• Overview of Chinese core journals
  • Chinese Science Citation Database(CSCD)
  • Chinese Scientific and Technological Paper and Citation Database (CSTPCD)
  • China National Knowledge Infrastructure(CNKI)
  • Chinese Science Abstracts Database(CSAD)
  • JST China
  • SCOPUS
Advanced Search
HU Guang-hua. A stochastic approximation for parameters Markov decision processesJ. Journal of Yunnan University: Natural Sciences Edition, 2003, 25(5): 377-380.
Citation: HU Guang-hua. A stochastic approximation for parameters Markov decision processesJ. Journal of Yunnan University: Natural Sciences Edition, 2003, 25(5): 377-380.
shu

A stochastic approximation for parameters Markov decision processes

    Abstract
  • A stochastic gradient algorithm for average reward Markov decision processes (MDP) that depends on a parameter vector is proposed.A new gradient of the object function is given and a stochastic approximation algorithm that bases on a single sample path is presented.Finally,a convergence of the gradient (with probability 1) is provided.
    • FullText(HTML)
  • loading
    • References (0)
    • Related Articles

Catalog

    Turn off MathJax
    Article Contents

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return