zbMATH — the first resource for mathematics

On a stopping rule for a class of sequential decision problems. (English) Zbl 0518.62070

62L15 Optimal stopping in statistics
62L05 Sequential statistical design
90C39 Dynamic programming
Full Text: DOI EuDML
[1] DeGroot, M.H.: Optimal statistical decisions. New York 1970. · Zbl 0225.62006
[2] Hengartner, W., D. Kalin andR. Theodorescu: On the Bernoulli two-armed bandit problem. Math. Operationsforsch. Statist., Ser. Optimization12, 1981, 307–316. · Zbl 0512.62081
[3] Hinderer, K.: Foundations of non-stationary dynamic programming with discrete time-parameter. Lecture Notes in Operations Research and Mathematical Systems, 33. New York 1970. · Zbl 0202.18401
[4] Jones, P.W.: Some results for the two-armed bandit problem. Math. Operationsforsch Statist.7, 1976, 471–475. · Zbl 0339.90056
[5] Kalin, D.: Zum Problem des zweiarmigen Bernoulli-Banditen mit einer bekannten Erfolgswahrscheinlichkeit und unendlich vielen Spielen. Metrika29, 1982, 261–270. · Zbl 0504.90085
[6] Kalin, D., andR. Theodorescu: Sur le probleme du bandit á deux bras quand une probabilité est connue. Publ. Inst. Statist. Paris25, 1980, 49–60. · Zbl 0453.60051
[7] Schäl, M.: Conditions for optimality in dynamic programming and for the limit ofn-stage optimal policies to be optimal. Z. Wahrscheinlichkeitstheorie Verw. Gebiete32, 1975, 179–196. · Zbl 0316.90080
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.