I found this bit slightly confusing. As far as I understand from the AGZ Nature paper, AGZ does not have a separate policy network p, but uses a single network fθ which outputs both the learned policy p and the estimated probability v that the current player will win the game. Is this what the sentence is referring to?
I found this bit slightly confusing. As far as I understand from the AGZ Nature paper, AGZ does not have a separate policy network p, but uses a single network fθ which outputs both the learned policy p and the estimated probability v that the current player will win the game. Is this what the sentence is referring to?
Yes, AGZ uses the same network for policy and value function.