teaching

Courses, tutorials, and learning resources.

M.Sc. AI and Robotics · University of Technology Nuremberg

Introduction to Reinforcement Learning

Lecture materials for the Introduction to Reinforcement Learning course. The course comprises twelve lectures, with materials published here as they become available.

Open Lecture 2: Dynamic Programming Open Lecture 3: Model-Free Prediction

Lecture sequence

  1. Introduction to Reinforcement Learning (CM)
  2. Dynamic Programming — Interactive HTML lecture
  3. Model-Free Prediction — Interactive HTML lecture
  4. Model-Free Control I (CM)
  5. Model-Free Control II (CM)
  6. Policy Gradient Methods I
  7. Policy Gradient Methods II
  8. Policy Gradient Methods III
  9. Model-Based Reinforcement Learning I (CM)
  10. Model-Based Reinforcement Learning II (CM)
  11. Introduction to Exploration
  12. Exploration in Deep RL and Modern RL Theory Questions

Lectures marked (CM) are taught by Christopher Mutschler.

The course schedule also includes a guest lecture, with the topic to be announced.

Selected tutorials

  • Foundations of Reinforcement Learning and Control — INFORMS tutorial.
  • Contextual Bandits — Reinforcement Learning Summer School, Barcelona, 2023. Watch the recording.
  • Foundations for Continual Reinforcement Learning — EWRL keynote, 2024.