Your description of AlphaStar is wrong; that’s the architecture for AlphaGo. One network to evaluate positions and one to suggest good moves. IIRC AlphaStar has three networks which are (roughly) build, move, look.
Your description of AlphaStar is wrong; that’s the architecture for AlphaGo. One network to evaluate positions and one to suggest good moves. IIRC AlphaStar has three networks which are (roughly) build, move, look.