Giters

yenchenlin / DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The final loss gradient is 1D but network output is (1,2). How is the gradient propagated ?

prateethvnayak opened this issue · comments

commented

I was wondering if the tf.reduce_sum and y are 1d and the mse cost term is 1d, however the gradient to be propagated needs to same dimension as network output i.e (1,ACTIONS) = (1,2). Is the final loss grad just replicated in both dimension ? i.e (1,1) -> (1,2) ?