Fernández-Gaucherand, Emmanuel; Arapostathis, Aristotle; Marcus, Steven I. On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes. (English) Zbl 0717.90094 Ann. Oper. Res. 29, No. 1-4, 439-469 (1991). MSC: 90C40 93E20 60J10 90B25 PDFBibTeX XMLCite \textit{E. Fernández-Gaucherand} et al., Ann. Oper. Res. 29, No. 1--4, 439--469 (1991; Zbl 0717.90094) Full Text: DOI
Arapostathis, Aristotle; Marcus, Steven I. Analysis of an identification algorithm arising in the adaptive estimation of Markov chains. (English) Zbl 0685.93063 Math. Control Signals Syst. 3, No. 1, 1-29 (1990). Reviewer: J.Stoyanov MSC: 93E10 93C40 60J10 PDFBibTeX XMLCite \textit{A. Arapostathis} and \textit{S. I. Marcus}, Math. Control Signals Syst. 3, No. 1, 1--29 (1990; Zbl 0685.93063) Full Text: DOI
Arapostathis, Aristotle; Marcus, Steven I. Adaptive estimation of Markov chains with incomplete observations. (English) Zbl 0673.93074 Analysis and control of nonlinear systems, Sel. Pap. 8th Int. Symp. Math. Networks Syst., Phoenix/Ariz. 1987, 3-12 (1988). MSC: 93E10 60J10 93C40 93E25 62L20 PDFBibTeX XML