{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:48:56Z","timestamp":1787320136175,"version":"build-2736575974"},"reference-count":25,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Control Optim."],"published-print":{"date-parts":[[2009,1]]},"abstract":"<jats:p>We consider a class of discrete-time two person zero-sum Markov games with Borel state and action spaces, and possibly unbounded payoffs. The game evolves according to the recursive equation $x_{n+1}=F(x_{n},a_{n},b_{n},\\xi_{n})$, $n=0,1,\\dots$, where the disturbance process $\\{\\xi_{n}\\}$ is formed by independent and identically distributed $\\mathbb{R}^{k}$-valued random vectors, which are observable but whose common density $\\rho$ is unknown to both players. Under certain continuity and compactness conditions, we combine a nonstationary iteration procedure and suitable density estimation methods to construct asymptotically discounted optimal strategies for both players.<\/jats:p>","DOI":"10.1137\/060651458","type":"journal-article","created":{"date-parts":[[2009,4,15]],"date-time":"2009-04-15T18:16:16Z","timestamp":1239819376000},"page":"1405-1421","source":"Crossref","is-referenced-by-count":9,"title":["Asymptotically Optimal Strategies for Adaptive Zero-Sum Discounted Markov Games"],"prefix":"10.1137","volume":"48","author":[{"given":"J. Adolfo","family":"Minj\u00e1rez-Sosa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oscar","family":"Vega-Amaya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2009,4,15]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02055577"},{"key":"R2","unstructured":"R. B Ash,\n                      Real Analysis and Probability\n                      , Academic Press, New York, 1972."},{"key":"R3","unstructured":"D. P. Bertsekas and S. E. Shreve,\n                      Stochastic Optimal Control: The Discrete Time Case\n                      , Academic Press, New York, 1978."},{"key":"R4","doi-asserted-by":"crossref","unstructured":"L. Devroye and G. Lugosi,\n                      Combinatorial Methods in Density Estimation\n                      , Springer-Verlag, New York, 2001.","DOI":"10.1007\/978-1-4613-0125-7"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901383837"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1137\/1129064"},{"key":"R7","first-page":"217","volume":"34","author":"Gordienko E. I.","year":"1998","journal-title":"Kybernetika","ISSN":"https:\/\/id.crossref.org\/issn\/0023-5954","issn-type":"print"},{"key":"R8","doi-asserted-by":"crossref","unstructured":"O. Hern\u00e1ndez-Lerma,\n                      Adaptive Markov Control Processes\n                      , Springer-Verlag, New York, 1989.","DOI":"10.1007\/978-1-4419-8714-3"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00049572"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"O. Hern\u00e1ndez-Lerma and J. B. Lasserre,\n                      Further Topics on Discrete-Time Markov Control Processes\n                      , Springer-Verlag, New York, 1999.","DOI":"10.1007\/978-1-4612-0561-6"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-005-0024-6"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012904443257"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1137\/040617303"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.3.2.187"},{"key":"R15","first-page":"227","volume":"8","author":"Luque-V\u00e1squez F.","year":"2002","journal-title":"Bol. Soc. Mat. Mexicana","ISSN":"https:\/\/id.crossref.org\/issn\/0037-8615","issn-type":"print"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.4064\/am-26-3-267-280"},{"key":"R17","first-page":"681","volume":"40","author":"Minj\u00e1rez-Sosa J. A.","year":"2004","journal-title":"Kybernetika","ISSN":"https:\/\/id.crossref.org\/issn\/0023-5954","issn-type":"print"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00050-4"},{"key":"R19","unstructured":"G. P. Papavassilopoulos,\n                      Adaptive games\n                      , in Stochastic Processes in Physics and Engineering, S. Albeverio, P. Blanchard, M. Hazewinkel, and L. Streit, eds., Reidel, Dordrecht, The Netherlands, 1988, pp. 223\u2013236."},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1080\/17442508708833435"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.1029\/WR023i012p02159"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1029\/WR011i006p00767"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"J. A. E. E. Van Nunen and J. Wessels,\n                      A note on dynamic programming with unbounded rewards\n                      , Management Sci., 24 (1977\/78), pp. 576\u2013580.","DOI":"10.1287\/mnsc.24.5.576"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1029\/WR018i004p00673"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1029\/WR021i012p01797"}],"container-title":["SIAM Journal on Control and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/060651458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:55:20Z","timestamp":1787316920000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/060651458"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,1]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2009,1]]}},"alternative-id":["10.1137\/060651458"],"URL":"https:\/\/doi.org\/10.1137\/060651458","relation":{},"ISSN":["0363-0129","1095-7138"],"issn-type":[{"value":"0363-0129","type":"print"},{"value":"1095-7138","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,1]]}}}