I am working lately on batch normalization for the last couple of days, but I just can't seem to solve it on how to apply it. So, to give the full code to you, I will just send the implementation.

Implementation DDPG Code: https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/blob/master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py

and fun thing is that this github creator actually also has a batch normalization implementation: https://github.com/MorvanZhou/Tensorflow-Tutorial/blob/master/tutorial-contents/502_batch_normalization.py. However, I don't get how he does it, since his videos are in Chinese.

I did a lot of research so far on how to implement it, however I usually get ValueErrors for "NoneType" or "False_Fn has to return a value".

The name differences between everything makes me even more confused on where what should be. Also, to avoid confusion, I am trying to add this version of batch normalisation: https://www.tensorflow.org/api_docs/python/tf/layers/batch_normalization

If you have any idea, suggestion on how to implement this, more than welcome.

  • $\begingroup$ Implementation questions belong on the Data Science community $\endgroup$ – Philip Raeisghasem Mar 11 '19 at 19:13
  • $\begingroup$ Not sure why my flag to migrate was declined. This is clearly an implementation question, which is off-topic according to the Help Center. $\endgroup$ – Philip Raeisghasem Mar 13 '19 at 9:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.