Literatur |
A comprehensive list of literature will be provided during the lectures Some introductory text books on the topic: - „Reinforcement Learning“, Richard Sutton & Andrew Barto, MIT Press - „Hands-On Machine Learning with Scikit-Learn & TensorFlow“ Aurélien Géron, O’Reilly |
Lerninhalte |
Within the course „Artificial Intelligence VII“, we will cover approaches and algorithms for reasoning under uncertainty. Based on sensory inputs, which are usually noisy, intelligent systems have to decide which action to take. During the course, the following approaches to tackle this problem are introduced: - Markov Decision Processes (MDP) - Partially Observable Markov Decision Processes (POMDP) - Reinforcement Learning (RL) - inverse Reinforcement Learning (iRL) - Advanced discriminative models (MRF, CRF) - plan, intent and activity recognition In addition, we will discuss the mathematics of the corresponding algorithms in detail. |