GRADIENT APPROACH FOR RECURSIVE ESTIMATION AND CONTROL IN FINITE MARKOV-CHAINS

被引:12
作者
ELFATTAH, YM
机构
关键词
D O I
10.2307/1426973
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
引用
收藏
页码:778 / 803
页数:26
相关论文
共 17 条
  • [1] BORKAR V, 1980, IEEE T AUTOMAT CONT, V24, P953
  • [2] Cox D., 1965, THEORY STOCHASTIC PR, DOI 10.1201/9780203719152
  • [3] DENARDO EV, 1973, MATH PROGRAMMING
  • [4] Derman C., 1970, FINITE STATE MARKOVI
  • [5] STRONG CONSISTENCY OF A MODIFIED MAXIMUM-LIKELIHOOD ESTIMATOR FOR CONTROLLED MARKOV-CHAINS
    DOSHI, B
    SHREVE, SE
    [J]. JOURNAL OF APPLIED PROBABILITY, 1980, 17 (03) : 726 - 734
  • [6] Durand E, 1961, SOLUTIONS NUMERIQUES, VII
  • [7] Flerov Y. A., 1972, Journal of Cybernetics, V2, P112, DOI 10.1080/01969727208542916
  • [8] Howard R, 1962, DYNAMIC PROGRAMMING
  • [9] LYUBCHIK LM, 1974, AUTOMAT REM CONTR+, V35, P777
  • [10] Mandl P., 1974, Advances in Applied Probability, V6, P40, DOI 10.2307/1426206