• Info: Barcelona Graduate School of Economics, Master of Data Science, 20 hours.

• Description: Reinforcement learning (RL) is a model-based theory of sequential decision-making under uncertainty. It is currently a dominant theoretical framework for understanding and building autonomous agents that can learn and act in the environment on their own. The objective of this course is to introduce students to the main challenges and techniques of modern RL, particularly focusing on computational aspects of dealing with the dynamic nature of the RL problem, and on the statistical challenges posed by the uncertainty of the environment. On both fronts, the goal is to provide a strong understanding of the most common methods and provide a basic algorithmic toolbox for building RL systems. The course puts a strong emphasis on crucial challenges that set RL problems apart from other machine learning problems. Students taking the course are expected to gain the capability to identify and tackle such challenges in various application domains. Various applications relevant to Data Science will be highlighted throughout the course.

• Offerings: 2019/2020.

• Instructor: Hrvoje Stojic and Gergely Neu

Description of the course and other administrative files can be found in organisation folder. However, you will probably care the most about the handouts, you can find these in handouts folder, in the pdf form. These files are generated (usually) from R, using Rmarkdown package; you can find the source files in the source folder. Source files are usually better if you want to copy-paste some of the code, since these are text-files, without any formatting (unlike pdf or html). There is also resources folder where I might put useful things related to the classes - snippets of the code, articles etc. Folder exercises will contain problems sets.

Finally, all the files you find in this folder comes with a license. LICENSE file describes in what ways you can use them further down the line, after the classes are over.