def test_determine_board_winner_on_winning_diagonal(self): size = 3 winning_length = 3 board = clean_board(size) side = -1 apply_move_inplace(board, (0, 0), side) apply_move_inplace(board, (1, 1), side) apply_move_inplace(board, (2, 2), side) self.assertEqual(determine_board_winner(board, winning_length), side)
def test_determine_board_winner_on_draw_board(self): board = np.array([[1, -1, 1], [-1, 1, -1], [-1, 1, -1]]) winning_length = 3 self.assertEqual(determine_board_winner(board, winning_length), 0)
def test_determine_board_winner_on_empty_board(self): size = 3 winning_length = 3 board = clean_board(size) self.assertEqual(determine_board_winner(board, winning_length), 0)
def calculate_reward(self, board): return determine_board_winner(board, self.winning_length)