I have an assignement where I need to use a Genetic Algorithm to solve the TSP (Traveling Salesman Problem). I alrerady implemented a solution in C# but the problem is we're asked to use some kind of method to do the Parameters Tunning (For example to pick the population size, mutation rate, etc..). For now, I only try random values and test..

I tried looking for an example with Taguchi method but I don't seem to understand how would one implement it for a GA problem.

Can anyone put me in the right direction?

  • 2
    $\begingroup$ Tuning the parameters of a GA is very tricky. Your best bet is probably to try multiple combinations of parameters on multiple types of instances, and from that data try to find a pattern of parameters which does generally well. Those parameters should do reasonably well on new instances of the problem. You could also have variable parameters, e.g., add a condition where if you notice that your population converges too quickly, then you increase the mutation rate, etc. $\endgroup$ – Philippe Olivier Mar 14 '18 at 17:04
  • $\begingroup$ Design of experiments can be used in this case? $\endgroup$ – Haytam Mar 14 '18 at 20:22
  • $\begingroup$ That is correct. $\endgroup$ – Philippe Olivier Mar 14 '18 at 21:16
  • $\begingroup$ Is there any good articles that you can advise if possible? THank you. $\endgroup$ – Haytam Mar 14 '18 at 22:14
  • $\begingroup$ I don't have any reference with me right now, but from memory population sizes of 30-100 and mutation rates of a few percentage points are pretty common. $\endgroup$ – Philippe Olivier Mar 14 '18 at 23:12

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.