Displaying similar documents to “On the adaptive control of countable Markov chains”

On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms

Ewa Drabik (1996)

Applicationes Mathematicae

Similarity:

Two kinds of strategies for a multiarmed Markov bandit problem with controlled arms are considered: a strategy with forcing and a strategy with randomization. The choice of arm and control function in both cases is based on the current value of the average cost per unit time functional. Some simulation results are also presented.

On the discrepancy of Markov-normal sequences

M. B. Levin (1996)

Journal de théorie des nombres de Bordeaux

Similarity:

We construct a Markov normal sequence with a discrepancy of O ( N - 1 / 2 log 2 N ) . The estimation of the discrepancy was previously known to be O ( e - c ( log N ) 1 / 2 ) .

On mean central limit theorems for stationary sequences

Jérôme Dedecker, Emmanuel Rio (2008)

Annales de l'I.H.P. Probabilités et statistiques

Similarity:

In this paper, we give estimates of the minimal 𝕃 1 distance between the distribution of the normalized partial sum and the limiting gaussian distribution for stationary sequences satisfying projective criteria in the style of Gordin or weak dependence conditions.

Origami

Παναγιώτης Τελώνης (1989-1990)

Ευκλείδης Α

Similarity: