Ph.D. Course: Advanced Topics in Reinforcement Learning 2020-2021


In this module we will cover advanced topics in (Deep) Reinforcement Learning, such as function approximation methods with policy networks and actor-critic architectures, and Multi-Agent Reinforcement Learning. The module will cover both theoretical foundations and applications. We will discuss key recent papers in this area and we will outline the open challenges in this field.


Please note that this is an advanced module on Reinforcement Learning. We will briefly review the basics of Reinforcement Learning, but the instructor will assume good knowledge of Reinforcement Learning fundamentals including multi-armed bandits and tabular methods.

Before taking this module, the instructor suggests to review Chapters 1-2-3-4-6 of the following book:

Richard S. Sutton and Andrew G. Barto. Reinforcement Learning. An Introduction. Second Edition. MIT Press. [Link to book website]

Calendar of the Lectures

13 April 2021 9-11am (Online)

20 April 2021 9-11am (Online)

27 April 2021 9-11am (Online)

4 May 2021 9-11am (Online)

11 May 2021 9-11am (Online)

The module will be delivered through Microsoft Teams. The enrolled students will receive a link before the classes.


An extensive list of resources will be provided during the module.

Teaching Material

It will be made available here before the lectures.


Students will be invited to present and discuss papers during the module.


In order to enroll you should fill this form. The information will be used only for sending information about this module.


Introduction to the Module and Overview of RL Basics

Introduction to Deep Learning

Value Approximation Methods

Policy Gradient Methods

Last updated: 3 May 2021.