OVERVIEW

The course presents algorthms for autonomous intelligent agents that interact with an unknown environment. In particular, the environment is simulated by a virtual world created through video games technology. The course will introduce the Reinforcement Learning e del Deep Reinforcement Learning approaches.

AIMS AND CONTENT

LEARNING OUTCOMES

The course provides algorithms and strategies to develop autonomous agents using a game engine.

AIMS AND LEARNING OUTCOMES

The aim of the course is to provide the basis for the design and development of software algorithms capable of autonomously acting within a virtual world. The student is introduced to different concepts of Reinforcement Learning and supported through extensive exercises during lectures. The course aims to train a professional figure capable of designing and implementing complex software applications using video game technologies and artificial intelligence algorithms.

PREREQUISITES

The students should have basic knowledge of programming and machine learning.

TEACHING METHODS

The course is composed of a set of frontal lessons and a set of practice sessions. During the frontal lesson, the teacher presents the topics providing also examples of live code that are tested on simualted environements. Students can use their own laptops during the lecture in order to reproduce what is proposed by the teacher. During the practice sessions, the students have to face up with real problems that they should solve by applying the techniques learnied during the lectures.

SYLLABUS/CONTENT

The titles of the main contents discussed during frontal lessons are provided in the following list. Notebooks can be obtained at the following lins: Reinforcement Learning and Deep Reinforcement Learning

01 - Markov Decision Process
02 - Dynamic Programming
03 - Exploration vs Exploitation
04 - Policy Evalutaion
05 - Policy Improvement
06 - Learning and Planning
07 - Function Approximation
08 - Deep Q-network
09 - Actor-Critic methods
10 - DDPG and PPO

RECOMMENDED READING/BIBLIOGRAPHY

• Lecture notes and notebooks (from Github)
• Books (as references):
  - Miguel Morales, Grokking Deep Reinforcement Learning, Manning
  - Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: an Introduction, MIT Press

TEACHERS AND EXAM BOARD

Exam Board

RICCARDO BERTA (President)

ALESSANDRO DE GLORIA

FRANCESCO BELLOTTI (President Substitute)

LESSONS

LESSONS START

https://corsi.unige.it/8732/p/studenti-orario

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The exam is an oral examination on the theoretical topics covered during lectures or a review of a recent scientific paper. In particular, the student has to provide fluency in the description of the main concept of autonomous agents development.

ASSESSMENT METHODS

During the oral exam, the teacher asks the student to illustrate some concepts learned in class. For each concept, the student has to present the definition, the conditions of applicability and pros/cons in relation to other approaches. During the examination, the teacher verifies that the concepts have been learned at a level of knowledge that allows the student to apply them in real cases.

Exam schedule