trial and error ANN
Posted 11 January 2013 - 11:35 PM
I have a fitness function, and how I plan on adjusting weights is for each output, i test random deviations of the output with the fitness function till i achieve a better result (just ever so slightly just for the next frame), then i back propagate this...
would this work?
Posted 12 January 2013 - 02:05 PM
Posted 14 January 2013 - 11:47 PM
Posted 15 January 2013 - 09:48 AM
You create networks of animations and it blends between them based on input events.
Posted 15 January 2013 - 03:08 PM
Posted 15 January 2013 - 11:10 PM
But setting up the physics system and neural net learning is really challenging.
oh well, i guess god wanted it to be a challenge anyway...
Posted 16 January 2013 - 09:27 AM
It's power comes from the fact that it can blend multiple animations in a realistic way.
The stuff that really makes a difference is the reaction system, for example someone getting shot. Traditionally we have one or two death animations, but with their system it actually has almost an infinite set of reactions depending on the nature of the event.
Makes a big difference.
1 user(s) are reading this topic
0 members, 1 guests, 0 anonymous users