Normalization process in Reinforcement Learning
11 ビュー (過去 30 日間)
古いコメントを表示
Unmanned Aerial and Space Systems
2022 年 5 月 4 日
コメント済み: Unmanned Aerial and Space Systems
2022 年 11 月 28 日
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 件のコメント
Jyo Deshmukh
2022 年 11 月 23 日
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'.
回答 (0 件)
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!