Admission requirements
It is strongly recommended that the student:
has successfully completed the master courses ‘Reinforcement Learning’ and ‘Introduction to Deep Learning’.
is interested in scientific research.
is proficient in programming, machine learning, presenting and report writing.
Warnings:
The course has a limited number of available spots. Students should check availability and sign up by contacting the responsible teacher in advance.
Peer feedback is an important aspect of the course, and presence at the weekly meetings is mandatory.
Description
For detailed information please visit the course website.
Deep Reinforcement Learning (RL) is a field of artificial intelligence that has attracted much attention, for example being the first computer programme to beat the human world champion in the game of Go. In this seminar we will dive into recent deep reinforcement learning papers.
The structure of the course is as follows. We first jointly read up on the deep reinforcement learning research field as a whole, after which you select - in groups of two - a specific deep RL paper of your interest. The paper may focus on i) a novel reinforcement learning algorithm, or ii) application of reinforcement learning to a specific problem area. The main goal of the course is to understand the paper and replicate its results. Throughout the course, you present your progress to the group for feedback, and you give feedback to others. If time permits, you may i) investigate your own novel extension of your paper or ii) try to improve reinforcement learning performance in your specific application area. At the end of the course, you write a report about your results, based on the guidelines of a true research paper.
Course objectives
After this course, the students are able to:
explain key topics in deep reinforcement learning research.
critically assess a deep reinforcement learning paper.
evaluate the experiment results of the replication of a deep reinforcement learning paper.
create a novel reinforcement learning algorithm or novel reinforcement learning application (optional).
give critical feedback on reinforcement learning research projects presented by peers.
present the progress of their reinforcement learning research project to peers.
write a paper about their reinforcement learning research project according to scientific standards.
Timetable
The most recent timetable can be found at the Computer Science (MSc) student website.
You will find the timetables for all courses and degree programmes of Leiden University in the tool MyTimetable (login). Any teaching activities that you have sucessfully registered for in MyStudymap will automatically be displayed in MyTimetable. Any timetables that you add manually, will be saved and automatically displayed the next time you sign in.
MyTimetable allows you to integrate your timetable with your calendar apps such as Outlook, Google Calendar, Apple Calendar and other calendar apps on your smartphone. Any timetable changes will be automatically synced with your calendar. If you wish, you can also receive an email notification of the change. You can turn notifications on in ‘Settings’ (after login).
For more information, watch the video or go the the 'help-page' in MyTimetable. Pleas note: Joint Degree students Leiden/Delft have to merge their two different timetables into one. This video explains how to do this.
Mode of instruction
Lecture/seminar sessions, in which students present results to the class, and the teachers and class provide peer feedback.
Practicals, in which the students work on their research project, and teachers are available for advice.
Assessment method
The final grade is determined by:
Written paper: 80%.
Presentation of results to class: 10%
Peer feedback & class participation: 10%
To pass the course, the student needs to be present in at least 80% of the lectures. In case of a fail grade, there is an opportunity to retake the written exam, but only the same research project.
Reading list
The reading list changes per year and is available from the course website.
Registration
Due to limited capacity, you need to register for this course in advance. You register for the course by sending an email to the teacher before August 1. After confirmation of admittance to the course you can register for the course in MyStudyMap, see information below.
From the academic year 2022-2023 on every student has to register for courses with the new enrollment tool MyStudymap. There are two registration periods per year: registration for the fall semester opens in July and registration for the spring semester opens in December. Please see this page for more information.
Please note that it is compulsory to register for every exam and retake. Not being registered for a course means that you are not allowed to participate in the final exam of the course.
Extensive FAQ on MyStudymap can be found here.
Contact
Lecturer: Thomas Moerland
Remarks
n/a