As. Poznyak et al., LEARNING AUTOMATA WITH CONTINUOUS INPUTS AND THEIR APPLICATION FOR MULTIMODAL FUNCTIONS OPTIMIZATION, International Journal of Systems Science, 27(1), 1996, pp. 87-95
Citations number
9
Categorie Soggetti
System Science","Computer Science Theory & Methods","Operatione Research & Management Science
This paper deals with the design and the analysis of a new reinforceme
nt scheme for learning automata and its application for multimodal fun
ctions optimization. This reinforcement scheme generalizes the well kn
own Bush-Mosteller scheme with decreasing gain for learning automata w
ith continuous inputs. The theoretical analysis is based on martingale
theory. The conditions associated with the convergence of this scheme
to the optimal pure strategy are stated, and the order of convergence
rate is estimated. The variation domains of the variables of the func
tion to be optimized are discretized into subsets which are associated
to the outputs of the learning automaton. The values of the function
on these subsets are used to construct the continuous automation input
s. Simulation results show the feasibility and the good performance of
this optimization technique.