论文信息 - Adaptive Control of a Partially Observed Discrete Time Markov Process

Adaptive Control of a Partially Observed Discrete Time Markov Process

Abstract. An adaptive control problem of a discrete time Markov process that is completely observed in a fixed recurrent domain and is partially observed elsewhere is formulated and a solution is given by constructing an approximately self-optimal strategy. The state space of the Markov process is either a closed subset of Euclidean space or a countable set. Another adaptive control problem is solved where the process is always only partially observed but there is a family of random times when the process evaluated at these times is a family of independent, identically distributed random variables.

[1] V. Borkar,et al. Parameter estimation in continuous-time stochastic processes , 1982 .

[2] V. Borkar. The Kumar-Becker-Lin scheme revisited , 1990 .

[3] E. Fernandez-Gaucherand,et al. A methodology for the adaptive control of Markov chains under partial state information , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[4] Ari Arapostathis,et al. Analysis of an adaptive control scheme for a partially observed controlled Markov chain , 1990 .

[5] Nearly optimal controls for stochastic ergodic problems with partial observation , 1993 .

[6] Łukasz Stettner,et al. On nearly self-optimizing strategies for a discrete-time uniformly ergodic adaptive model , 1993 .

[7] L. Stettner,et al. On the ergodic and the adaptive control of stochastic differential delay systems , 1994 .

[8] Łukasz Stettner,et al. On adaptive control of a partially observed Markov chain , 1994 .

[9] B. Pasik-Duncan,et al. Almost self-optimizing strategies for the adaptive control of diffusion processes , 1994 .

[10] L. Stettner,et al. Approximations of discrete time partially observed control problems , 1994 .