How the generated parameters of agent are related PI/PID controller in reinforcement learning algorithm
4 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Kurnam Gnaneshwar
el 11 de En. de 2023
Comentada: Emmanouil Tzorakoleftherakis
el 19 de Feb. de 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 comentarios
Respuesta aceptada
Emmanouil Tzorakoleftherakis
el 24 de En. de 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 comentarios
Emmanouil Tzorakoleftherakis
el 19 de Feb. de 2023
Not sure I fully understand. The actor model in the example is fully editable
Más respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!