Learning Motor Skills - From Algorithms to Robot Experiments

de Jens Kober
État : Neuf
102,54 €
TVA incluse - Livraison GRATUITE
Jens Kober Learning Motor Skills - From Algorithms to Robot Experiments
Jens Kober - Learning Motor Skills - From Algorithms to Robot Experiments

Ce produit vous plaît ? N'hésitez pas à le dire !

102,54 € dont de TVA
Plus que 1 exemplaire(s) disponible(s) Plus que 1 exemplaire(s) disponible(s)
Livraison : entre jeudi 26 mai 2022 et lundi 30 mai 2022
Vente et expédition: Dodax

La 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.


Jens Kober
Jan Peters

Détails du produit

Commentaire illustrations:
XVI, 191 p. 56 illus., 54 illus. in color.
Table des Matières:
Reinforcement Learning in Robotics: A Survey.- Movement Templates for Learning of Hitting and Batting.- Policy Search for Motor Primitives in Robotics.- Reinforcement Learning to Adjust Parameterized Motor Primitives to New Situations.- Learning Prioritized Control of Motor Primitives.
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

Type de média:
Springer International Publishing
Softcover reprint of the original 1st ed. 2014
Nombre de pages:
This overview by an award-winning researcher of the ways reinforcement learning can be applied to robotics includes new algorithms and applications. It assesses their success in benchmark tasks such as darts, table tennis, and ball-throwing and bouncing.

Données de base

Type d'produit:
Livre de poche
Date de publication:
27 août 2016
Dimensions du colis:
0.235 x 0.155 x 0.012 m;
102,54 €
Nous avons recours aux cookies sur notre site internet afin de rendre votre visite plus agréable et ergonomique. Nous vous invitons ainsi à cliquer sur "Accepter les cookies" ! De plus amples informations sont disponibles dans notreDéclaration de protection des données.