{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T14:00:46Z","timestamp":1648821646366},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,9,26]],"date-time":"2013-09-26T00:00:00Z","timestamp":1380153600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Optim Theory Appl"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s10957-013-0418-1","type":"journal-article","created":{"date-parts":[[2013,9,25]],"date-time":"2013-09-25T21:35:19Z","timestamp":1380144919000},"page":"165-180","source":"Crossref","is-referenced-by-count":2,"title":["Temporal Difference-Based Policy Iteration for Optimal Control of Stochastic Systems"],"prefix":"10.1007","volume":"163","author":[{"given":"Kang","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shumin","family":"Fei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanjian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haikun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,9,26]]},"reference":[{"key":"418_CR1","volume-title":"Dynamic Programming","author":"R.E. Bellman","year":"1957","unstructured":"Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"418_CR2","volume-title":"Dynamic Programming and Stochastic Control, vols. I and II","author":"D.P. Bertsekas","year":"2007","unstructured":"Bertsekas, D.P.: Dynamic Programming and Stochastic Control, vols. I and II, 3rd edn. Athena Scientific, Belmont (2007)","edition":"3"},{"key":"418_CR3","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume-title":"Approximate Dynamic Programming: Solving the Curses of Dimensionality","author":"W.B. Powell","year":"2007","unstructured":"Powell, W.B.: Approximate Dynamic Programming: Solving the Curses of Dimensionality. Wiley, New York (2007)"},{"key":"418_CR4","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"418_CR5","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1007\/s11768-011-1005-3","volume":"9","author":"D.P. Bertsekas","year":"2011","unstructured":"Bertsekas, D.P.: Approximate policy iteration: a survey and some new methods. J. Control Theory Appl. 9, 310\u2013335 (2011)","journal-title":"J. Control Theory Appl."},{"key":"418_CR6","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11768-011-0313-y","volume":"9","author":"W.B. Powell","year":"2011","unstructured":"Powell, W.B., Ma, J.: A review of stochastic algorithms with continuous value function approximation and some new approximate policy iteration algorithms for multidimensional continuous applications. J. Control Theory Appl. 9, 336\u2013352 (2011)","journal-title":"J. Control Theory Appl."},{"key":"418_CR7","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1109\/9.633827","volume":"42","author":"X.R. Cao","year":"1997","unstructured":"Cao, X.R., Chen, H.F.: Potentials, perturbation realization, and sensitivity analysis of Markov processes. IEEE Trans. Autom. Control 42, 1382\u20131393 (1997)","journal-title":"IEEE Trans. Autom. Control"},{"key":"418_CR8","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/S0005-1098(99)00207-1","volume":"36","author":"X.R. Cao","year":"2000","unstructured":"Cao, X.R.: A unified approach to Markov decision problems and performance sensitivity analysis. Automatica 36, 771\u2013774 (2000)","journal-title":"Automatica"},{"key":"418_CR9","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1016\/j.automatica.2004.05.003","volume":"40","author":"X.R. Cao","year":"2004","unstructured":"Cao, X.R., Guo, X.P.: A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases. Automatica 40, 1749\u20131759 (2004)","journal-title":"Automatica"},{"key":"418_CR10","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1016\/j.automatica.2007.08.014","volume":"44","author":"K.J. Zhang","year":"2008","unstructured":"Zhang, K.J., Xu, Y.K., Chen, X., Cao, X.R.: Policy iteration based feedback control. Automatica 44, 1055\u20131061 (2008)","journal-title":"Automatica"},{"key":"418_CR11","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1023\/A:1022634422482","volume":"100","author":"X.R. Cao","year":"1999","unstructured":"Cao, X.R.: Single sample path-based optimization of Markov chains. J. Optim. Theory Appl. 100, 527\u2013548 (1999)","journal-title":"J. Optim. Theory Appl."