//]]>

Adaptive Representations for Reinforcement Learning (Record no. 11276)

000 -LEADER
fixed length control field 03350nam a22003975i 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20140310143344.0
007 - PHYSICAL DESCRIPTION FIXED FIELD--GENERAL INFORMATION
fixed length control field cr nn 008mamaa
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 100709s2010 gw | s |||| 0|eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
International Standard Book Number 9783642139321
978-3-642-13932-1
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 006.3
Edition number 23
264 #1 -
-- Berlin, Heidelberg :
-- Springer Berlin Heidelberg,
-- 2010.
912 ## -
-- ZDB-2-ENG
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name Whiteson, Shimon.
Relator term author.
245 10 - IMMEDIATE SOURCE OF ACQUISITION NOTE
Title Adaptive Representations for Reinforcement Learning
Medium [electronic resource] /
Statement of responsibility, etc by Shimon Whiteson.
300 ## - PHYSICAL DESCRIPTION
Extent 133p. 11 illus. in color.
Other physical details online resource.
440 1# - SERIES STATEMENT/ADDED ENTRY--TITLE
Title Studies in Computational Intelligence,
International Standard Serial Number 1860-949X ;
Volume number/sequential designation 291
505 0# - FORMATTED CONTENTS NOTE
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 ## - SUMMARY, 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.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name as entry element Engineering.
Topical term or geographic name as entry element Artificial intelligence.
Topical term or geographic name as entry element Engineering.
Topical term or geographic name as entry element Computational Intelligence.
Topical term or geographic name as entry element Artificial Intelligence (incl. Robotics).
710 2# - ADDED ENTRY--CORPORATE NAME
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
Display text Printed edition:
International Standard Book Number 9783642139314
856 40 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier http://dx.doi.org/10.1007/978-3-642-13932-1
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme
Item type E-Book
Copies
Price effective from Permanent location Date last seen Not for loan Date acquired Source of classification or shelving scheme Koha item type Damaged status Lost status Withdrawn status Current location Full call number
2014-03-31AUM Main Library2014-03-31 2014-03-31 E-Book   AUM Main Library006.3