From your excellent writeup (thank you!):
History of State: Since Go is not completely observable from the current state of the board, the neural network also takes as input the boards from the last 7 time steps. This is a feature of the game itself, and other games such as Chess and Othello would only require the current board as input.
This is not strictly speaking true, as chess also requires knowledge of the previous states of the board, to determine for example if castling is permitted, or if you may capture en passant amongst others.
From your excellent writeup (thank you!):
This is not strictly speaking true, as chess also requires knowledge of the previous states of the board, to determine for example if castling is permitted, or if you may capture en passant amongst others.