Ph.D. Course: Reinforcement Learning for Autonomous Systems Design 2019-2020
Overview
The course will provide an introduction to Reinforcement Learning in the context of the design of intelligent systems, intelligent agents and intelligent machines. In particular, we will discuss multi-armed bandits, Montecarlo methods, tabular methods, approximation function methods, and Deep Reinforcement Learning.
We will consider a series of applications including classic control theory problems, robotics, games, recommender systems and distributed systems design.
Calendar
Tuesday 1 September 9-11am 2-5pm
Monday 7 September 9-11am 2-5pm
Tuesday 8 September 9-11am
Tuesday 22 September 9-11am
Wednesday 23 September 9-11am
Resources
An extensive list of resources will provide during the module.
Teaching Material
It will be made available here before the lectures.
Delivery Modality
The module will be delivered through Microsoft Teams. The enrolled students will receive a link before the classes.
Assessment
Students will be invited to present and discuss papers during the module.
Enrolment
Please contact me for enrolling in this module (mirco.musolesi[AT]unibo.it).
Slides
Introduction to Reinforcement Learning
Value Approximation Methods in Reinforcement Learning and Deep Reinforcement Learning
Last updated: 8 September 2020.