A methodology for the adaptive control of Markov chains under partial state information
暂无分享,去创建一个
E. Fernandez-Gaucherand | A. Arapostathis | E. Fernández-Gaucherand | S. Marcus | A. Arapostathis | S.I. Marcus
[1] D. Teneketzis,et al. Routing in queueing networks under imperfect information: stochastic dominance and thresholds , 1989 .
[2] Ernst-Erich Doberkat. Stochastic Automata: Stability, Nondeterminism, and Prediction , 1981, Lecture Notes in Computer Science.
[3] Dimitri P. Bertsekas,et al. Dynamic Programming: Deterministic and Stochastic Models , 1987 .
[4] Ari Arapostathis,et al. Analysis of an adaptive control scheme for a partially observed controlled Markov chain , 1990 .
[5] Ari Arapostathis,et al. On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes , 1991, Ann. Oper. Res..
[6] A. Arapostathis,et al. Analysis of an adaptive control scheme for a partially observed controlled Markov chain , 1990, 29th IEEE Conference on Decision and Control.
[7] John S. Baras,et al. Stochastic control of two partially observed competing queues , 1981 .
[8] Kazuyoshi Wakuta,et al. Optimal control of an M/G/1 queue with imperfectly observed queue length when the input source is finite , 1991, Journal of Applied Probability.
[9] M. K. Ghosh,et al. Discrete-time controlled Markov processes with average cost criterion: a survey , 1993 .