Autonomous and Adaptive Systems 2023-24

Overview

This course will provide the students with a solid understanding of the state of the art and the key conceptual and practical aspects of the design, implementation and evaluation of intelligent machines and autonomous systems that learn by interacting with their environment. The course also takes into consideration ethical, societal and philosophical aspects related to these technologies.

Link to official course page containing syllabus and textbooks


Teaching Team

Mirco Musolesi (Instructor)

Giorgio Franceschelli (Teaching Assistant)


Notices

The enrolment for the exam sessions in June and July 2024 is now open.


Mailing List of the Course

Please join the mailing list of the course by signing up through this form.

The instructor will use this mailing list exclusively to send all the information regarding the module, including organisation of the lectures, additional material, exams, etc. Please sign-up using your institutional address.


Slides of the Lectures

Introduction to the Course

Intelligent Agents and Machines

Introduction to Reinforcement Learning

Multi-armed Bandits

Temporal Difference Methods

Deep Learning and Neural Architectures - First Part

Deep Learning and Neural Architectures - Second Part

Deep Learning and Neural Architectures - Third Part

Value Approximation Methods

Monte Carlo Methods

Policy Gradient Methods

Generative Learning

Multi-agent Systems


Slides of the Practicals

Introduction to Gym

Introduction to TensorFlow

Advanced TensorFlow for Reinforcement Learning


Slides of the Tutorials

Machine Creativity


Slides about Project Guidelines

Project Guidelines


Notebooks

Notebook Keras MNIST

Notebook DQN Cartpole

Notebook DQN Atari Game



Last updated: 17 May 2024.