chess-alpha-zero
chess-alpha-zero copied to clipboard
policy_out dimension
Tell me, how the dimension size was determined in the Dense output layer (None, 1968) in the policy_out header?
That's the number of combinations of (starting square, ending square) for legal chess moves (in a rank, file, diagonal, or knight), plus some extra indicators for promotions. See the original DeepMind paper for the detailed explanation.