[Icfp04-discuss] Evolutionary Ants
Jens Hauke
hauke at ipd.uka.de
Wed Jun 9 12:52:21 EDT 2004
Detlef Pleiss wrote:
> BTW: The evolutionary approach definitely does require the programming of a
> working simulator :)
... which should run fast :-)
> I also tried starting the evolution with a random 10000 lines ant brain.
> I was amazed to see that even these actually collected some food!
> But as during some time they didn't evolve further than a couple points I
> dropped that approach.
Maybe try the same with less than 300 lines? I got much better results
with very short ant programs (the search space is much smaller and good
strategys dont need much code). The next improvement (i think): leave
the goto's in each line nearly untouched to safe the program flow.
What are good criteria for good ants? Collecting much food or collecting
more than the other? I used the second and saw, that the collecting rate
decrease sometimes from 300 down to 10 during the evolution. Dont know
why that could be better....
Jens
More information about the Icfp04-discuss
mailing list