{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T14:22:34Z","timestamp":1761488554568},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,10,1]],"date-time":"2010-10-01T00:00:00Z","timestamp":1285891200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Discrete Event Dyn Syst"],"published-print":{"date-parts":[[2011,3]]},"DOI":"10.1007\/s10626-010-0093-4","type":"journal-article","created":{"date-parts":[[2010,9,30]],"date-time":"2010-09-30T03:18:01Z","timestamp":1285816681000},"page":"11-38","source":"Crossref","is-referenced-by-count":14,"title":["Stochastic control via direct comparison"],"prefix":"10.1007","volume":"21","author":[{"given":"Xi-Ren","family":"Cao","sequence":"first","affiliation":[]},{"given":"De-Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,10,1]]},"reference":[{"key":"93_CR1","volume-title":"Dynamic programming and optimal control, vols I and II","author":"DP Bertsekas","year":"2007","unstructured":"Bertsekas DP (2007) Dynamic programming and optimal control, vols I and II. Athena Scientific, Belmont"},{"key":"93_CR2","volume-title":"Neuro-dynamic programming","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas DP, Tsitsiklis TN (1996) Neuro-dynamic programming. Athena Scientific, Belmont"},{"key":"93_CR3","volume-title":"Probability and measure","author":"P Billingsley","year":"1979","unstructured":"Billingsley P (1979) Probability and measure. Wiley, New York"},{"key":"93_CR4","unstructured":"Brockett R (2009) Stochastic control. Lecture Notes, Harvard University"},{"key":"93_CR5","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022188803039","volume":"13","author":"X-R Cao","year":"2003","unstructured":"Cao X-R (2003) From perturbation analysis to Markov decision processes and reinforcement learning. Discrete Event Dyn Syst 13:9\u201339","journal-title":"Discrete Event Dyn Syst"},{"key":"93_CR6","doi-asserted-by":"crossref","first-page":"2129","DOI":"10.1109\/TAC.2004.838494","volume":"49","author":"X-R Cao","year":"2004","unstructured":"Cao X-R (2004) The potential structure of sample paths and performance sensitivities of Markov systems. IEEE Trans Automat Contr 49:2129\u20132142","journal-title":"IEEE Trans Automat Contr"},{"key":"93_CR7","doi-asserted-by":"crossref","unstructured":"Cao X-R (2007) Stochastic learning and optimization\u2014a sensitivity-based approach. Springer","DOI":"10.1007\/978-0-387-69082-7"},{"key":"93_CR8","unstructured":"Cao X-R (2009a) Stochastic control of continuous-time and continuous-state systems via direct comparison. In: The proceedings of the 48th IEEE conference on decision and control, pp 1593\u20131598"},{"key":"93_CR9","doi-asserted-by":"crossref","unstructured":"Cao X-R (2009b) A new model of continuous-time Markov processes and impulse stochastic control. In: The proceedings of the 48th IEEE conference on decision and control, pp 525\u2013530","DOI":"10.1109\/CDC.2009.5399775"},{"key":"93_CR10","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1109\/TAC.2007.915168","volume":"53","author":"XR Cao","year":"2008","unstructured":"Cao XR, Zhang JY (2008) The Nth-order bias optimality for multichain Markov decision processes. IEEE Trans Automat Contr 53:496\u2013508","journal-title":"IEEE Trans Automat Contr"},{"key":"93_CR11","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1109\/9.545747","volume":"41","author":"X-R Cao","year":"1996","unstructured":"Cao X-R, Yuan XM, Qiu L (1996) A single sample path-based performance sensitivity formula for Markov chains. IEEE Trans Automat Contr 41:1814\u20131817","journal-title":"IEEE Trans Automat Contr"},{"key":"93_CR12","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4070-7","volume-title":"Introduction to discrete event systems","author":"CG Cassandras","year":"1999","unstructured":"Cassandras CG, Lafortune S (1999) Introduction to discrete event systems. Kluwer, Boston"},{"key":"93_CR13","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1287\/opre.51.6.850.24925","volume":"51","author":"DP Farias De","year":"2003","unstructured":"De Farias DP, Van Roy B (2003) The linear programming approach to approximate dynamic programming. Oper Res 51:850\u2013865","journal-title":"Oper Res"},{"key":"93_CR14","doi-asserted-by":"crossref","unstructured":"Ethier SN, Kurtz TG (1986) Markov processes: characterization and convergence. Wiley","DOI":"10.1002\/9780470316658"},{"key":"93_CR15","volume-title":"Handbook of Markov decision processes: methods and application","year":"2002","unstructured":"Feinberg EA, Shwartz A (eds) (2002) Handbook of Markov decision processes: methods and application. Kluwer, Boston"},{"key":"93_CR16","unstructured":"Fleming WH, Soner HM (2006) Controlled Markov processes and viscosity solutions, 2nd edn. Springer"},{"key":"93_CR17","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1214\/aop\/1039639370","volume":"24","author":"PW Glynn","year":"1996","unstructured":"Glynn PW, Meyn SP (1996) A Lyapunov bound for solutions of the Poisson equation. Ann Probab 24:916\u2013931","journal-title":"Ann Probab"},{"key":"93_CR18","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0729-0","volume-title":"Discrete-time Markov control processes: basic optimality criteria","author":"O Hernandez-Lerma","year":"1996","unstructured":"Hernandez-Lerma O, Lasserre JB (1996) Discrete-time