{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:28:57Z","timestamp":1759336137089,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T00:00:00Z","timestamp":1600041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T00:00:00Z","timestamp":1600041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["MSIT(2020R1C1C1009766)"],"award-info":[{"award-number":["MSIT(2020R1C1C1009766)"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","award":["Creative-Pioneering Researchers Program"],"award-info":[{"award-number":["Creative-Pioneering Researchers Program"]}],"id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s10957-020-01747-1","type":"journal-article","created":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T07:02:45Z","timestamp":1600066965000},"page":"133-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Convex Optimization Approach to Dynamic Programming in Continuous State and Action Spaces"],"prefix":"10.1007","volume":"187","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-6169","authenticated-orcid":false,"given":"Insoon","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,14]]},"reference":[{"key":"1747_CR1","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"key":"1747_CR2","volume-title":"Numerical Methods for Stochastic Control Problems in Continuous Time","author":"H Kushner","year":"2013","unstructured":"Kushner, H., Dupuis, P.G.: Numerical Methods for Stochastic Control Problems in Continuous Time. Springer, New York (2013)"},{"key":"1747_CR3","volume-title":"Discrete-Time Markov Control Processes: Basic Optimality Criteria","author":"O Hern\u00e1ndez-Lerma","year":"2012","unstructured":"Hern\u00e1ndez-Lerma, O., Lasserre, J.B.: Discrete-Time Markov Control Processes: Basic Optimality Criteria. Springer, New York (2012)"},{"doi-asserted-by":"crossref","unstructured":"Savorgnan, C., Lasserre, J.B., Diehl, M.: Discrete-time stochastic optimal control via occupation measures and moment relaxations. In: Proceedings of Joint 48th IEEE Conference on Decision and Control and 28th Chinese Control Conference (2009)","key":"1747_CR4","DOI":"10.1109\/CDC.2009.5399899"},{"issue":"2","key":"1747_CR5","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1137\/120867925","volume":"51","author":"F Dufour","year":"2013","unstructured":"Dufour, F., Prieto-Rumeau, T.: Finite linear programming approximations of constrained discounted Markov decision processes. SIAM J. Control Optim. 51(2), 1298\u20131324 (2013)","journal-title":"SIAM J. Control Optim."},{"key":"1747_CR6","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"key":"1747_CR7","volume-title":"Reinforcement Learning and Optimal Control","author":"DP Bertsekas","year":"2019","unstructured":"Bertsekas, D.P.: Reinforcement Learning and Optimal Control. Athena Scientific, Belmont (2019)"},{"key":"1747_CR8","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009","volume-title":"Algorithms for Reinforcement Learning","author":"C Szepesvari","year":"2010","unstructured":"Szepesvari, C.: Algorithms for Reinforcement Learning. Morgan and Claypool Publishers, San Rafael (2010)"},{"issue":"3","key":"1747_CR9","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1109\/TAC.1975.1100984","volume":"20","author":"DP Bertsekas","year":"1975","unstructured":"Bertsekas, D.P.: Convergence of discretization procedures in dynamic programming. IEEE Trans. Autom. Control 20(3), 415\u2013419 (1975)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"4","key":"1747_CR10","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1287\/moor.6.4.493","volume":"6","author":"H-J Langen","year":"1981","unstructured":"Langen, H.-J.: Convergence of dynamic programming models. Math. Oper. Res. 6(4), 493\u2013512 (1981)","journal-title":"Math. Oper. Res."},{"issue":"3","key":"1747_CR11","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1287\/moor.3.3.231","volume":"3","author":"W Whitt","year":"1978","unstructured":"Whitt, W.: Approximations of dynamic programs, I. Math. Oper. Res. 3(3), 231\u2013243 (1978)","journal-title":"Math. Oper. Res."},{"key":"1747_CR12","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/B978-0-12-568150-6.50022-2","volume-title":"Dynamic Programming and Its Applications","author":"K Hinderer","year":"1978","unstructured":"Hinderer, K.: On approximate solutions of finite-stage dynamic programs. In: Puterman, M.L. (ed.) Dynamic Programming and Its Applications, pp. 289\u2013317. Academic Press, New York (1978)"},{"issue":"8","key":"1747_CR13","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/9.133184","volume":"36","author":"C-S Chow","year":"1991","unstructured":"Chow, C.