp. 151\u2013165. Springer, Berlin (2013)","DOI":"10.1007\/978-3-642-39736-3_12"},{"issue":"1","key":"4_CR18","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.ejor.2014.11.031","volume":"244","author":"H Le Thi","year":"2015","unstructured":"Le Thi, H., Pham Dinh, T., Le, H., Vo, X.: Dc approximation approaches for sparse optimization. Eur. J. Oper. Res. 244(1), 26\u201346 (2015)","journal-title":"Eur. J. Oper. Res."},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Le Thi, H.A., Le, H.M., Pham Dinh, T.: Feature selection in machine learning: an exact penalty approach using a difference of convex function algorithm. Mach. Learn. 101(1\u20133), 163\u2013186 (2015)","DOI":"10.1007\/s10994-014-5455-y"},{"issue":"12","key":"4_CR20","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1162\/NECO_a_00673","volume":"26","author":"HA Le Thi","year":"2014","unstructured":"Le Thi, H.A., Nguyen, M.C., Pham Dinh, T.: A dc programming approach for finding communities in networks. Neural Comput. 26(12), 2827\u20132854 (2014)","journal-title":"Neural Comput."},{"key":"4_CR21","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.neunet.2014.06.011","volume":"59","author":"HA Le Thi","year":"2014","unstructured":"Le Thi, H.A., Vo, X.T., Pham Dinh, T.: Feature selection for linear SVMs under uncertain data: Robust optimization based on difference of convex functions algorithms. Neural Netw. 59, 36\u201350 (2014)","journal-title":"Neural Netw."},{"issue":"5\u20136","key":"4_CR22","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1007\/s10618-014-0369-7","volume":"28","author":"H Le Thi","year":"2014","unstructured":"Le Thi, H., Nguyen, M.: Self-organizing maps by difference of convex functions optimization. Data Min. Knowl. Discov. 28(5\u20136), 1336\u20131365 (2014)","journal-title":"Data Min. Knowl. Discov."},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Munos, R.: Performance bounds in $$L_p$$ norm for approximate value iteration. SIAM J. Control Optim. (2007)","DOI":"10.1137\/040614384"},{"issue":"8","key":"4_CR24","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1109\/TAC.2014.2301575","volume":"59","author":"Tao Pham Dinh","year":"2014","unstructured":"Pham Dinh, T., Le, H.M., Le Thi, H.A., Lauer, F.: A difference of convex functions algorithm for switched linear regression. IEEE Trans. Autom. Control 59(8), 2277\u20132282 (2014)","journal-title":"IEEE Transactions on Automatic Control"},{"issue":"1","key":"4_CR25","first-page":"289","volume":"22","author":"T Pham Dinh","year":"1997","unstructured":"Pham Dinh, T., Le Thi, H.A.: Convex analysis approach to d.c. programming: theory, algorithms and applications. Acta Math. Vietnam. 22(1), 289\u2013355 (1997)","journal-title":"Acta Math. Vietnam."},{"issue":"2","key":"4_CR26","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1137\/S1052623494274313","volume":"8","author":"T Pham Dinh","year":"1998","unstructured":"Pham Dinh, T., Le Thi, H.A.: DC optimization algorithms for solving the trust region subproblem. SIAM J. Optim. 8(2), 476\u2013505 (1998)","journal-title":"SIAM J. Optim."},{"key":"4_CR27","first-page":"1","volume-title":"Transactions on Computational Intelligence XIII","author":"Tao Pham Dinh","year":"2014","unstructured":"Pham Dinh, T., Le Thi, H.A.: Recent advances in DC programming and DCA. In: Nguyen, N.T., Le Thi, H.A. (eds.) Transactions on Computational Intelligence XIII, vol. 8342, pp. 1\u201337. Springer, Berlin (2014)"},{"key":"4_CR28","unstructured":"Piot, B., Geist, M., Pietquin, O.: Difference of convex functions programming for reinforcement learning. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 2519\u20132527. Curran Associates, Inc. (2014)"},{"key":"4_CR29","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","year":"1994","unstructured":"Puterman, M.L. (ed.): Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York (1994)"},{"key":"4_CR30","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.dam.2005.02.028","volume":"151","author":"T Sch\u00fcle","year":"2005","unstructured":"Sch\u00fcle, T., Schn\u00f6rr, C., Weber, S., Hornegger, J.: Discrete tomography by convex-concave regularization and d.c. programming. Discret. Appl. Math. 151, 229\u2013243 (2005)","journal-title":"Discret. Appl. Math."},{"key":"4_CR31","unstructured":"Sigaud, O., Buffet, O. (eds.): Markov Decision Processes in Artificial Intelligence. Wiley, IEEE Press (2010)"},{"key":"4_CR32","unstructured":"Yin, P., Lou, Y., He, Q., Xin, J.: Minimization of $$L_1-L_2$$ for compressed sensing. SIAM J. Sci. Comput. (to appear)"}],"updated-by":[{"DOI":"10.1007\/978-3-319-38884-7_21","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2019,12,11]],"date-time":"2019-12-11T00:00:00Z","timestamp":1576022400000}}],"container-title":["Advances in Intelligent Systems and Computing","Advanced Computational Methods for Knowledge Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-38884-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T08:04:28Z","timestamp":1697875468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-38884-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319388830","9783319388847"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-38884-7_4","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"value":"2194-5357","type":"print"},{"value":"2194-5365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"23 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"11 December 2019","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"In the original version of the book, the following belated corrections are to be incorporated.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}