Cargando…
Learning motor skills: from algorithms to robot experiments
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...
Autores principales: | , |
---|---|
Lenguaje: | eng |
Publicado: |
Springer
2014
|
Materias: | |
Acceso en línea: | https://dx.doi.org/10.1007/978-3-319-03194-1 http://cds.cern.ch/record/1635115 |
_version_ | 1780934507168268288 |
---|---|
author | Kober, Jens Peters, Jan |
author_facet | Kober, Jens Peters, Jan |
author_sort | Kober, Jens |
collection | CERN |
description | 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. |
id | cern-1635115 |
institution | Organización Europea para la Investigación Nuclear |
language | eng |
publishDate | 2014 |
publisher | Springer |
record_format | invenio |
spelling | cern-16351152021-04-21T21:30:09Zdoi:10.1007/978-3-319-03194-1http://cds.cern.ch/record/1635115engKober, JensPeters, JanLearning motor skills: from algorithms to robot experimentsEngineeringThis 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.Springeroai:cds.cern.ch:16351152014 |
spellingShingle | Engineering Kober, Jens Peters, Jan Learning motor skills: from algorithms to robot experiments |
title | Learning motor skills: from algorithms to robot experiments |
title_full | Learning motor skills: from algorithms to robot experiments |
title_fullStr | Learning motor skills: from algorithms to robot experiments |
title_full_unstemmed | Learning motor skills: from algorithms to robot experiments |
title_short | Learning motor skills: from algorithms to robot experiments |
title_sort | learning motor skills: from algorithms to robot experiments |
topic | Engineering |
url | https://dx.doi.org/10.1007/978-3-319-03194-1 http://cds.cern.ch/record/1635115 |
work_keys_str_mv | AT koberjens learningmotorskillsfromalgorithmstorobotexperiments AT petersjan learningmotorskillsfromalgorithmstorobotexperiments |