Teaching — Dr. Simon Hirländer
Courses taught at Paris Lodron University Salzburg (PLUS) in the areas of Reinforcement Learning, AI, and Data Science.
Current Courses (2025/2026)
KI: Grundlagen und Anwendung
Introductory course (KS) covering foundations and applications of Artificial Intelligence.
Undergraduate AI
Advanced Reinforcement Learning and Agentic AI Systems
Advanced course covering cutting-edge topics in reinforcement learning and the design of autonomous AI agents capable of long-term planning and decision-making in complex environments.
Graduate RL AI
Introduction to Deep Reinforcement Learning
Foundational course introducing deep reinforcement learning algorithms, combining neural networks with RL. Topics include DQN, Policy Gradients, Actor-Critic methods, and practical implementations.
Graduate RL Deep Learning
Introduction to Reinforcement Learning
Comprehensive introduction to reinforcement learning covering Markov Decision Processes, value-based methods (Q-learning, SARSA), policy-based methods, and exploration-exploitation trade-offs.
Undergraduate/Graduate RL
Advanced Topics in Reinforcement Learning
Advanced seminar covering recent research in RL including model-based RL, meta-learning, multi-agent systems, safe RL, and applications in robotics and control.
Graduate RL Research
Special Topics in Data Science
Course exploring specialized topics in data science including time series analysis, Bayesian methods, uncertainty quantification, and applications in industrial systems.
Graduate Data Science
Mathematical Foundations in Precision Medicine
Interdisciplinary course exploring mathematical and statistical methods for personalized medicine, including dynamic treatment regimes and reinforcement learning in healthcare.
Graduate Medicine Math
AI Bachelor Seminar
Seminar for undergraduate students covering current topics in artificial intelligence, providing an introduction to AI research methods and paper presentation skills.
Undergraduate AI Seminar
Teaching Philosophy
My teaching approach emphasizes the connection between theory and practice. I believe in:
- Hands-on Learning: Students implement algorithms and work on real-world problems
- Interdisciplinary Thinking: Connecting RL concepts to physics, control theory, and domain applications
- Research Integration: Exposing students to cutting-edge research and open problems
- Industry Relevance: Bridging academic concepts with practical industrial applications
Bootcamps & Workshops
Beyond regular courses, I organize intensive training programs:
2nd RL Bootcamp (2025)
Intensive bootcamp held in Salzburg (Sep 17-19, 2025). Covered advanced policy gradients, actor-critic methods, and continuous control.
1st RL Bootcamp (2024)
Inaugural bootcamp bringing together students and researchers for hands-on RL training.
RL Coffee
Monthly informal meetup (first Friday of each month) for RL researchers and practitioners.
RL4AA Workshops
International workshops on Reinforcement Learning for Autonomous Accelerators (CERN, DESY, KIT, SLAC).