How to extract neural network of reinforcement learning agent?

6 次查看（过去 30 天）
Yihao Wan
Yihao Wan 2021-3-4
编辑： Emmanouil Tzorakoleftherakis 2021-3-11
Is there a way to get the neural network of trained reinforcement learning agent?

请先登录，再回答此问题。

采纳的回答

Emmanouil Tzorakoleftherakis
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 个评论
显示 3更早的评论
Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis 2021-3-5
编辑：Emmanouil Tzorakoleftherakis 2021-3-11
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.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning with Simulink 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

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

Start Hunting!

Translated by