there is a caffe implementation of q learning on https://github.com/muupan/dqn-in-the-caffe/blob/master/dqn.prototxt - can perhaps be used.

main purpose would be to show that the q-learning loop i.e. the data input and the conv.net inside the q-learning algorithm is feasible to run on iphone. this can potentially be used to create better Game AI on e.g. Apple TV and iPhone/iPad