help-octave
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

problem with ga function variable bounds


From: George Kousiouris
Subject: problem with ga function variable bounds
Date: Mon, 18 May 2009 13:46:12 +0300
User-agent: Thunderbird 2.0.0.21 (Windows/20090302)

Hi,

I am using ga package version 0.9.4. I am trying to launch the genetic algorithm with lower and upper bounds for the variables but this does not seem to work. It seems that the values are inside the interval [0,1]. So I took the values from this interval and normalized them in order to fall inside the intervals I wanted. But while it was working well for 30-40 generations, then values over 1 or negative appeared. Does anyone have any idea why this is happening? I also tried PopInitRange which again worked for a while and then it gave values outside the interval. I guess this option may refer only to the initial population range.

Snippet from my code:

% Fitness function
fitnessFunction = @script2;
% Number of Variables
nvars = 19;

% Linear inequality constraints
Aineq = [];
Bineq = [];
% Linear equality constraints
Aeq = [];
Beq = [];
% Bounds
lb = [3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1];
ub = [10 13 13 13 13 13 13 13 13 13 13 8 8 8 8 8 8 8 8];
% Nonlinear constraints
nonlconFunction = [];

%options = gaoptimset;
% Modify some parameters

options = gaoptimset('Generations' ,3,'PopulationSize',20);
%NORMALIZATION GIA TA YPOLOIPA DIASTHMATA


%options = gaoptimset(options,'StallTimeLimit' ,Inf);
%options = gaoptimset(options,'Display' ,'off');
% Run GA

[X,FVAL,REASON,OUTPUT,POPULATION,SCORES] = ga(fitnessFunction,nvars,Aineq,Bineq,Aeq,Beq,lb,ub,nonlconFunction,options)





reply via email to

[Prev in Thread] Current Thread [Next in Thread]