-S., Tsitsiklis, J.N.: An optimal one-way multigrid algorithm for discrete-time stochastic control. IEEE Trans. Autom. Control 36(8), 898\u2013914 (1991)","journal-title":"IEEE Trans. Autom. Control"},{"key":"1747_CR14","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1016\/j.jmaa.2011.11.015","volume":"388","author":"F Dufour","year":"2012","unstructured":"Dufour, F., Prieto-Rumeau, T.: Approximation of Markov decision processes with general state space. J. Math. Anal. Appl. 388, 1254\u20131267 (2012)","journal-title":"J. Math. Anal. Appl."},{"issue":"2","key":"1747_CR15","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1080\/17442508.2014.939979","volume":"87","author":"F Dufour","year":"2015","unstructured":"Dufour, F., Prieto-Rumeau, T.: Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities. Stochast. Int. J. Probab. Stochast. Process. 87(2), 273\u2013307 (2015)","journal-title":"Stochast. Int. J. Probab. Stochast. Process."},{"issue":"4","key":"1747_CR16","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1287\/moor.2016.0832","volume":"42","author":"N Saldi","year":"2017","unstructured":"Saldi, N., Y\u00fcksel, S., Linder, T.: On the asymptotic optimality of finite approximations to Markov decision processes with Borel spaces. Math. Oper. Res. 42(4), 945\u2013978 (2017)","journal-title":"Math. Oper. Res."},{"key":"1747_CR17","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/0022-247X(89)90259-X","volume":"137","author":"O Hern\u00e1ndez-Lerma","year":"1989","unstructured":"Hern\u00e1ndez-Lerma, O.: Discretization procedures for adaptive Markov control processes. J. Math. Anal. Appl. 137, 485\u2013514 (1989)","journal-title":"J. Math. Anal. Appl."},{"issue":"3","key":"1747_CR18","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1287\/opre.41.3.484","volume":"41","author":"SA Johnson","year":"1993","unstructured":"Johnson, S.A., Stedinger, J.R., Shoemaker, C.A., Li, Y., Tejada-Guibert, J.A.: Numerical solution of continuous-state dynamic programs using linear and spline interpolation. Oper. Res. 41(3), 484\u2013500 (1993)","journal-title":"Oper. Res."},{"key":"1747_CR19","volume-title":"Further Topics on Discrete-Time Markov Control Processes","author":"O Hern\u00e1ndez-Lerma","year":"2012","unstructured":"Hern\u00e1ndez-Lerma, O., Lasserre, J.B.: Further Topics on Discrete-Time Markov Control Processes. Springer, New York (2012)"},{"issue":"3","key":"1747_CR20","doi-asserted-by":"publisher","first-page":"487","DOI":"10.2307\/2171751","volume":"65","author":"J Rust","year":"1997","unstructured":"Rust, J.: Using randomization to break the curse of dimensionality. Econometrica 65(3), 487\u2013516 (1997)","journal-title":"Econometrica"},{"key":"1747_CR21","first-page":"815","volume":"1","author":"R Munos","year":"2008","unstructured":"Munos, R., Szepesv\u00e1ri, C.: Finite-time bounds for fitted value iteration. J. Mach. Learn. Res. 1, 815\u2013857 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"1747_CR22","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1109\/TAC.2019.2907414","volume":"65","author":"WB Haskell","year":"2020","unstructured":"Haskell, W.B., Jain, R., Sharma, H., Yu, P.: A universal empirical dynamic programming algorithm for continuous state MDPs. IEEE Trans. Autom. Control 65(1), 115\u2013129 (2020)","journal-title":"IEEE Trans. Autom. Control"},{"doi-asserted-by":"crossref","unstructured":"Jang, S., Yang, I.: Stochastic subgradient methods for dynamic programming in continuous state and action spaces. In: Proceedings of the 58th IEEE Conference on Decision and Control, pp. 7287\u20137293 (2019)","key":"1747_CR23","DOI":"10.1109\/CDC40024.2019.9028854"},{"key":"1747_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4","volume-title":"Lectures on Convex Optimization","author":"Y Nesterov","year":"2018","unstructured":"Nesterov, Y.: Lectures on Convex Optimization, 2nd edn. Springer, Cham (2018)","edition":"2"},{"key":"1747_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"S Boyd","year":"2004","unstructured":"Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)"},{"key":"1747_CR26","volume-title":"Convex Optimization Algorithms","author":"DP Bertsekas","year":"2015","unstructured":"Bertsekas, D.P.: Convex Optimization Algorithms. Athena Scientific, Bellmont (2015)"},{"key":"1747_CR27","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973051","volume-title":"Semi-Lagrangian Approximation Schemes for Linear and Hamilton-Jacobi Equations","author":"M Falcone","year":"2013","unstructured":"Falcone, M., Ferretti, R.: Semi-Lagrangian Approximation Schemes for Linear and Hamilton-Jacobi Equations. SIAM, Philadelphia (2013)"},{"issue":"4","key":"1747_CR28","doi-asserted-by":"publisher","first-page":"A2384","DOI":"10.1137\/18M1203900","volume":"41","author":"A Alla","year":"2019","unstructured":"Alla, A., Falcone, M., Saluzzi, L.: An efficient DP algorithm on a tree-structure for finite horizon optimal control problems. SIAM J. Sci. Comput. 