It is a using a genetic algorithm so learning lies in the mutation and crossover of chromosomes as well as selection of the fittest individuals.
https://github.com/xviniette/FlappyLearning/blob/gh-pages/Ne...
https://github.com/xviniette/FlappyLearning/blob/gh-pages/Ne...
While visiting a lab in Paris, I saw some researchers using neuroevolution to teach a bird-like robot how to fly.
some links related to neuroevolution:
https://en.wikipedia.org/wiki/Neuroevolution_of_augmenting_t...
Are there other good ways of training a neural network in this kind of scenario?
in some cases you might lack an easy way to calculate a fitness score out of the NN performance, which is needed to run the GA.
i tried training a simple NN with a stupid hill climber some time ago but quickly hit a roadblock even with very few neurons because of local minima ... or maybe bugs.
i guess for more complicated problems the pure GA training method might just not be "cost effective" (i.e. time/quality tradeoff).
Different applications, though. Backtracking in the normal sense needs input and expected output (e.g. lots of training data), while GA/EA learns to solve it without explicit wrong/correct actions, just the score at the end.