[galib] dynamic mutation rate

[Camilo Gomez]

Hi,
 
I would like to know if anyone is using dynamic mutation rate adjustment
to perturb the GA when it stalls at a point so that it can jump
somewhere else in the search space?
 
What I am doing is monitoring the scores of the previous generations to
see if the mutation rate needs to be changed so that the GA continues to
evolve to a better solution. To adjust the mutation rate I am using: 
 
ga.pMutation(NewMutationRate)
 
Unfortunately it seems that this does not actually update the mutation
rate dynamically. Do you guys have any suggestion?
 
Camilo Gómez
 
 
"About 60 million transistors were built this year just for you, with
another 60 million for each of your friends, plus 60 million for every
other man, woman, and child on Earth. By 2010, the number should be
around one billion transistors per person per year. "
 
http://www.embedded.com/story/OEG20021217S0039
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.mit.edu/pipermail/galib/attachments/20040229/0231d6e4/attachment.htm