},{"key":"418_CR12","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1109\/TAC.2004.825647","volume":"49","author":"H.T. Fang","year":"2004","unstructured":"Fang, H.T., Cao, X.R.: Potential-based on-line policy iteration algorithms for Markov decision processes. IEEE Trans. Autom. Control 49, 493\u2013505 (2004)","journal-title":"IEEE Trans. Autom. Control"},{"key":"418_CR13","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"418_CR14","first-page":"33","volume":"22","author":"S. Bradtke","year":"1996","unstructured":"Bradtke, S., Barto, A.: Linear least-squares algorithms for temporal difference learning. Mach. Learn. 22, 33\u201357 (1996)","journal-title":"Mach. Learn."},{"key":"418_CR15","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","volume":"13","author":"A. Nedic","year":"2003","unstructured":"Nedic, A., Bertsekas, D.P.: Least squares policy evaluation algorithms with linear function approximation. Discrete Event Dyn. Syst. 13, 79\u2013110 (2003)","journal-title":"Discrete Event Dyn. Syst."},{"key":"418_CR16","first-page":"1107","volume":"4","author":"M. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M., Parr, R.: Least-squares policy iteration. J. Mach. Learn. Res. 4, 1107\u20131149 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"418_CR17","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.cam.2008.07.037","volume":"227","author":"D.P. Bertsekas","year":"2009","unstructured":"Bertsekas, D.P., Yu, H.Z.: Projected equation methods for approximate solution of large linear systems. J. Comput. Appl. Math. 227, 27\u201350 (2009)","journal-title":"J. Comput. Appl. Math."},{"key":"418_CR18","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Roy, B.V.: An analysis of temporal-difference learning with function approximation. IEEE Trans. Autom. Control 42, 674\u2013690 (1997)","journal-title":"IEEE Trans. Autom. Control"},{"key":"418_CR19","first-page":"66","volume-title":"ADPRL 2009\u2014Proceedings","author":"J. Ma","year":"2009","unstructured":"Ma, J., Powell, W.B.: A convergent recursive least squares approximate policy iteration algorithm for multi-dimensional Markov decision process with continuous state and action spaces. In: ADPRL 2009\u2014Proceedings, Nashville, USA, pp. 66\u201373 (2009)"},{"key":"418_CR20","doi-asserted-by":"crossref","first-page":"666","DOI":"10.2307\/1427125","volume":"17","author":"K.S. Chan","year":"1985","unstructured":"Chan, K.S., Tong, H.: On the use of the deterministic Lyapunov function for the ergodicity of stochastic difference equations. Adv. Appl. Probab. 17, 666\u2013678 (1985)","journal-title":"Adv. Appl. Probab."},{"key":"418_CR21","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-3267-7","volume-title":"Markov Chains and Stochastic Stability","author":"S.P. Meyn","year":"1993","unstructured":"Meyn, S.P., Tweedie, R.L.: Markov Chains and Stochastic Stability. Springer, London (1993)"},{"key":"418_CR22","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1109\/TAC.2009.2022097","volume":"54","author":"H.Z. Yu","year":"2009","unstructured":"Yu, H.Z., Bertsekas, D.P.: Convergence results for some temporal difference methods based on least squares. IEEE Trans. Autom. Control 54, 1515\u20131531 (2009)","journal-title":"IEEE Trans. Autom. Control"},{"key":"418_CR23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/s10626-010-0093-4","volume":"21","author":"X.R. Cao","year":"2011","unstructured":"Cao, X.R.: Stochastic control via direct comparison. Discrete Event Dyn. Syst. 21, 11\u201338 (2011)","journal-title":"Discrete Event Dyn. Syst."}],"container-title":["Journal of Optimization Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-013-0418-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10957-013-0418-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10957-013-0418-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T09:55:25Z","timestamp":1559469325000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10957-013-0418-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,26]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["418"],"URL":"https:\/\/doi.org\/10.1007\/s10957-013-0418-1","relation":{},"ISSN":["0022-3239","1573-2878"],"issn-type":[{"value":"0022-3239","type":"print"},{"value":"1573-2878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,26]]}}}