How the generated parameters of agent are related PI/PID controller in reinforcement learning algorithm
4 views (last 30 days)
Show older comments
Kurnam Gnaneshwar
on 11 Jan 2023
Commented: Emmanouil Tzorakoleftherakis
on 19 Feb 2023
Respected all,
The following example shows the PI controller design using TD3 reinforcement learning algorithm. How the agent parameters are related to PI controller gains for the following example.
0 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 24 Jan 2023
This example uses an actor network that works as a PI controller. This is possible because we are using a customer layer called fullyConnectedPILayer.
After training, the weights of the fullyConnectedPILayer are effectively the weights of the tuned PI controller.
Hope that helps
2 Comments
Emmanouil Tzorakoleftherakis
on 19 Feb 2023
Not sure I fully understand. The actor model in the example is fully editable
More Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!