Why does the RL Toolbox not support BatchNormalization layer?

8 views (last 30 days)
Hi.
I'm currently trying DDPG with my own network.
But when I try to use BatchNormalizationLayer, the error message says Batch Normalization is not supported.
I don't see any theoretical reason the batch normalization cannot come in.
Is there any plan to update the toolbox to make it possible?
Or is there a specific reason that the batch normalization cannot come in?
Thanks.
  1 Comment
Abd-Elhamid Nabeel
Abd-Elhamid Nabeel on 11 Sep 2022 at 21:50
Actually i face the same problem, but i thought this would help :
1- calculate the running mean and running STD of the data in Simulink for example (or matlab)
2- make a matlab function in simulink/matlab that could calculate the zscore for each feature through the equation :
X_zs = (X - Xmean)/STD
This would standardize your data.

Sign in to comment.

Accepted Answer

Aditya Patil
Aditya Patil on 6 Apr 2021
This is an known issue, and it might be fixed in any of the upcoming releases.

More Answers (1)

Abd-Elhamid Nabeel
Abd-Elhamid Nabeel on 11 Sep 2022 at 21:50
Actually i face the same problem, but i thought this would help :
1- calculate the running mean and running STD of the data in Simulink for example (or matlab)
2- make a matlab function in simulink/matlab that could calculate the zscore for each feature through the equation :
X_zs = (X - Xmean)/STD
This would standardize your data.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!