☰ Category

Hierarchical Relative Entropy Policy Search

 

Marketed By :  AV Akademikerverlag   Sold By :  Kamal Books International  
Delivery in :  10-12 Business Days

 

Check Your Delivery Options

Product Out of Stock Subscription

(Notify me when this product is back in stock)

Rs. 2,675

Availability: Out of stock

 
  • Product Description
 

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.

Product Specifications
SKU :COC59497
AuthorChristian Daniel and Gerhard Neumann
LanguageEnglish
BindingPaperback
Number of Pages68
Publishing Year04.01.2014
ISBN9783639475999
Edition1 st
Book TypeComputer networking & communications
Country of ManufactureIndia
Product BrandAV Akademikerverlag
Product Packaging InfoBox
In The Box1 Piece
Product First Available On ClickOnCare.com2015-08-05 00:00:00
0 Review(s)