92858 - Autonomous and Adaptive Systems M

Course Unit Page

Academic Year 2020/2021

Learning outcomes

The goal of this module is to provide a solid introduction to the design of autonomous and adaptive computing systems from a theoretical and practical point of view. Topics will include principles of autonomous system design, reinforcement learning, game-theoretic approaches to cooperation and coordination, bio-inspired systems, complex adaptive systems, and computational social systems. The module will also cover several practical applications from a variety of fields including but not limited to distributed and networked systems, mobile 1) and ubiquitous systems, robotic systems, and vehicular and transportation systems. 2) Si propone la modifica degli obiettivi formativi delle seguenti attività:

Course contents

Introduction to the design of adaptive and autonomous systems, intelligent agents and intelligent machines.

Review of Machine Learning/Deep Learning fundamentals.

Introduction to Reinforcement Learning (RL): multi-armed bandits, Montecarlo methods, tabular methods, approximation function methods, and deep RL.

Applications of RL to games. 

Applications of RL to classic control theory problems and robotics.

Applications of RL to networked and distributed systems design.

RL and cognitive sciences&neuroscience.

Intelligent machines and creativity: Generative Deep Learning, AI and the Arts.

Introduction to algorithmic game theory for autonomous systems: cooperation and coordination, social dilemmas, and Multi-Agent Reinforcement Learning.

Bio-inspired adaptive systems.

Autonomous and mobile robots.

Driverless cars and autonomous transportation systems.

Ethical implications of AI and autonomous systems.

Machine intelligence, super-intelligence, self-awareness, controllability and the future.

The course will include labs in which we will discuss implementation oriented aspects of the techniques and methodologies presented during the course.


During the course, the instructor will provide an extensive list of pointers (scientific papers, technical documentation, books, etc.) for each topic.

Useful textbooks for the course include the following:

  • Francois Chollet. Deep Learning with Python. Manning. 2017.
  • Dario Floreano and Claudio Mattiussi. Bio-inspired Artificial Intelligence: Theories, Methods and Technologies. MIT Press. 2008.
  • David Foster. Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play. O’Reilly. 2019.
  • Robin R. Murphy. Introduction to AI Robotics. Second Edition. MIT Press. 2019.
  • Peter Norvig and Stuart J. Russell. Artificial Intelligence: A Modern Approach. Fourth Edition. MIT Press. 2020.
  • Max Pumperla and Kevin Ferguson. Deep Learning and the Game of Go. Manning. 2019.
  • Richard R. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press 2018.

Teaching methods

Lectures in the classroom and in the lab.

Assessment methods

Oral exam (90%) and class participation (10%).



Teaching tools

The teaching material of the module can be found at this link.

Office hours

See the website of Mirco Musolesi