Markov control processes: basic optimality criteria. Springer, New York"},{"key":"93_CR19","volume-title":"Perturbation analysis of discrete-event dynamic systems","author":"YC Ho","year":"1991","unstructured":"Ho YC, Cao X-R (1991) Perturbation analysis of discrete-event dynamic systems. Kluwer, Boston"},{"key":"93_CR20","unstructured":"Hojgaard B, Taksar M (2009) Diffusion optimization models in insurance and finance. Preprint"},{"key":"93_CR21","unstructured":"Howard RA (1960) Dynamic programming and Markov processes. Wiley"},{"key":"93_CR22","unstructured":"Karatzas I, Shreve SE (1991) Brownian motion and stochastic calculus, 2nd edn. Springer"},{"key":"93_CR23","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1287\/opre.1030.0107","volume":"52","author":"S Kumar","year":"2004","unstructured":"Kumar S, Muthuraman K (2004) A numerical method for solving singular stochastic control problems. Oper Res 52:563\u2013582","journal-title":"Oper Res"},{"key":"93_CR24","doi-asserted-by":"crossref","first-page":"1663","DOI":"10.1109\/9.650016","volume":"42","author":"SP Meyn","year":"1997","unstructured":"Meyn SP (1997) The policy iteration algorithm for average reward Markov decision processes with general state space. IEEE Trans Automat Contr 42:1663\u20131680","journal-title":"IEEE Trans Automat Contr"},{"key":"93_CR25","doi-asserted-by":"crossref","first-page":"518","DOI":"10.2307\/1427522","volume":"25","author":"SP Meyn","year":"1993","unstructured":"Meyn SP, Tweedie RL (1993) Stability of Markovian processes III: Foster\u2013Lyapunov criteria for continuous time processes. Adv Appl Probab 25:518\u2013548","journal-title":"Adv Appl Probab"},{"key":"93_CR26","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511626630","volume-title":"Markov chains and stochastic stability","author":"SP Meyn","year":"2009","unstructured":"Meyn SP, Tweedie RL (2009) Markov chains and stochastic stability, 2nd edn. Cambridge University Press, London","edition":"2"},{"key":"93_CR27","doi-asserted-by":"crossref","unstructured":"Oksendal B, Sulem A (2007) Applied stochastic control of jump diffusions. Springer","DOI":"10.1007\/978-3-540-69826-5"},{"key":"93_CR28","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1287\/opre.49.3.398.11219","volume":"49","author":"CR Philbrick Jr","year":"2001","unstructured":"Philbrick CR Jr, Kitanidis PK (2001) Improved dynamic programming methods for optimal control of lumped-parameter stochastic systems. Oper Res 49:398\u2013468","journal-title":"Oper Res"},{"key":"93_CR29","doi-asserted-by":"crossref","DOI":"10.1002\/9780470182963","volume-title":"Approximate dynamic programming: solving the curses of dimensionality","author":"WB Powell","year":"2007","unstructured":"Powell WB (2007) Approximate dynamic programming: solving the curses of dimensionality. Wiley, New York"},{"key":"93_CR30","doi-asserted-by":"crossref","unstructured":"Puterman ML (1994) Markov decision processes: discrete stochastic dynamic programming. Wiley","DOI":"10.1002\/9780470316887"},{"key":"93_CR31","doi-asserted-by":"crossref","unstructured":"Revuz D, Yor M (1991) Continuous martingales and Brownian motion. Springer","DOI":"10.1007\/978-3-662-21726-9"},{"key":"93_CR32","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT, Cambridge"},{"issue":"2","key":"93_CR33","doi-asserted-by":"crossref","first-page":"401","DOI":"10.2307\/3212261","volume":"5","author":"PJ Schweitzer","year":"1968","unstructured":"Schweitzer PJ (1968) Perturbation theory and finite Markov chains. J Appl Probab 5(2):401\u2013413","journal-title":"J Appl Probab"},{"issue":"5","key":"93_CR34","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1214\/aoms\/1177697379","volume":"40","author":"AF Veinott","year":"1969","unstructured":"Veinott AF (1969) Discrete dynamic programming with sensitive discount optimality criteria. Ann Math Stat 40(5):1635\u20131660","journal-title":"Ann Math Stat"},{"issue":"10","key":"93_CR35","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1109\/TAC.2006.883022","volume":"51","author":"L Xia","year":"2006","unstructured":"Xia L, Cao X-R (2006) Relationship between perturbation realization factors with queueing models and Markov models. IEEE Trans Automat Contr 51(10):1699\u20131704","journal-title":"IEEE Trans Automat Contr"},{"key":"93_CR36","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1016\/j.automatica.2009.03.007","volume":"45","author":"L Xia","year":"2009","unstructured":"Xia L, Chen X, Cao X-R (2009) Policy iteration of customer-average performance in queueing systems. Automatica 45:1639\u20131648","journal-title":"Automatica"}],"container-title":["Discrete Event Dynamic Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10626-010-0093-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10626-010-0093-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10626-010-0093-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T21:46:43Z","timestamp":1636580803000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10626-010-0093-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["93"],"URL":"https:\/\/doi.org\/10.1007\/s10626-010-0093-4","relation":{},"ISSN":["0924-6703","1573-7594"],"issn-type":[{"value":"0924-6703","type":"print"},{"value":"1573-7594","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,10,1]]}}}