Model-Based Policy Gradients An empirical study on linear quadratic environments Ângelo Gregório Lovatto Thesis presented to the Institute of Mathematics and Statistics of the University of São Paulo in partial fulfillment of the requirements for the degree of Master of Science Program: Ciência da Computação Advisor: Profª. Drª. Leliane Nunes de Barros Durante o desenvolvimento deste trabalho o autor recebeu auxílio financeiro da CAPES São Paulo February 28, 2022