How to extract neural network of reinforcement learning agent?
조회 수: 4 (최근 30일)
이전 댓글 표시
Yihao Wan
2021년 3월 4일
편집: Emmanouil Tzorakoleftherakis
2021년 3월 11일
Is there a way to get the neural network of trained reinforcement learning agent?
댓글 수: 0
채택된 답변
Emmanouil Tzorakoleftherakis
2021년 3월 5일
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
댓글 수: 5
Emmanouil Tzorakoleftherakis
2021년 3월 5일
편집: Emmanouil Tzorakoleftherakis
2021년 3월 11일
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.
추가 답변 (0개)
참고 항목
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!