Submitted by Yendor on Sun, 2003-06-01 19:12
Please tell me that I am missing something, and not that I'm trying to do
the impossible.
I have hand-designed a fram named George. Admittedly, I haven't fully
designed his brain as I was hoping evolution would perfect it for me. There
are a couple things that George's brain definitely needs though, which have
been strategically placed throughout his NN.
With everything set up, I send George through a NN-only run - only to find
that my hand-coded neurons have been corrupted long before George even knows
how to walk.
Try as I might, I can't find a way to preserve the contents of George's
hand-coded neurons while allowing evolution the opportunity to modify all
the others.
Any suggestions? Or is this a request for the developers?
Forums:
Re: Directing Evolution
"Yendor" wrote in message
news:bbe7gm$rif$1@cancer.cs.put.poznan.pl...
> Please tell me that I am missing something, and not that I'm trying to do
> the impossible.
>
> I have hand-designed a fram named George. Admittedly, I haven't fully
> designed his brain as I was hoping evolution would perfect it for me.
There
> are a couple things that George's brain definitely needs though, which
have
> been strategically placed throughout his NN.
>
> With everything set up, I send George through a NN-only run - only to find
> that my hand-coded neurons have been corrupted long before George even
knows
> how to walk.
>
> Try as I might, I can't find a way to preserve the contents of George's
> hand-coded neurons while allowing evolution the opportunity to modify all
> the others.
>
> Any suggestions? Or is this a request for the developers?
>
>
I have found some adjustable Simulation parameters in the Genetics section
which may have something to do with the rate of mutation of different
sections of a creature. Each of the three genetic coding methods have
different adjustable options. My guess is by reducing some of the parameters
to 0 you might be able to concentrate on mutating specific areas of your
creature. I am not sure what crosser over evolution may do to George so it
might me safer to reduce this parameter to 0 initially.
Re: Directing Evolution
> I have found some adjustable Simulation parameters in the Genetics section
> which may have something to do with the rate of mutation of different
> sections of a creature. Each of the three genetic coding methods have
> different adjustable options. My guess is by reducing some of the parameters
> to 0 you might be able to concentrate on mutating specific areas of your
> creature. I am not sure what crosser over evolution may do to George so it
> might me safer to reduce this parameter to 0 initially.
Regarding mutation on specific genetic formats: yes,
these detailed parameters may be helpful to fine-tune
evolution.
Yes, crossing over should be disabled in this case.
Please discuss further ideas on framsticks creatures
development in the framsticks.users forum. This one
is dedicated to software development.
MacKo