Introduction to Reinforcement Learning with a focus on Temporal Difference techniques

Abstract

The talk will give a general introduction to Reinforcement Learning aimed at covering the basics underpinning the core concepts in RL. Therefore, the discussion will focus on one of the most crucial RL-techniques, namely Temporal Difference Learning, by providing both theoretical justifications and concrete applications.

Speaker

• Giulia Lombardi - PhD in Mathematics, University of Trento

Contact person

• Luigi Amedeo Bianchi, University of Trento

The seminar corresponds to the final exam of Reinforcement Learning, a planned course within Giulia Lombardi’s  first year PHD study programme