Design of Experiments for Reinforcement Learning
Titre:
Design of Experiments for Reinforcement Learning
ISBN (Numéro international normalisé des livres):
9783319121970
Auteur personnel:
Edition:
1st ed. 2015.
PRODUCTION_INFO:
Cham : Springer International Publishing : Imprint: Springer, 2015.
Description physique:
XIII, 191 p. 46 illus., 25 illus. in color. online resource.
Collections:
Springer Theses, Recognizing Outstanding Ph.D. Research,
Table des matières:
Introduction -- Reinforcement Learning. Design of Experiments -- Methodology -- The Mountain Car Problem -- The Truck Backer-Upper Problem -- The Tandem Truck Backer-Upper Problem -- Appendices.
Extrait:
This thesis takes an empirical approach to understanding of the behavior and interactions between the two main components of reinforcement learning: the learning algorithm and the functional representation of learned knowledge. The author approaches these entities using design of experiments not commonly employed to study machine learning methods. The results outlined in this work provide insight as to what enables and what has an effect on successful reinforcement learning implementations so that this learning method can be applied to more challenging problems.
Auteur collectif ajouté:
Accès électronique:
Full Text Available From Springer Nature Engineering 2015 Packages
Langue:
Anglais