Knihu momentálně nemáme skladem
Hierarchical Relative Entropy Policy Search
An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots
Autoři
Více o knize
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.
Nákup knihy
Hierarchical Relative Entropy Policy Search, Christian Daniel, Gerhard Neumann
- Jazyk
- Rok vydání
- 2014
- product-detail.submit-box.info.binding
- (měkká)
Jakmile ji vyčmucháme, pošleme vám e-mail.
Doručení
Platební metody
Navrhnout úpravu
- Titul
- Hierarchical Relative Entropy Policy Search
- Podtitul
- An Information Theoretic Learning Algorithm in Multimodal Solution Spaces for Real Robots
- Jazyk
- anglicky
- Autoři
- Christian Daniel, Gerhard Neumann
- Vydavatel
- AV Akademikerverlag
- Rok vydání
- 2014
- Vazba
- měkká
- Počet stran
- 68
- ISBN13
- 9783639475999
- Kategorie
- Počítače, IT, programování
- Anotace
- 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.