Artículos relacionados a Hierarchical Relative Entropy Policy Search: An Information...
Hierarchical Relative Entropy Policy Search: An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots - Tapa blanda
Sinopsis
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.
"Sinopsis" puede pertenecer a otra edición de este libro.
Reseña del editor
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.
Biografía del autor
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.
"Sobre este título" puede pertenecer a otra edición de este libro.
Comprar nuevo
Ver este artículo
EUR 31,95
EUR 11,00 gastos de envío desde Alemania a España
Destinos, gastos y plazos de envíoResultados de la búsqueda para Hierarchical Relative Entropy Policy Search: An Information...
Imagen del vendedor
Hierarchical Relative Entropy Policy Search
Publicado por
AV Akademikerverlag Jan 2014, 2014
ISBN 10: 3639475992
ISBN 13: 9783639475999
Nuevo
Taschenbuch
Librería: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Alemania
Calificación del vendedor: 5 de 5 estrellas
Taschenbuch. Condición: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -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. 68 pp. Englisch. Nº de ref. del artículo: 9783639475999
Cantidad disponible: 2 disponibles
Imagen del vendedor
Hierarchical Relative Entropy Policy Search : An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots
Publicado por
AV Akademikerverlag, 2014
ISBN 10: 3639475992
ISBN 13: 9783639475999
Nuevo
Taschenbuch
Librería: AHA-BUCH GmbH, Einbeck, Alemania
Calificación del vendedor: 5 de 5 estrellas
Taschenbuch. Condición: Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - 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. Nº de ref. del artículo: 9783639475999
Cantidad disponible: 1 disponibles
Imagen del vendedor
Hierarchical Relative Entropy Policy Search
Publicado por
AV Akademikerverlag, 2014
ISBN 10: 3639475992
ISBN 13: 9783639475999
Nuevo
Tapa blanda
Librería: moluna, Greven, Alemania
Calificación del vendedor: 5 de 5 estrellas
Condición: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Daniel ChristianChristian 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 autonom. Nº de ref. del artículo: 4991377
Cantidad disponible: Más de 20 disponibles
Imagen del vendedor
Hierarchical Relative Entropy Policy Search
Publicado por
AV Akademikerverlag Jan 2014, 2014
ISBN 10: 3639475992
ISBN 13: 9783639475999
Nuevo
Taschenbuch
Librería: buchversandmimpf2000, Emtmannsberg, BAYE, Alemania
Calificación del vendedor: 5 de 5 estrellas
Taschenbuch. Condición: Neu. Neuware -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.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 68 pp. Englisch. Nº de ref. del artículo: 9783639475999
Cantidad disponible: 2 disponibles