Normalization process in Reinforcement Learning

6 次查看（过去 30 天）
Unmanned Aerial and Space Systems
评论： Unmanned Aerial and Space Systems 2022-11-28
Hi everyone, I have a question about 'Normalization', I'm asking that how do this process operate in ==>featureInputLayer?
The documentation says us that "Normalization" part is performed automatically. Is that true? Because when the featureInputLayer is created, 'Normalization' is defined "None" as following:
----------------------------------------------------------------------------------
featureInputLayer(numObservations,'Normalization','none','Name','observation')
----------------------------------------------------------------------------------
But, How it normalize observations/actions? Can you explain it clearly?
UASS
  3 个评论
显示 1更早的评论
Jyo Deshmukh
Jyo Deshmukh 2022-11-23
In fact when I use normalization with any other option, I get an error:
Error using rl.internal.model.DLNetworkModel>localValidateLayer
Set 'Normalization' parameter
of featureInputLayer to 'none'.
Unmanned Aerial and Space Systems
Unmanned Aerial and Space Systems 2022-11-28
yes, i agree with you, how can we use other options? the question is how we gonna change this option with other?

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Logical 的更多信息

标签

产品


版本

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by