Lecture 1: Martedì 14 novembre 2023
15:30 – 17.45 (1 hour seminar + QA)
“Sala Seminari” - edificio Abacus (U14)
Speaker
Dr. Matteo Hessel
Google DeepMind
Lecture 1: Introduction to Reinforcement Learning
Abstract
In this first lecture we first discuss the role of reinforcement learning (RL) as a formalization of the problem of intelligence. We introduce the key concepts in RL and the main algorithmic challenges (exploration, credit assignment, planning, state construction, function approximation). In the process, we describe a number of field-defining algorithms, from Q-learning and policy gradients to monte-carlo tree search.
Short Bio:
Matteo Hessel is a Staff Research Engineering Manager at Google DeepMind, Honorary Lecturer at University College London, and a co-organizer of the Mediterranean Machine Learning summer school. His research focuses on the integration of deep learning and reinforcement learning methods for building increasingly intelligent agents, capable of mastering a wide range of skills across diverse domains.
contact person for this Seminar: prof. Matteo Palmonari