{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T13:45:09Z","timestamp":1778679909922,"version":"3.51.4"},"reference-count":19,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2002,6,1]],"date-time":"2002-06-01T00:00:00Z","timestamp":1022889600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Automatica"],"published-print":{"date-parts":[[2002,6]]},"DOI":"10.1016\/s0005-1098(01)00282-5","type":"journal-article","created":{"date-parts":[[2002,10,14]],"date-time":"2002-10-14T13:01:41Z","timestamp":1034600501000},"page":"929-943","source":"Crossref","is-referenced-by-count":61,"title":["A time aggregation approach to Markov decision processes"],"prefix":"10.1016","volume":"38","author":[{"given":"Xi-Ren","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0005-1098(01)00282-5_BIB1","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/9.67293","article-title":"Aggregation of the policy iteration method for nearly completely decomposable Markov chains","volume":"36","author":"Aldhaheri","year":"1991","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB2","series-title":"Neuro-dynamic programming","author":"Bertsekas","year":"1996"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB3","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/87.701341","article-title":"Algorithms for sensitivity analysis of Markov systems through potentials and perturbation realization","volume":"6","author":"Xi-Ren Cao","year":"1998","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB4","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1008260528575","article-title":"The relation among potentials, perturbation analysis, Markov decision processes, and other topics","volume":"8","author":"Xi-Ren Cao","year":"1998","journal-title":"Journal of Discrete Event Dynamic Systems"},{"issue":"3","key":"10.1016\/S0005-1098(01)00282-5_BIB5","first-page":"527","article-title":"Single sample path-based optimization of Markov chains","volume":"100","author":"Xi-Ren Cao","year":"1999","journal-title":"Journal of Optimization: Theory and Applications"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB6","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/S0005-1098(99)00207-1","article-title":"A unified approach to Markov decision problems and performance sensitivity analysis","volume":"36","author":"Xi-Ren Cao","year":"2000","journal-title":"Automatica"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB7","series-title":"Dependability for systems with a partitioned state space","author":"Csenki","year":"1994"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB8","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/TAC.1978.1101707","article-title":"Multilayer control of large Markov chains","volume":"AC-23","author":"Forestier","year":"1978","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB9","series-title":"Discrete stochastic processes","author":"Gallager","year":"1996"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB10","series-title":"Computer networking: a top\u2013down approach","author":"Kurose","year":"2001"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB11","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/9.905687","article-title":"Simulation-based optimization of Markov reward processes","volume":"46","author":"Marbach","year":"2001","journal-title":"IEEE Transactions on Automatic Control"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB12","unstructured":"Parr, R. E. (1998). Hierarchical control and learning for Markov decision processes. Ph.D dissertation, Department of Computer Science, University of California, Berkeley."},{"key":"10.1016\/S0005-1098(01)00282-5_BIB13","series-title":"Markov chains","author":"Revuz","year":"1984"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB14","doi-asserted-by":"crossref","first-page":"487","DOI":"10.2307\/2171751","article-title":"Using randomization to break the curse of dimensionality","volume":"65","author":"Rust","year":"1997","journal-title":"Econometrica"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB15","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning","volume":"12","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB16","doi-asserted-by":"crossref","first-page":"1799","DOI":"10.1016\/S0005-1098(99)00099-0","article-title":"Average cost temporal-difference learning","volume":"35","author":"Tsitsiklis","year":"1999","journal-title":"Automatica"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB17","unstructured":"Van Roy, B., Bertsekas, D. P., Lee, Y., & Tsitsiklis, J. N. (1996). A neuro-dynamic programming approach to retailer inventory management. Preprint."},{"key":"10.1016\/S0005-1098(01)00282-5_BIB18","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/S0005-1098(01)00282-5_BIB19","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1109\/9.100931","article-title":"Performance gradient estimation for very large finite Markov chains","volume":"36","author":"Zhang","year":"1991","journal-title":"IEEE Transactions on Automatic Control"}],"container-title":["Automatica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0005109801002825?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0005109801002825?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,2,9]],"date-time":"2019-02-09T01:14:07Z","timestamp":1549674847000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0005109801002825"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,6]]},"references-count":19,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2002,6]]}},"alternative-id":["S0005109801002825"],"URL":"https:\/\/doi.org\/10.1016\/s0005-1098(01)00282-5","relation":{},"ISSN":["0005-1098"],"issn-type":[{"value":"0005-1098","type":"print"}],"subject":[],"published":{"date-parts":[[2002,6]]}}}