Karolis issues

Repositories
Issues
Comments

Results 1 issues of


                                            Karolis

Possible mistake in Deep Q Learning Space Invaders notebook

Hey. Shouldn't `self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_))` in DQN class be `self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_), axis=1)`, i.e. reduced along columns so that the output length of `self.Q` is equal to the...