search

simoninithomas / Deep_reinforcement_learning_Course

Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
http://www.simoninithomas.com/deep-rl-course
3.77k stars 1.22k forks source link

bug in space invaders #68

Open yonigottesman opened 5 years ago

yonigottesman commented 5 years ago

the line: self.Q = tf.reducesum(tf.multiply(self.output, self.actions))

should be: self.Q = tf.reducesum(tf.multiply(self.output, self.actions), axis=1)