Rotterdam, Netherlands

Reinforcement Learning

when 22 August 2022 - 26 August 2022
language English
duration 1 week
credits 3 EC
fee EUR 1000

This course studies reinforcement learning methods to model and solve management science and marketing problems that involve an explicit trade-off between learning (exploration) and exploiting the information that has been already acquired (e.g., earning). In particular, we will focus on the class of reinforcement learning problems that can be described and modeled as multi-armed bandits. Applications include online advertising, website optimization, clinical trials, new product development, pricing, revenue management, and consumer search.

The 2022 edition of this course has a strong emphasis on algorithms and an applied nature. This course will give you competence to identify multi-armed bandit problems (MABs), properly model them, and identify appropriate methods to solve them. In addition to gaining competence in MABs in general, you will be exposed to the challenges and methods used to tackle online MABs, i.e., problems that need to be solved in real time.

Course leader

Gui Liberali is Professor of Digital Marketing at Erasmus University. His research interests include optimal learning, multi-armed bandits, sequential decision-making and adaptive sampling in various settings.

Target group

This course is targeted at PhD students (and research master students) with a strong background in statistics, econometrics, or computer science.

Course aim

Reinforcement Learning course focuses on using machine learning methods to model and solve problems relevant to management science problems – in particular, those problems involving machines that autonomously make decisions on the behalf of the modeler, as in online settings.

The course is based mainly on reinforcement learning (when we model states and transitions) and multi-armed bandits (when states are not modelled). We will focus on the design, solution, and implementation of learning methods for sequential decision-making under uncertainty. Sequential decision problems involve a trade-off between exploitation (acting on the information already collected) and exploration (gathering more information). These problems arise in many important domains, ranging from online advertising, clinical trials, website optimization, marketing campaign and revenue management.

Credits info

3 EC
Participants who joined at least 80% of all sessions will receive a certificate of participation stating that the summer school is equivalent to a workload of 3 ECTS. Note that it is the student’s own responsibility to get these credits registered at their university.

Fee info

EUR 1000: PhD and Master Students

The course fee covers tuition, course materials, daily lunches and coffee/tea during short breaks, social event including a dinner and farewell drinks. The course fee does not include accommodation. Please ask us about discount options for a student hotel.
EUR 1500: Academics (incl postdocs) € 1.500
Professionals € 2.000

The course fee covers tuition, course materials, daily lunches and coffee/tea during short breaks, social event including a dinner and farewell drinks. The course fee does not include accommodation. Please ask us about discount options for a student hotel.