News for hackers. Stuff that matters.

A comment on Teaching AI to race using NNs and genetic algorithms. Parent comment

Re:Teaching AI to race using NNs and genetic algorithms by Lord_Fixer on Tuesday August 30, 2016 @02:22PM (#12392550)
After 100 generations thay actually have learned to move correctly, that's impresive. But they move very slowly. But for 100 nodes in a single hidden layer it takes them only around 10-20 generations to learn for me (not 80), and they race really fast.
[ Parent | on HN ]
Re:Teaching AI to race using NNs and genetic algorithms by breckinloggins on Tuesday August 30, 2016 @02:27PM (#12392606)
That actually sounds right. For me, they took 80 or so to race what I subjectively thought of as "well", but they only took 10 or 20 - as you said - to roughly figure out what they were doing.

And I figured out what the behavior difference was: before they finally "figure it out", they spend most of their time spinning in place or moving in "epicycles", for lack of a better term.

Thanks for the project; it's been great fun!

[ Parent | on HN ]