Currenly I'm trying to reimplement alphazero in pure c++ using libtorch to accomodate my project's need. But when I training my model, I found out that the value loss doesn't decrese at all after even ~2000 iterations and the policy loss decreases pretty fast from the very begining.
Have anybody met any similar issue when developing your alphazero project? And could you give some suggestion of the cause of my issue based on your experience?
Many apreciates