How can I set the initial value of action space while using Simulink DDPG Agent?

29 Ansichten (letzte 30 Tage)
lei wang
lei wang am 20 Nov. 2024 um 14:48
Beantwortet: Shlok am 29 Nov. 2024 um 6:52
I got a robot model in Simulink, now I want to train the robot using DDPG Agent.
My question is, how can I set the initial value of action space? I want the action starts from some specefic value such as zero.

Antworten (1)

Shlok
Shlok am 29 Nov. 2024 um 6:52
Hi Lei,
DDPG agents are designed to operate in continuous action spaces. Hence, to create a custom continuous action space for the DDPG agent, you can use the “rlNumericSpec” function. rlNumericSpec” helps in creating specifications object for a numeric action or observation channel. By setting the “LowerLimit” to zero, you can specify that the action starts from there.
Here is a sample code:
actionInfo = rlNumericSpec([1,1], 'LowerLimit', 0, 'UpperLimit', 1);
observationInfo = ... // define observation specifications
agtInitOpts = ... // define agent options
agent = rlDDPGAgent(observationInfo,actionInfo,agtInitOpts);
To know more about “rlNumericSpec function, you can refer to the following MATLAB Answer and documentations:

Produkte


Version

R2024b

Community Treasure Hunt

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

Start Hunting!

Translated by