Action value exceeds the boundry of the final layer activation fucntion of the actor

2 次查看（过去 30 天）
awcii
awcii 2023-6-17
评论： awcii 2023-6-19
Hi,
I'm using DDPG agent for my RL application with Matlab 2022a version.
I want to take action between 0 and 1 value. To do this, i use SigmoidLayer function at the final layer of the action. However, it exceed the 0-1 boundry. I also tried to use tanh with
scalingLayer(Scale=0.5,Bias=0.5);
,but it exceed the boundry again. How it can be possible?
Meanwhile, i also tried to use
actInfo = rlNumericSpec([1 1],LowerLimit=0,UpperLimit=1);
to limit action, yes it limits the action value but it doesn't scale it. it just act as a saturation block (like putting a saturation block in simulink in front of the action output). So, with this way, the RL works wrong.
How can achive to take action between 0 and 1?
  3 个评论
显示 1更早的评论
awcii
awcii 2023-6-19
however, deacreasing the noise variance cause a lack of exploration during training. So, in totaly, i need a new solution.

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 Policies and Value Functions 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by