search

tianxiaoy9 / Data-driven-deep-reinforcement-learning-controller-for-DC-DC-buck-converter-feeding-CPLs

Source code for deep reinforcement learning in MATLAB
17 stars 4 forks source link

About training agent #2

Open ydxuesheng opened 7 months ago

ydxuesheng commented 7 months ago

Hello, sorry to bother you again. I have a few questions for you about training agents.

  1. For the process from 200w to 500w, that is, the 25.mat file, I retrained myself, and the hyperparameter parameters of the training did not change. Why are there some differences between my results and yours? Besides, the training ends in the fifth round, do I need to modify the parameter 'StopTrainingValue'?
  2. In the process of using matlab for reinforcement learning, can the trained agent be retrained?
  3. How to set these hyperparameters of training and reward module properly? Thank you！