Abstract
Policy Mirror Descent is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning due to the inaccessibility of explicit action-value functions. We address this challenge by...
Abstract
...
The Networked Systems research group, led by Proff. Alessandro Di Giorgio and Antonio Pietrabissa, aims at developing control methodologies in the context of networked systems. Besides classical control methods, such as model predictive control, optimal control and robust control,...
The research in this area is at the intersection between Artificial Intelligence and Robotics, and has its roots in the early AI research that targeted robots as embodiments of the intelligent agent.
The key scientific challenge, which has received a...
