Bookbot

Hierarchical Relative Entropy Policy Search

An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots

Paramètres

  • 68pages
  • 3 heures de lecture

En savoir plus sur le livre

The book explores the significance of hierarchical structures in enhancing scalability and performance in motor skill tasks. It introduces the concept of a "mixed option policy," where a gating network selects which option to execute, followed by an option-policy that determines the action. This hierarchical approach enables the learning of multiple solutions to problems. The algorithm is grounded in an innovative information theoretic policy search method that effectively manages the exploitation-exploration trade-off, minimizing information loss during policy updates.

Achat du livre

Hierarchical Relative Entropy Policy Search, Christian Daniel, Gerhard Neumann

Langue
Année de publication
2014
product-detail.submit-box.info.binding
(souple)
Nous vous informerons par e-mail dès que nous l’aurons retrouvé.

Modes de paiement

Personne n'a encore évalué .Évaluer