Admission requirements
No formal requirements.
The course builds on concepts from the bachelor courses Symbolic AI and Machine Learning. Students are expected to program in Python.
Description
For detailed information please visit the course website.
Reinforcement learning is a part of machine learning that focuses on agents interacting in an environment. The goal is to learn a sequence of actions that maximizes the rewards obtained by the agent. The field is rapidly growing, with a wide range of applications in games, robotics, and general decision-making. This course provides a broad introduction to the fundamental (tabular) concepts of Reinforcement Learning. A large part of the course focuses on acquiring hands-on practical experience with applying reinforcement learning algorithms.
Course objectives
After this course, the students are able to:
identify the position of reinforcement learning within the broader machine learning field, and recognize real-world problems suitable for reinforcement learning.
explain the fundamental concepts of sequential decision making, including Markov Decision Processes and Dynamic Programming.
describe the main challenges that appear in reinforcement learning, such as the exploration/exploitation trade-off and the credit assignment problem, and possible solution approaches.
compare different reinforcement learning algorithms, such as model-free versus model-based or on-policy versus off-policy approaches, on their strengths and weaknesses.
implement reinforcement learning algorithms in Python and test them on different environments.
analyze the outcome of reinforcement learning experiments and identify possible explanations.
Timetable
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
Lectures.
Practicals, in which the students can work on the practical assignments, and teachers are available for advice.
Assessment method
Written examination with closed questions (50%)
Assignments (50%)
The final grade for the course is established by determining the weighted average. However, both partial grades need to be above the passing margin. There is an opportunity to retake the exam.The teacher will inform the students how the inspection of and follow-up discussion of the exams will take place.
Reading list
Sutton & Barto, Reinforcement Learning: An Introduction, 2nd edition. This is the main textbook of the course, and it has a free online pdf version.
Plaat, Learning to Play, 1st edition. This is supplementary material, and also comes with a free online pdf version.
Course reader
Registration
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
no remarks