gamultiobj save the optimum value and population in each generation (iteration)

Question

Thushara De Silva 2020-1-9

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/499554-gamultiobj-save-the-optimum-value-and-population-in-each-generation-iteration

评论： Thushara De Silva 2020-5-11

I use gamultiobj to do a multiobjective optimization. It is possible to see the changes of parato front graphically in each iteration through the option setting. I can see the final pareto set, variable set and population of all the variables at the end of optimization. However, I want to save the population set and pareto solution set over each iteration over the optimization. In my problem I use population size 50 for 12 variables. Please help me on this.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Alan Weiss 2020-1-10

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/499554-gamultiobj-save-the-optimum-value-and-population-in-each-generation-iteration#answer_409564

You can use a custom output function, as in this example, to record the population and Pareto front. In the State Structure, the Pareto front is the set of individuals of rank 1, I believe.

Alan Weiss

MATLAB mathematical toolbox documentation

3 个评论
显示 1更早的评论隐藏 1更早的评论

Alan Weiss 2020-5-11

Please look at the link to the State Structure in my previous answer. You will find that gamultiobj passes a state structure that has the information you are looking for to a plot function or output function. Use the plot function or output function to record whatever you want to variables in your workspace, as in the example in the link in my previous answer for recording the history.

As for setting an initial random seed, use rng.

If I have answered your questions, please Accept the answer.

Alan Weiss

MATLAB mathematical toolbox documentation

Thushara De Silva 2020-5-11

Assuming I will use Output Function as the example, can you please write the additional lines of codes to record the distance, FunEval, spread, and setting rng?

请先登录，再进行评论。