Two adaptive procedures for controlled Markov chains which are based on a nonparametric window estimation are shown.
@article{bwmeta1.element.bwnjournal-article-zmv27i2p143bwm,
author = {Ewa Drabik and \L ukasz Stettner},
title = {On adaptive control of Markov chains using nonparametric estimation},
journal = {Applicationes Mathematicae},
volume = {27},
year = {2000},
pages = {143-152},
zbl = {1006.93069},
language = {en},
url = {http://dml.mathdoc.fr/item/bwmeta1.element.bwnjournal-article-zmv27i2p143bwm}
}
Drabik, Ewa; Stettner, Łukasz. On adaptive control of Markov chains using nonparametric estimation. Applicationes Mathematicae, Tome 27 (2000) pp. 143-152. http://gdmltest.u-ga.fr/item/bwmeta1.element.bwnjournal-article-zmv27i2p143bwm/
[000] [1] R. Agraval, The continuum-armed bandit problem, SIAM J. Control Optim. 33 (1995), 1926-1951. | Zbl 0848.93069
[001] [2] V. S. Borkar, Recursive self-tuning of finite Markov chains, Appl. Math. (Warsaw) 24 (1996), 169-188. | Zbl 0951.93537
[002] [3] E. Drabik, On nearly selfoptimizing strategies for multiarmed bandit problems with controlled arms, ibid. 23 (1996), 449-473. | Zbl 0848.93068
[003] [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. | Zbl 0914.93076
[004] [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. | Zbl 1006.93071
[005] [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. | Zbl 0717.93066
[006] [7] A. Nowak, A generalization of Ueno's inequality for n-step transition probabilities, Appl. Math. (Warsaw) 25 (1998), 295-299. | Zbl 0998.60068