-
document
-
Van Witteveen, K. (author)
This thesis investigates the applicability of the Probabilistic Inference for Learning COntrol (PILCO) algorithm to large systems and systems with time varying measurement noise. PILCO is a state-of-the-art model-learning Reinforcement Learning (RL) algorithm that uses a Gaussian Process (GP) model to average over uncertainties during learning....
master thesis 2014
Source URL (retrieved on 2024-06-03 08:31): https://repository.tudelft.nl/islandora/search/subject%3A%22Parallel%255C%20Computing%22?collection=education&display=tud_default&f%5B0%5D=mods_name_personal_author_namePart_family_ss%3A%22Van%5C%20Witteveen%22