Reinforcement learning, particularly if enhanced by deep networks, is now more than ever mainstream research. I will go through a very basic overview of reinforcement learning, to focus on financial applications and eventually discuss the concept of algorithmic risk.
Marcello Paris comes from a Ph.D. in Mathematics and spent many years in market finance and computational IT, mainly for applications to derivates modelling and risk measurement. Current activities cover: UniCredit R&D's research collaborations and development (coding) of computing solutions. Current research interests: topological methods in data analysis and machine learning, FPGA computing.