Section: Computer Science and Engineering
Tutor: GATTI NICOLA
Advisor: RESTELLI MARCELLO Major Research topic
:Risk-Averse Reinforcement LearningAbstract:
Reinforcement Learning (RL) has recently proved to be highly successful in a variety of tasks, from robotic control to videogames, obtaining and, sometimes, beating human performance by means of a learning process that does not rely on specific domain knowledge. Indeed, its general framework could be applied, in principle, in every context in which, at each interaction, it is possible to obtain as feedback the state of the environment, and a reward signal which is representative of the performance w.r.t. the goal. However, the standard RL objective, which consists in maximizing the expected value of the reward sum, does not always capture human goals, which may involve also keeping the risk under control.
In an Autonomous Navigation setting, e.g., it is essential for a vehicle to reach the target position, but it is also of extreme importance to avoid any failure which can damage its motion capabilities. While some work has been done for handling risk constraints (on Variance, VaR, CVaR , etc.), current solutions approach consists in proposing novel algorithms, tailored for the specific case, that often do not have the performance of state-of-the-art algorithms. The subject of this thesis is the development of risk-averse Reinforcement Learning techniques, in order to ease the direct application of state-of-the-art Reinforcement Learning algorithms in a wider area of real problems, where risk-aversion is essential.