Deep_reinforcement_learning_Course icon indicating copy to clipboard operation
Deep_reinforcement_learning_Course copied to clipboard
verified publisher icon simoninithomas

bug in space invaders

Open yonigottesman opened this issue 6 years ago • 0 comments

the line: self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_))

should be: self.Q = tf.reduce_sum(tf.multiply(self.output, self.actions_), axis=1)

yonigottesman avatar Sep 29 '19 10:09 yonigottesman