Jump to content
  • Advertisement
Sign in to follow this  
  • entries
  • comments
  • views

My crappy ANN

Sign in to follow this  


OK, so after my hard-drive went bottom-side-up I've got things going and I have my little space flight environment running.

Now I have set up an ANN to teach the space ship to pursue a target moving along a line at a constant speed. Unforunately, the results have been notable only in that they are stupendously crappy. I'm training the ANN using a genetic algorithm so I know that convergence is going to be slow, but the problem seems to be that the network always falls into some local minimum, which is invariably crappy.

What to do...

I don't want to abandon the neural network approach just yet. I want to figure out exactly what's "wrong" with it and how I can improve it; I mean, it's not like this is a problem that hasn't been solved before with ANNs!
Sign in to follow this  


Recommended Comments

There are no comments to display.

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Advertisement

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

We are the game development community.

Whether you are an indie, hobbyist, AAA developer, or just trying to learn, GameDev.net is the place for you to learn, share, and connect with the games industry. Learn more About Us or sign up!

Sign me up!