Teaching Summer 2024

Lecture: Action and Planning in AI: Learning, Models, and Algorithms

  • Models and Solvers in AI
  • State models and heuristic search
  • Logic, SAT solving, and ASP solving
  • Classical planning: language, model, basic algorithms (heuristic search and SAT)
  • Markov Decision Processes (MDPs): basic models and algorithms (VI, PI, RTDP, MCTS)
  • Deep learning (DL) as model and solver; supervised learning, Approx VI, PI, MPI with DL
  • Reinforcement Learning (RL): Value-based and policy gradient methods
  • Current research in planning and RL

Seminar: Advanced Topics in Reinforcement Learning and Planning

Students will present papers from a list of important recent works in machine learning compiled by the professor. Topics include deep and reinforcement learning, and transformer and GNN architectures. The focus will be in the use of these techniques in simple applications that are crisp and easy to understand. The list of papers will also include those underlying well-known learning systems like as Dalle-E, ChaptGPT, Alphazero, Gato, etc.

Proseminar: Causal Inference

In this proseminar, we will discuss causality, causal inference, and causal reasoning, as described by Pearl. While there are many powerful statistical methods for analyzing data, these methods typically focus more on data description and less on finding causal relationships. Based on Pearl’s book on Causal Inference in Statistics, we will define a mathematical notion of causality and discuss several methods how these can be used for causal reasoning. This allows answering questions such as How effective is a given treatment in preventing a disease? and Had I taken the train, would I have arrived earlier?