41(4), A2384\u2013A2406 (2019)","journal-title":"SIAM J. Sci. Comput."},{"key":"1747_CR29","doi-asserted-by":"publisher","first-page":"104619","DOI":"10.1016\/j.sysconle.2019.104619","volume":"137","author":"A Picarelli","year":"2020","unstructured":"Picarelli, A., Reisinger, C.: Probabilistic error analysis for some approximation schemes to optimal control problems. Syst. Control Lett. 137, 104619 (2020)","journal-title":"Syst. Control Lett."},{"unstructured":"Yang, I.: A convex optimization approach to dynamic programming in continuous state and action spaces. arXiv preprint arXiv:1810.03847 (2018)","key":"1747_CR30"},{"key":"1747_CR31","doi-asserted-by":"publisher","first-page":"2724","DOI":"10.1016\/j.automatica.2008.03.027","volume":"44","author":"A Abate","year":"2008","unstructured":"Abate, A., Prandini, M., Lygeros, J., Sastry, S.: Probabilistic reachability and safety for controlled discrete time stochastic hybrid systems. Automatica 44, 2724\u20132734 (2008)","journal-title":"Automatica"},{"key":"1747_CR32","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.automatica.2018.04.022","volume":"94","author":"I Yang","year":"2018","unstructured":"Yang, I.: A dynamic game approach to distributionally robust safety specifications for stochastic systems. Automatica 94, 94\u2013101 (2018)","journal-title":"Automatica"},{"key":"1747_CR33","volume-title":"Linear Programming and Extensions","author":"GB Dantzig","year":"1998","unstructured":"Dantzig, G.B.: Linear Programming and Extensions. Princeton University Press, Princeton (1998)"},{"key":"1747_CR34","volume-title":"Introduction to Linear Optimization","author":"D Bertsimas","year":"1997","unstructured":"Bertsimas, D., Tsitsiklis, J.N.: Introduction to Linear Optimization. Athena Scientific, Belmont (1997)"},{"key":"1747_CR35","volume-title":"Optimal Control Theory: Applications to Management Science and Economics","author":"SP Sethi","year":"2000","unstructured":"Sethi, S.P., Thompson, G.L.: Optimal Control Theory: Applications to Management Science and Economics. Springer, New York (2000)"},{"issue":"3","key":"1747_CR36","doi-asserted-by":"publisher","first-page":"497","DOI":"10.2307\/2372560","volume":"79","author":"LE Dubins","year":"1957","unstructured":"Dubins, L.E.: On curves of minimal length with a constraint on average curvature, and with prescribed initial and terminal positions and tangents. Am. J. Math. 79(3), 497\u2013516 (1957)","journal-title":"Am. J. Math."},{"issue":"4","key":"1747_CR37","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1137\/17M1121044","volume":"57","author":"V Magron","year":"2019","unstructured":"Magron, V., Garoche, P.-L., Henrion, D., Thirioux, X.: Semidefinite approximations of reachable sets for discrete-time polynomial systems. SIAM J. Control Optim. 57(4), 2799\u20132820 (2019)","journal-title":"SIAM J. Control Optim."},{"key":"1747_CR38","doi-asserted-by":"publisher","first-page":"1414","DOI":"10.1016\/j.automatica.2011.02.009","volume":"47","author":"AA Kurzhanskiy","year":"2011","unstructured":"Kurzhanskiy, A.A., Varaiya, P.: Reach set computation and control synthesis for discrete-time dynamical systems with disturbances. Automatica 47, 1414\u20131426 (2011)","journal-title":"Automatica"}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-020-01747-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10957-020-01747-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-020-01747-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,14]],"date-time":"2021-09-14T01:57:35Z","timestamp":1631584655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10957-020-01747-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,14]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["1747"],"URL":"https:\/\/doi.org\/10.1007\/s10957-020-01747-1","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"type":"print","value":"0022-3239"},{"type":"electronic","value":"1573-2878"}],"subject":[],"published":{"date-parts":[[2020,9,14]]},"assertion":[{"value":"15 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}