A New Continuous Action-Set Learning Automaton for Function Optimization
In this paper, we study an adaptive random search method based on learning automaton for solving stochastic optimization problems in which only the noise-corrupted value of objective function at any chosen point in the parameter space is available. We first introduce a new continuous action-set learning automaton (CALA) and theoretically study its convergence properties, which implies the convergence to the optimal action. Then we give an algorithm, which needs only one function evaluation in each stage, for optimizing an unknown function.
Unable to display preview. Download preview PDF.
- 2.Narendra, K.S., Thathachar, K.S.: Learning Automata: An Introduction. Printice-Hall, New York (1989)Google Scholar
- 5.Gullapalli, V.: Reinforcement learning And Its Application on Control. PhD thesis, Deparqement of Computer and Information Sciences, University of Massachusetts, Amherst, MA, USA (February 1992)Google Scholar
- 8.Frost, G.P.: Stochastic Optimization of Vehicle Suspension Control Systems Via Learning Auiomata. PhD thesis, Department of Aeronautical and Automotive Engineering, Loughborough University, Loughborough, Leicestershire, LE81 3TU, UI (October 1998)Google Scholar
- 9.Beigy, H., Meybodi, M.R.: A New Continuous Action-set Learning Automaton for Function Optimization, Tech. Rep. TR-CE-2003-002, Computer Engineering Department, Amirkabir University of Technology, Tehran, Iran (2003)Google Scholar