Hierarchical Relative Entropy Policy Search: An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots - Couverture souple

Daniel, Christian; Neumann, Gerhard

 
9783639475999: Hierarchical Relative Entropy Policy Search: An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots
Couverture souple
ISBN 10 : 3639475992 ISBN 13 : 9783639475999
Editeur : AV Akademikerverlag, 2014

Synopsis

Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performance on motor skill tasks. However, such hierarchical structures cannot be exploited by current policy search algorithms. We concentrate on a basic, but highly relevant hierarchy — the `mixed option’ policy. Here, a gating network first decides which of the options to execute and, subsequently, the option-policy determines the action. Using a hierarchical setup for our learning method allows us to learn not only one solution to a problem but many. We base our algorithm on a recently proposed information theoretic policy search method, which addresses the exploitation-exploration trade-off by limiting the loss of information between policy updates.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performance on motor skill tasks. However, such hierarchical structures cannot be exploited by current policy search algorithms. We concentrate on a basic, but highly relevant hierarchy — the `mixed option’ policy. Here, a gating network first decides which of the options to execute and, subsequently, the option-policy determines the action. Using a hierarchical setup for our learning method allows us to learn not only one solution to a problem but many. We base our algorithm on a recently proposed information theoretic policy search method, which addresses the exploitation-exploration trade-off by limiting the loss of information between policy updates.

Biographie de l'auteur

Christian Daniel studied computational engineering at Technische Universitaet Darmstadt and EPFL Lausanne and is pursuing a PhD in Robot Learning. His research focuses on developing new learning algorithms for autonomous robots, especially in the field of robot skill learning and hierarchical reinforcement learning.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
AV Akademikerverlag
Date d'édition
2014
Langue
anglais
ISBN 10 
3639475992
ISBN 13 
9783639475999
Reliure
Broché
Nombre de pages
68
Coordonnées du fabricant
non disponible
Personne responsable
non disponible