Learning Theory and Reinforcement Learning

This is a brief overview of the course Learning Theory and Reinforcement Learning given in spring 2020. More details regarding the course will be given further on.

Course goals

In the first course module, we aim to ensure that all students master the basic mathematical tools (statistical framework, optimization, concentration) that constitute the foundations of the theory of Machine Learning.

The second course module applies the tools introduced in the first module to recent solutions for supervised and unsupervised learning problems (SVM, Kernel methods, Deep learning, as well as clustering and cluster validation).

The third course module contains an exhaustive introduction of theoretical and practical aspects of reinforcement learning (MDP, dynamic programming, Q-learning, policy-gradient, learning with function approximation, and recent Deep RL algorithms).

Organization

The course is offered in spring 2019 and organized into three different modules:

Course module #1: Mathematical Foundations of ML

KTH

Prerequisites: Anyone admitted to WASP-AI should be able to attend this module. Basic background in probability and optimization is required.

Course module #2: Supervised and Unsupervised Learning

KTH

Prerequisites: The same prerequisites as for the first module hold. In addition, basic notions and results in linear algebra would be helpful. The second module builds upon the first.

Course module #3: Reinforcement Learning

Örebro

Prerequisites: The same prerequisites as for the first two modules hold. In addition, basic understanding of computational complexity, convergence of sequences, variance and bias of Monte Carlo estimators, and Markov chains would be helpful. The third module is complementary to modules one and two and their content is assumed to be known and understood.

Examination

To pass the course all modules have to be completed.