 Our proposed method uses a quantum classical hybrid simulator to design quantum algorithms assisted by machine learning, where the learning system evolves into a quantum algorithm for a given problem with the help of a classical main feedback system. This method is applicable for designing quantum oracle-based algorithms, and we showed that our simulator can faithfully learn a quantum algorithm for solving a Deutsch-Jorzer problem using Monte Carlo simulations, with a learning time proportional to the square root of the total number of parameters rather than showing the exponential dependence found in classical machine learning-based methods. This article was authored by Joel Hobang, Jung Hee-Ri-Woo, Seo Kwon-Yoo, and others.