Exploratory Mean Variance Algorithm

Here is a code in order to replicate experiments made in the article "Continuous-Time Mean–Variance Portfolio Selection: A Reinforcement Learning Framework" by H. Wang and X. Y. Zhou (link: https://arxiv.org/pdf/1904.11392). It was made for the course "Machine Learning in Finance: Theorical Foundations" from J.-D. Fermanian and H. Pham at ENSAE Paris, in collaboration with Maximilien Audeguy and Bastien Cannard.