Central Library

Normal view MARC view ISBD view

Design of Experiments for Reinforcement Learning [electronic resource] / by Christopher Gatti.

By: Gatti, Christopher [author.].
Contributor(s): SpringerLink (Online service).
Material type: materialTypeLabelBookSeries: Springer Theses, Recognizing Outstanding Ph.D. Research: Publisher: Cham : Springer International Publishing : Imprint: Springer, 2015Description: XIII, 191 p. 46 illus., 25 illus. in color. online resource.Content type: text Media type: computer Carrier type: online resourceISBN: 9783319121970.Subject(s): Engineering | Logic design | Artificial intelligence | Computational intelligence | Engineering | Computational Intelligence | Logic Design | Artificial Intelligence (incl. Robotics)Additional physical formats: Printed edition:: No titleDDC classification: 006.3 Online resources: Click here to access online
Contents:
Introduction -- Reinforcement Learning. Design of Experiments -- Methodology -- The Mountain Car Problem -- The Truck Backer-Upper Problem -- The Tandem Truck Backer-Upper Problem -- Appendices.
In: Springer eBooksSummary: 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.
    average rating: 0.0 (0 votes)
No physical items for this record

Introduction -- Reinforcement Learning. Design of Experiments -- Methodology -- The Mountain Car Problem -- The Truck Backer-Upper Problem -- The Tandem Truck Backer-Upper Problem -- Appendices.

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.

There are no comments for this item.

Log in to your account to post a comment.