Tune PI Controller Using Reinforcement Learning

Question

嘻嘻 2023-10-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2035244-tune-pi-controller-using-reinforcement-learning

回答： Emmanouil Tzorakoleftherakis 2023-10-23

How is the initial value of the weight of this neural network determined? If I want to change my PI controller to a PID controller, do I just add another weight to this row that is initialGain = single([1e-3 2])?

This code is from the demo "Tune PI Controller Using Reinforcement Learning."

initialGain = single([1e-3 2]);

actorNet = [

featureInputLayer(numObs)

fullyConnectedPILayer(initialGain,'ActOutLyr')

];

actorNet = dlnetwork(actorNet);

actor = rlContinuousDeterministicActor(actorNet,obsInfo,actInfo);

Can my network be changed to look like the following：

actorNet= [

featureInputLayer(numObs)

fullyConnectedPILayer(randi([-60,60],1,3), 'Action')]

3 个评论
显示 1更早的评论隐藏 1更早的评论

嘻嘻 2023-10-18

I want the weights of the network to represent the controller parameters, the input of the network to represent the error and the error integral and its first derivative, and the final output of the network to be the control instructions

嘻嘻 2023-10-18

I'm not really sure. What do you think of this scheme?

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Emmanouil Tzorakoleftherakis 2023-10-23

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2035244-tune-pi-controller-using-reinforcement-learning#answer_1339046

I also replied to the other thread. The fullyConnectedPILayer is a custom layer provided in the example - you can open it and see how it's implemented. So you can certainly add a third weight for the D term, but you will most likely run into other issues (e.g. how to approximate the error derivative)