On adaptive control of Markov chains using nonparametric estimation

Ewa Drabik; Łukasz Stettner

Applicationes Mathematicae (2000)

  • Volume: 27, Issue: 2, page 143-152
  • ISSN: 1233-7234

Abstract

top
Two adaptive procedures for controlled Markov chains which are based on a nonparametric window estimation are shown.

How to cite

top

Drabik, Ewa, and Stettner, Łukasz. "On adaptive control of Markov chains using nonparametric estimation." Applicationes Mathematicae 27.2 (2000): 143-152. <http://eudml.org/doc/219263>.

@article{Drabik2000,
abstract = {Two adaptive procedures for controlled Markov chains which are based on a nonparametric window estimation are shown.},
author = {Drabik, Ewa, Stettner, Łukasz},
journal = {Applicationes Mathematicae},
keywords = {controlled Markov chain; estimation; adaptive control},
language = {eng},
number = {2},
pages = {143-152},
title = {On adaptive control of Markov chains using nonparametric estimation},
url = {http://eudml.org/doc/219263},
volume = {27},
year = {2000},
}

TY - JOUR
AU - Drabik, Ewa
AU - Stettner, Łukasz
TI - On adaptive control of Markov chains using nonparametric estimation
JO - Applicationes Mathematicae
PY - 2000
VL - 27
IS - 2
SP - 143
EP - 152
AB - Two adaptive procedures for controlled Markov chains which are based on a nonparametric window estimation are shown.
LA - eng
KW - controlled Markov chain; estimation; adaptive control
UR - http://eudml.org/doc/219263
ER -

References

top
  1. [1] R. Agraval, The continuum-armed bandit problem, SIAM J. Control Optim. 33 (1995), 1926-1951. Zbl0848.93069
  2. [2] V. S. Borkar, Recursive self-tuning of finite Markov chains, Appl. Math. (Warsaw) 24 (1996), 169-188. Zbl0951.93537
  3. [3] E. Drabik, On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms, ibid. 23 (1996), 449-473. Zbl0848.93068
  4. [4] T. Duncan, B. Pasik-Duncan and Ł. Stettner, Discretized maximum likelihood and almost optimal adaptive control of ergodic adaptive models, SIAM J. Control Optim. 36 (1998), 422-446. Zbl0914.93076
  5. [5] T. Duncan, B. Pasik-Duncan and Ł. Stettner, Adaptive control of discrete Markov processes by the method of large deviations, in: Proc. 35th IEEE CDC, Kobe 1996, IEEE, 360-365. Zbl1006.93071
  6. [6] O. Hernández-Lerma and R. Cavazos-Cadena, Density estimation and adaptive control of Markov processes; average and discounted criteria, Acta Appl. Math. 20 (1990), 285-307. Zbl0717.93066
  7. [7] A. Nowak, A generalization of Ueno's inequality for n-step transition probabilities, Appl. Math. (Warsaw) 25 (1998), 295-299. Zbl0998.60068

NotesEmbed ?

top

You must be logged in to post comments.