def get_next_state(self, board, player, move):
if (action == 8 * 8):
return (board, player)
b = Board()
b.pieces = np.copy(board)
move = (int(action / 8), action % 8)
b.executeMove(player, move)
return (b.pieces, -player)
def getNextState(self, board, player, action):
# if player takes action on board, return next (board,player)
# action must be a valid move
if action == self.n * self.n:
return (board, -player)
b = Board(self.n)
b.pieces = np.copy(board)
move = (int(action / self.n), action % self.n)
b.execute_move(move, player)
return (b.pieces, -player)
def getGameEnded(self, board, player):
# return 0 if not ended, 1 if player 1 won, -1 if player 1 lost
# player = 1
b = Board(self.n)
b.pieces = np.copy(board)
if b.has_legal_moves(player):
return 0
if b.has_legal_moves(-player):
return 0
if b.countDiff(player) > 0:
return 1
return -1
def getValidMoves(self, board, player):
# return a fixed size binary vector
valids = [0] * self.getActionSize()
b = Board(self.n)
b.pieces = np.copy(board)
legalMoves = b.get_legal_moves(player)
if len(legalMoves) == 0:
valids[-1] = 1
return np.array(valids)
for x, y in legalMoves:
valids[self.n * x + y] = 1
return np.array(valids)
def getScore(self, board, player):
b = Board(self.n)
b.pieces = np.copy(board)
return b.countDiff(player)