Christian Daniel

(Author)

Hierarchical Relative Entropy Policy SearchPaperback, 4 January 2014

Hierarchical Relative Entropy Policy Search
Qty
1
Turbo
Ships in 2 - 3 days
In Stock
Free Delivery
Cash on Delivery
15 Days
Free Returns
Secure Checkout
Buy More, Save More
Turbo Shipping
Print Length
68 pages
Language
English
Publisher
AV Akademikerverlag
Date Published
4 Jan 2014
ISBN-10
3639475992
ISBN-13
9783639475999

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 Details

Authors:
Christian DanielGerhard Neumann
Book Format:
Paperback
Country of Origin:
US
Date Published:
4 January 2014
Dimensions:
22.86 x 15.24 x 0.41 cm
ISBN-10:
3639475992
ISBN-13:
9783639475999
Language:
English
Pages:
68
Weight:
113.4 gm

Need Help?
+971 6 731 0280
support@gzb.ae

About UsContact UsPayment MethodsFAQsShipping PolicyRefund and ReturnTerms of UsePrivacy PolicyCookie Notice

VisaMastercardCash on Delivery

© 2024 White Lion General Trading LLC. All rights reserved.