How to extract neural network of reinforcement learning agent?
4 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Yihao Wan
el 4 de Mzo. de 2021
Editada: Emmanouil Tzorakoleftherakis
el 11 de Mzo. de 2021
Is there a way to get the neural network of trained reinforcement learning agent?
0 comentarios
Respuesta aceptada
Emmanouil Tzorakoleftherakis
el 5 de Mzo. de 2021
For critics:
criticNet = getModel(getCritic(trained_agent))
For actors
actorNet = getModel(getActor(trained_agent))
Note that you can use this regardless of whether the agent is trained or not.
Hope this helps
5 comentarios
Emmanouil Tzorakoleftherakis
el 5 de Mzo. de 2021
Editada: Emmanouil Tzorakoleftherakis
el 11 de Mzo. de 2021
What I mentioned above should work then. Use the DL blocks or ML Function block to bring the trained network into Simulink, and the plain C codegen feature I mentioned in my other answer to deploy. Plain C code generation shipped in R2021a.
Más respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!