Sie sind hier: Startseite Teaching SS2022



Foundations of Artificial Intelligence (Lecture)

Jointly organized with Tim Welschehold, and Janek Thomas.

Lectures: pre-recorded, please make sure to watch them during the week before the Q&A; Q&A: Friday 10:00 - 12:00; in hybrid format, for details see ILIAS page.

Deep Learning Lab (Lab Course)

Jointly organized with the Robotics, Robot LearningComputer Vision and Machine Learning labs.
Lecture/Exercises: Tuesday, 10.00-12.00; SR 00-034, Building 051. webpage

Q-Learning: Basics and Modern Extensions (Proseminar)

First meeting on Friday, April 29th. Please follow the link in the title for more information.


Q-Learning: Basics and Modern Extensions (Proseminar)


Prof. Dr. Joschka Boedecker


Jasper Hoffmann, Yuan Zhang, Branka Mirchevska, and Moritz Schneider


In this proseminar, we will introduce the basics of Dynamic Programming, Reinforcement Learning (RL), and Q-Learning in particular. We will cover the classic Q-Learning algorithm, one of the most successful algorithms in the history of RL, and study several modern extensions. In addition, we will introduce general aspects of scientific presentations and academic honesty. 

Course information

Course number:  11LE13S-510-27
place: 10
Zoom session details (can be used for all meeting if you cannot attend in person):

Meeting ID: 638 2089 0181
Passcode: 9hfd7YfF2

Lectures on 03/06/2022 and 17/06/2022 will be in hybrid format.

Attention: room change ! Those wanting to join in person should come to meeting room R42 on the second floor (1st floor) of the new IMBIT building (Georges-Köhler-Allee 201). This is right next to the kitchen area. 

Course Schedule:
Introduction 29/04/2022, 13:00h


Further sessions: 
  • 03/06/2022, 10:00 am, Introduction to Reinforcement Learning, 
  • 03/06/2022, 2:00 pm, MDPs, Value Iteration, Policy Iteration
  • 17/06/2022, 10:00 am, MC and Temporal Difference Methods, Q-Learning, paper selection
  • 24/06/2022, 10:00 am, Advice on preparing academic presentations

Other important dates:
  • 01/07/2022: meet with your supervisor to discuss your paper and clarify any doubts
  • 15/07/2022: meet with your supervisor to discuss a first complete draft of your presentation
  • 28/07/2022: presentations (date changed!)
  • 02/09/2022: three-page summaries are due
Requirements: No prior knowledge of reinforcement learning is necessary. We will introduce the basics to get you up to speed so that you will be able to understand the assigned papers (with the help of your supervisor).
Due to the ongoing pandemic, we will offer the seminar in a hybrid format (see above for a zoom link).



  1. Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method (NFQ)
  2. Human-level Control Through Deep Reinforcement Learning (DQN)
  3. Prioritized Experience Replay (PER)
  4. Dueling Network Architectures for Deep Reinforcement Learning (Dueling DQN)
  5. Deep Reinforcement Learning with Double Q-learning (Double DQN)
  6. Integrated Modeling and Control based on Reinforcement Learning and Dynamic Programming (Dyna-Q)
  7. Continuous Control With Deep Reinforcement Learning (DDPG)
  8. Noisy Networks for Exploration (Noisy Nets)
  9. Addressing Function Approximation Error in Actor-Critic Methods (TD3)


Slides used for the introductory lectures

PDF document icon lecture-joschka-1.pdf — PDF document, 1.10 MB (1158247 bytes)

PDF document icon lecture-joschka-2.pdf — PDF document, 644 KB (660094 bytes)

PDF document icon lecture-joschka-3.pdf — PDF document, 1.09 MB (1147141 bytes)