IJA Automaton: Expediency and ε-Optimality Properties
In this paper, we present a new fixed structure learning automaton (FSSA), called UA, and study its steady state behavior in stationary environments. The proposed automaton characterizes by star shaped transition diagram and each branch of the star contains N states associated with a particular action. This new automaton is an improvement of the Krinsky FSSA and not only ε-optimal and expedient, but also converges to the optimal action faster than the old one.
FSSA Learning automata ε-optimallty.
R.Iraji M. T. Manzuri-Shalmani A. H. Jamalian H. Beigy
Department of Computer Engineering, Sharif University of Technology, Tehran, IRAN
国际会议
Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)
北京
英文
617-622
2006-07-17（万方平台首次上网日期，不代表论文的发表时间）