Section outline

  • The course is open to Allievi of the Scuola Superiore Sant'Anna and Ph. D. students. Please check course prerequisites.

    Schedule

    The course is held on the second term in an online form. Lectures are delivered through Teams, accessible trough this link.

    The course does not have a fixed schedule: register to Moodle notifications to receive information about the next lectures.

    Objective

    Course Prerequisites

    Course prerequisites include knowledge of machine learning fundamentals (e.g. covered through ML course), knowledge of deep learning models and probabilistic learning (e.g. covered through the ISPR course). Knowledge of elements of probability and statistics, calculus and optimization algorithms are also expected. Previous programming experience with Python is expected for project assigments.

    Course Overview

    The course will introduce students to the fundamentals of reinforcement learning (RL). The course will start by recalling the machine learning and statistics fundamentals needed to fully understand the specifics of RL. Then, it will introduce RL problem formulation, its core challenges and a survey of consolidated approaches from literature. Finally, the course will cover more recent reinforcement learning models that combine RL with deep learning techniques.

    Space will be devoted to present RL applications in areas that are relevant for students of industrial and information engineering, such as robotics, pattern recognition, life sciences, material sciences, signal processing, computer vision and natural language processing.  The course will leverage a combination of theoretical and applicative lectures.

    A student successfully completing the course should be able to lay down the key aspects differentiating RL from other machine learning approaches. Given an application, the student should be able to determine (i) if it can be adequately formulated as a RL problem;  (ii) be able to formalize it as such and (iii) identify a set of techniques best suited to solve the task, together with the software tools to implement the solution.

    Textbook and Teaching Materials

    The course textbook is the classical reference book for RL course, altough it might not covering all contents in the lectures.

    Note that the book has also an electronic version which is freely available online.

    [RL] Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second Edition, MIT Press, 2018 (PDF)