Asymptotic behaviour of a learning algorithm
作者:
M. A. L. THATHACHAR,
K. M. RAMACHANDRAN,
期刊:
International Journal of Control
(Taylor Available online 1984)
卷期:
Volume 39,
issue 4
页码: 827-838
ISSN:0020-7179
年代: 1984
DOI:10.1080/00207178408933209
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
The paper considers a learning automaton operating in a stationary random environment. The automaton has multiple actions and updates its action probability vector according to the linear reward — ϵ penalty (LR-ϵp) algorithm. Using weak convergence concepts it is shown that for large time and small values of parameters in the algorithm, the evolution of the action probability can be represented by Gauss-Markov diffusion.
点击下载:
PDF (282KB)
返 回