Reinforcement Learning (RL) is a set of techniques that can be used to solve sequential decision-making tasks. When combined with deep learning as a function approximator, these algorithms are referred to as deep RL and they have been able to solve a variety of tasks that were previously out of reach for a machine (e.g. the game of Go). Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more.
This course will provide an introduction to deep reinforcement learning techniques and algorithms. Particular focus will be given to aspects related to generalization and how deep RL can be used for practical applications. The course will need of some basic knowledge in RL but will provide the theoretical foundations on the topics covered as well as an introduction to the practical skills necessary to apply (deep) RL techniques. Students will also improve their coding skills by developing (deep) RL agents.
The advanced topics covered during the course will cover algorithms with rich structures that allow for the combination of reasoning and learning as well as how one agent can learn useful abstract representations. Concepts such as temporal abstraction, meta-learning, the reality gap and lifelong learning will also be discussed so that the students get a good understanding of the current challenges in research. Examples of applications such as video games, robotics, self-driving cars, etc. will also be covered.
Course leader
Vincent Francois-Lavet
Target group
Master and PhD students that already know at least the basics of machine learning.
Course aim
Knowledge and understanding:
By the end of this course students will be familiar with different (deep) reinforcement learning algorithms and they will be able to apply them to sequential decision-making tasks under uncertainty, including in the context of high dimensional inputs (e.g. time series). At the end of the course, they will understand how one can solve a sequential decision-making problem close to real-life.
Applying knowledge and understanding:
By the end of this course students will be able to understand how to implement deep RL algorithms, how to compare them and how to apply them in real-life problems.
Making judgements:
By the end of this course students will have an understanding of the key learning techniques for sequential decision-making tasks used in RL, as well as an overview of a few key AI applications for such techniques along with a short discussion on societal impacts.
Learning skills:
Students will be trained in acquiring a set of complex AI and programming skills in a restricted period of time. They will also be trained in applying those techniques on a few specific problems during some of the afternoons that will be focused on practical skills.
Credits info: 2 EC
28 contact hours
Fee info
EUR 550: Tuition fee one-week course
VU Students/PhD candidates and employees of VU Amsterdam* or an Aurora Network Partner €375
Students at Partner Universities of VU Amsterdam €500
Students and PhD candidates at non-partner universities of VU Amsterdam €550
Professionals €650
For further information, please click the "LINK TO ORIGINAL" button below.