Avsnittsöversikt
-
More information may appear later
Course Instructors
Niel Hens, Hasselt University and University Antwerp
Pieter Libin, Vrije Universiteit Brussel
Course contents:This course covers the following topics:
-
General introduction to epidemic modeling and reinforcement learning
-
Compartment and metapopulation models
-
Individual-based models
-
Practical session on metapopulation and individual-based models [Python]
-
Reinforcement learning: intuition and problem setting
-
Value functions, Q-learning (including Deep Q-Networks), and Policy gradient (including PPO).
-
Multi-armed bandits
-
Practical session on Q-learning [Python]
-
Policy optimisation for epidemic decision making
-
Use case: Q-learning in a metapopulation model [Python]
Software: Python and a set of free software libraries
Follow up: Homework projects for those interested
Time and Place
All lectures take place at Stockholm University in Campus Albano, house 1, level 2 (signs will show which room). See "Registration and Venue" page for further details.Lecture times (includes also problem solving, tutorials, computer sessions, ...):
Monday June 22: 9.00-10.30, 11.00-12.30, 14.00-15.30, 16.00-17.30
Tuesday June 23: 9.00-10.30, 11.00-12.30, 14.00-15.30, 16.00-17.30
Wednesday June 24: 9.00-10.30, 11.00-12.30
General prerequisites
It is expected that course participants have basic knowledge of statistics and mathematics and rudimentary knowledge of infectious disease epidemiology. It is also expected that participants have basic computer software knowledge and preferably are familiar with the software R.
IMPORTANT: All participants are expected to bring a laptop with R installed on it.
Additional prerequisites for this course
Programming in a scripting language (such as R, Python)
Relevant literature
[1] http://incompleteideas.net/book/the-book-2nd.html
[2] https://link.springer.com/chapter/10.1007/978-3-030-67670-4_10
[3] https://link.springer.com/chapter/10.1007/978-3-030-10997-4_28
-