Adaptive Representations for Reinforcement Learning (Registro nro. 202503)

MARC details
000 -LÍDER
fixed length control field 03514nam a22004335i 4500
001 - NÚMERO DE CONTROL
control field u374623
003 - IDENTIFICADOR DEL NÚMERO DE CONTROL
control field SIRSI
005 - FECHA Y HORA DE LA ULTIMA TRANSACCIÓN
control field 20160812084243.0
007 - CAMPO FIJO DE DESCRIPCIÓN FIJA--INFORMACIÓN GENERAL
fixed length control field cr nn 008mamaa
008 - ELEMENTOS DE LONGITUD FIJA -- INFORMACIÓN GENERAL
fixed length control field 100709s2010 gw | s |||| 0|eng d
020 ## - NÚMERO INTERNACIONAL NORMALIZADO PARA LIBROS
International Standard Book Number 9783642139321
-- 978-3-642-13932-1
040 ## - FUENTE DE CATALOGACIÓN
Transcribing agency MX-MeUAM
050 #4 - SIGNATURA TOPOGRÁFICA DE LA BIBLIOTECA DEL CONGRESO
Classification number Q342
082 04 - NÚMERO DE CLASIFICACIÓN DECIMAL DEWEY
Classification number 006.3
Edition number 23
100 1# - ASIENTO PRINCIPAL--NOMBRE PERSONAL
Personal name Whiteson, Shimon.
Relator term author.
245 10 - MENCIÓN DE TITULO
Title Adaptive Representations for Reinforcement Learning
Medium [recurso electrónico] /
Statement of responsibility, etc. by Shimon Whiteson.
264 #1 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE
Place of production, publication, distribution, manufacture Berlin, Heidelberg :
Name of producer, publisher, distributor, manufacturer Springer Berlin Heidelberg,
Date of production, publication, distribution, manufacture, or copyright notice 2010.
300 ## - DESCRIPCIÓN FÍSICA
Extent XIII, 116 p.
Other physical details online resource.
336 ## - CONTENT TYPE
Content type term text
Content type code txt
Source rdacontent
337 ## - MEDIA TYPE
Media type term computer
Media type code c
Source rdamedia
338 ## - CARRIER TYPE
Carrier type term online resource
Carrier type code cr
Source rdacarrier
347 ## - DIGITAL FILE CHARACTERISTICS
File type text file
Encoding format PDF
Source rda
490 1# - MENCIÓN DE SERIE
Series statement Studies in Computational Intelligence,
International Standard Serial Number 1860-949X ;
Volume/sequential designation 291
505 0# - NOTA DE CONTENIDO
Formatted contents note Part 1 Introduction -- Part 2 Reinforcement Learning -- Part 3 On-Line Evolutionary Computation -- Part 4 Evolutionary Function Approximation -- Part 5 Sample-Efficient Evolutionary Function Approximation -- Part 6 Automatic Feature Selection for Reinforcement Learning -- Part 7 Adaptive Tile Coding -- Part 8 RelatedWork -- Part 9 Conclusion -- Part 10 Statistical Significance.
520 ## - NOTA DE RESUMEN, ETC.
Summary, etc. This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.
596 ## -
-- 19
650 #0 - ASIENTO SECUNDARIO DE MATERIA - TERMINO TEMÁTICO
Topical term or geographic name as entry element Engineering.
650 #0 - ASIENTO SECUNDARIO DE MATERIA - TERMINO TEMÁTICO
Topical term or geographic name as entry element Artificial intelligence.
650 14 - ASIENTO SECUNDARIO DE MATERIA - TERMINO TEMÁTICO
Topical term or geographic name as entry element Engineering.
650 24 - ASIENTO SECUNDARIO DE MATERIA - TERMINO TEMÁTICO
Topical term or geographic name as entry element Computational Intelligence.
650 24 - ASIENTO SECUNDARIO DE MATERIA - TERMINO TEMÁTICO
Topical term or geographic name as entry element Artificial Intelligence (incl. Robotics).
710 2# - ASIENTO SECUNDARIO - NOMBRE CORPORATIVO
Corporate name or jurisdiction name as entry element SpringerLink (Online service)
773 0# - HOST ITEM ENTRY
Title Springer eBooks
776 08 - ADDITIONAL PHYSICAL FORM ENTRY
Relationship information Printed edition:
International Standard Book Number 9783642139314
830 #0 - ASIENTO SECUNDARIO DE SERIE--TITULO UNIFORME
Uniform title Studies in Computational Intelligence,
International Standard Serial Number 1860-949X ;
Volume number/sequential designation 291
856 40 - LOCALIZACIÓN Y ACCESO ELECTRÓNICOS
Public note Libro electrónico
Uniform Resource Identifier <a href="http://148.231.10.114:2048/login?url=http://link.springer.com/book/10.1007/978-3-642-13932-1">http://148.231.10.114:2048/login?url=http://link.springer.com/book/10.1007/978-3-642-13932-1</a>
942 ## - TIPO DE MATERIAL (KOHA)
Koha item type Libro Electrónico
Existencias
Estado de retiro Fuente de clasificación Colección Ubicación permanente Ubicación actual Fecha de ingreso Total Checkouts Signatura topográfica Código de barras Date last seen Número de copia Tipo de material
    Colección de Libros Electrónicos Biblioteca Electrónica Biblioteca Electrónica     Q342 374623-2001 12/08/2016 1 Libro Electrónico

Con tecnología Koha