Reinforcement Learning 6 credits

Reinforcement Learning (RL) is a method for learning to make optimal decisions through trial and error. The goal of RL is to achieve an optimal policy for every state in a system. The course covers the underlying formalism of RL known as Markov Decision Processes and fundamental RL algorithms. Examples include dynamic programming. We will demonstrate how to model a problem as a Markov Decision Process and implement basic RL algorithms to solve them. In addition, we will explore various ways to compare and evaluate the performance of learning methods.

This course is intended for professionals.

The course includes three mandatory half-day sessions.