Overview
- Presents an overview of reinforcement learning as applied to robotics
- Provides novel algorithms and novel applications for learning motor skills
- Extensively evaluates the applications of the approaches on benchmark and robot tasks (including ball-in-a-cup, darts, table-tennis, throwing and ball-bouncing) with simulated and real robots
Part of the book series: Springer Tracts in Advanced Robotics (STAR, volume 97)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (7 chapters)
Keywords
About this book
This book presents the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. It discusses recent approaches that allow robots to learn motor.
skills and presents tasks that need to take into account the dynamic behavior of the robot and its environment, where a kinematic movement plan is not sufficient. The book illustrates a method that learns to generalize parameterized motor plans which is obtained by imitation or reinforcement learning, by adapting a small set of global parameters and appropriate kernel-based reinforcement learning algorithms. The presented applications explore highly dynamic tasks and exhibit a very efficient learning process. All proposed approaches have been extensively validated with benchmarks tasks, in simulation and on real robots. These tasks correspond to sports and games but the presented techniques are also applicable to more mundane household tasks. The book is based on the first author’s doctoral thesis, which won the 2013 EURON Georges Giralt PhD Award.
Authors and Affiliations
Bibliographic Information
Book Title: Learning Motor Skills
Book Subtitle: From Algorithms to Robot Experiments
Authors: Jens Kober, Jan Peters
Series Title: Springer Tracts in Advanced Robotics
DOI: https://doi.org/10.1007/978-3-319-03194-1
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer International Publishing Switzerland 2014
Hardcover ISBN: 978-3-319-03193-4Published: 09 December 2013
Softcover ISBN: 978-3-319-37732-2Published: 27 August 2016
eBook ISBN: 978-3-319-03194-1Published: 23 November 2013
Series ISSN: 1610-7438
Series E-ISSN: 1610-742X
Edition Number: 1
Number of Pages: XVI, 191
Number of Illustrations: 2 b/w illustrations, 54 illustrations in colour