Zero knowledge Chess Engine * Establish the search tree * Use a neural net to prune the search tree Definitionin: Value network V - f(board) What is V? V = -1 black wins board state V = 0 draw board state V = 1 white wins board state Should we fix the value of the initial board state What's the value of "about to lose"? Simpler: All positions where white wins = 1 All positions where draw = 0 All positions where black wins = -1 State(Board): Pieces(1+6*2 - 16) * Universal ** Blank ** En passant * Pieces ** Pawn ** Bishop ** Knight ** Rook ** Rook (can castle) ** Queen ** King Extra state: * To move * Castle available x2 * En passant (target square - 64 bits) 8x8x5 = 260 bits (vector of 0 or 1)