Learning Objectives
1.1 Subject-specific Competencies
Students
• gain insight into the theory and applications of reinforcement learning
• learn to analyze the challenges in a reinforcement learning application and to identify promising
learning approaches.
• are able to assess for which problems reinforcement learning is particularly well suited and which
disadvantages exist with regard to this.
• understand, explain, and classify relevant basic concepts.
1.2 Methodological Competencies
Students
• can evaluate the properties of different learning strategies depending on the problem.
• are able to implement selected methods with the programming language. Python and with the help
of suitable frameworks.
1.3 Interdisciplinary Competencies
Students
• can evaluate solutions in highly complex environments.
• are able to acquire detailed knowledge for solving specific problems on their own.
• learn to discuss and derive solutions within a team.
Course Content
• Introduction to Decision Making (Reward Hypothesis, Markov Reward and Decision Processes,
Value and Policy Iteration, Bellman Equation).
• Basic principles (Exploration and Exploitation, On and Off-policy learning, model-free and model-
based policy learning.
• Algorithmic principles: Q-learning, SARSA, TD-learning, function approximation.
• Introduction to deep reinforcement learning as well as basic concepts of deep learning.
Literature
R. S. Sutton, A. G. Barto; Reinforcement Learning - An Introduction; MIT Press; 2nd Edition;
2018
• C. Szepesvari; Algorithms for Reinforcement Learning; Morgan & Claypool Publishers; 2010 |
