Time in Year:
Course runs in Semester 1.
Number of Posts:
This course is a MSc level introduction to reinforcement
learning. The first 60% of this course will cover the standard material
in Sutton and Barto's textbook. The latter 40% will focus on more state
of the art topics ranging from policy gradient algorithms to multiagent
The course includes two homework assignments and 3-4 tutorial sessions.
The tutorials will consist of specific exercises set in advance of the
tutorial, and all students are expected to prepare these prior to the
tutorial session. However, it is likely that the students will require
clarifications on the concepts. So, the tutor's job is to lead the
group through the exercises, answer questions etc.
The tutor will also be expected to mark the two homework assignments
for this course (to be verified by the instructor before official
assignment of the marks). The homework assignments will include a
The tutor will need to be familiar with the topics mentioned
above. Having done well in machine learning courses (preferably,
including one on RL) would be suitable preparation.
This post is paid at grade UE06, currently upwards of £12.50/hr.
5 contact hours + 10 preparation hours
Apply by email to firstname.lastname@example.org and copy your email to the instructor.
|Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail:
Please contact our webadmin with
any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright ©
The University of Edinburgh