Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?

1 visualización (últimos 30 días)
When I want to resume training of an agent, I simply load it and set the "resetexperiencebuffer" option to false, but this does not avoid the exploration (depending on epsilon) to start anew. Is there any way to make the agent start from the exact point it left off without manually setting the epsilon value?

Respuesta aceptada

Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis el 22 de Jun. de 2021
Hello,
This is currently not possible, but it is a great enhancement idea. I have informed the developers about your request and it will be considered for a future release.

Más respuestas (0)

Productos


Versión

R2021a

Community Treasure Hunt

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

Start Hunting!

Translated by