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
Reinforcement learning is a part of machine learning that focuses on agents interacting in an environment, learning which actions to take in order to maximize some kind of reward. 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:
Understand the fundamental concepts that Reinforcement Learning is based on.
Characterize and differentiate between different fundamental approaches to Reinforcement Learning.
Understand the challenges of using Reinforcement Learning in practice, and current advanced solutions to such challenges.
Be able to apply various types of Reinforcement Learning methods in various environments of varying difficulty.
Timetable
The most updated version of the timetables can be found on the students' website.
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. Available for free from http://incompleteideas.net/book/the-book.html
Plaat, Learning to Play, 1st edition. Available for free from https://learningtoplay.net/
Course reader
Registration
Aanmelding voor vakken verloopt via uSis. Hiervoor is de uSis-code van het vak nodig, die te vinden zijn in de Studiegids. Meer info over het inschrijven voor vakken of tentamens is hier te vinden.
MyTimetable
In MyTimetable kun je alle vak- en opleidingsroosters vinden, waarmee jij je persoonlijke rooster kunt samenstellen. Onderwijsactiviteiten waarvoor je in uSis staat ingeschreven, worden automatisch in je rooster getoond. Daarnaast kun je My Timetable gemakkelijk koppelen aan een agenda-app op je telefoon en worden roosterwijzigingen automatisch in je agenda doorgevoerd; bovendien ontvang je desgewenst per e-mail een notificatie van de wijziging.
Vragen? Bekijk de video-instructie, lees de instructie of neem contact op met de ISSC helpdesk.
Brightspace
Inschrijving voor vakken verloopt via uSis. Wanneer je je hier inschrijft voor een bepaald vak krijg je automatisch ook toegang tot de omgeving van dit vak via Brightspace.
Voor meer informatie over Brightspace kun je op deze link klikken om de handleidingen van de universiteit te bekijken. Bij overige vragen of problemen kan contact opgenomen worden met de helpdesk van de universiteit Leiden.
Contact
Riet Derogee, coordinator
Website
Through Brightspace