Reinforcement Learning Lecture

In recent years, Reinforcement Learning (RL) has produced some of the most impressive results in the realm of Machine Learning (ML), especially in game playing (as with the game of Go) and robotics (e.g., RoboCup or autonomously navigating robots). Its view of the ML model as an agent acting within an environment allows for learning by trial and error and reasoning beyond human expert knowledge. RL is a quickly evolving field with a constant inflow of new ideas that leads to an increasing number of algorithms and applications. Therefore this course will begin with teaching the mathematical foundations of RL and provide an overview of the field's development up until today. At the end of the lecture, you will be able to understand the current state of RL research and reason about the theoretical foundations of different RL approaches. The accompanying exercises will teach you how to implement several RL algorithms and develop general RL pipelines, including learning environments, agent evaluation, and hyperparameter settings. At the end of the semester, you will apply your new skills to an interesting RL project of your choice.

• Artificial Intelligence
• Machine Learning
• Deep Learning