• applications to portfolio optimization problems
• machine learning
• stochastic optimal control

In the first part of the thesis, it is given an introduction to the most important concepts and results employed in stochastic optimal control problems. We provided the derivation of the Dynamic Programming principle, Bellman principle and HJB equation. After that, we presented an approach that employs stochastic optimal control methods to portfolio optimization problems.
In the second part of the thesis, we focused on machine learning and reinforcement learning techniques, presenting two different machine learning models to approach the portfolio optimization task