Examining the ϵ-optimality property of a tunable FSSA

@article{Jamalian2007ExaminingT,
  title={Examining the ϵ-optimality property of a tunable FSSA},
  author={A. H. Jamalian and Reza Iraji and A. R. Sefidpour and M. T. Manzuri-Shalmani},
  journal={6th IEEE International Conference on Cognitive Informatics},
  year={2007},
  pages={169-177}
}
In this paper, a new fixed structure learning automaton (FSSA), with a tuning parameter for amount of its rewards, is presented and its behavior in stationary environments will be studied. This new automaton is called TFSLA (tunable fixed structured learning automata). The proposed automaton characterizes by star shaped transition diagram and each branch of the star contains N states associated with a particular action. TFSLA is tunable, so that the automaton can receive reward flexibly, even… CONTINUE READING
Highly Cited
This paper has 19 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Reinforcement Automata-Based Solutions" IEEE Trans. Syst., Man, learning control of nonlinear multi-link system,

  • I. 0. Bucak, M. A. Zohdy
  • J. Cybern., Part B,
  • 2005

Continuous action Optimization

  • M. N. Howell, T. J. Gordon
  • IEEE Trans. Syst., Man, Cybern., Part…
  • 2002

Learning Automata and [18] G

  • A. S. Pomyak, K. Najim
  • i. PApadmitoua.tomakaliandAnSl Stochastic…
  • 1997
1 Excerpt

Learning Neurocomputing 61

  • K. Narendra, M.A.L. Thathatchar
  • pp. 381-394, 2004. Automata: An Introduction…
  • 1989
1 Excerpt

Automaton Theory and Modeling of Biological Systems

  • M. L. Tsetlin
  • New York: Academic
  • 1974
2 Excerpts

Similar Papers

Loading similar papers…