Adaptive control of discrete time Markov processes by the method of large deviations
暂无分享,去创建一个
Adaptive control strategies for discrete time Markov processes are constructed using the uniform, large deviations of empirical distributions. The adaptive procedure is based on the construction of a finite set of continuous nearly optimal control functions, and implies that in a finite time interval a control function exists that is almost optimal with probability close to 1.
[1] L. Stettner,et al. Bayesian ergodic adaptive control of discrete time markov processes , 1995 .
[2] Majorations de Chernoff pour des chaînes de Markov contrÔlées , 1980 .
[3] Łukasz Stettner,et al. On nearly self-optimizing strategies for a discrete-time uniformly ergodic adaptive model , 1993 .
[4] S. Varadhan,et al. Asymptotic evaluation of certain Markov process expectations for large time , 1975 .