amaneureka / T-Rex

MLP based network which learns and play T-Rex game all by itself.
http://amaneureka.github.io/T-Rex/
295 stars 37 forks source link

[Game] Need to test with 'PTERODACTYL' #2

Open amaneureka opened 8 years ago

amaneureka commented 8 years ago

Current network works on object coming towards it, It does not care what is the 'Y-Pos' of it. Add this feature to network and enable 'PTERODACTYL' for testing.

amaneureka commented 8 years ago

Possible solution: push 'y' coordinate also in the input matrix, And let the network handle everything else. ;-)

Changes should include, number of neurons in input layer, array push (y-pos feature) and maybe number of neurons in hidden layers.