Hey!TO whom it may concern!
In line 35
cLoss=tf.reduce_mean(tf.square(rewards-vOut))]
But it seems without the define of vOut and vOut is the output of the NN approximation but I didn't find it.
Thanks in advance!
https://github.com/VisionResearchBlog/Introduction-to-deep-learning-code-examples/blob/master/Chapter-6-03-RL.py