Anticipatory Learning Classifier Systems

Overview

Anticipatory Learning Classifier Systems describes the state of the art of anticipatory learning classifier systems-adaptive rule learning systems that autonomously build anticipatory environmental models. An anticipatory model specifies all possible action-effects in an environment with respect to given situations. It can be used to simulate anticipatory adaptive behavior.

Anticipatory Learning Classifier Systems highlights how anticipations influence cognitive systems and ...

See more details below
Paperback (Softcover reprint of the original 1st ed. 2002)
$167.85
BN.com price
(Save 15%)$199.00 List Price
Other sellers (Paperback)
  • All (5) from $158.96   
  • New (4) from $158.96   
  • Used (1) from $248.93   
Sending request ...

Overview

Anticipatory Learning Classifier Systems describes the state of the art of anticipatory learning classifier systems-adaptive rule learning systems that autonomously build anticipatory environmental models. An anticipatory model specifies all possible action-effects in an environment with respect to given situations. It can be used to simulate anticipatory adaptive behavior.

Anticipatory Learning Classifier Systems highlights how anticipations influence cognitive systems and illustrates the use of anticipations for (1) faster reactivity, (2) adaptive behavior beyond reinforcement learning, (3) attentional mechanisms, (4) simulation of other agents and (5) the implementation of a motivational module. The book focuses on a particular evolutionary model learning mechanism, a combination of a directed specializing mechanism and a genetic generalizing mechanism. Experiments show that anticipatory adaptive behavior can be simulated by exploiting the evolving anticipatory model for even faster model learning, planning applications, and adaptive behavior beyond reinforcement learning.

Anticipatory Learning Classifier Systems gives a detailed algorithmic description as well as a program documentation of a C++ implementation of the system.

Read More Show Less

Editorial Reviews

From The Critics
Butz (U. of Würzburg, Germany) discusses the simulation and utilization of anticipations to a simulated learning environment in an artificial behavioral learning system. A major focus is on how an environmental model can be represented and learned in an artificial learning system, while a secondary, but significant, concern is an investigation of how the evolving artificial environmental model may influence the behavior of the artificial system. One particular anticipatory learning classifier system, ACS2, is introduced, along with the C++ code documentation and algorithmic descriptions. ACS2 forms condition-action-effect rules perceiving an environment and acting in that environment. The formed rules specify what may change after the execution of an action in a given situation. The primary goal of the system is to evolve a complete, accurate, and compact set of rules that fully represent an environmental model. Annotation c. Book News, Inc., Portland, OR (booknews.com)
Read More Show Less

Product Details

  • ISBN-13: 9781461352907
  • Publisher: Springer US
  • Publication date: 4/30/2013
  • Series: Genetic Algorithms and Evolutionary Computation Series , #4
  • Edition description: Softcover reprint of the original 1st ed. 2002
  • Edition number: 1
  • Pages: 172
  • Product dimensions: 6.14 (w) x 9.21 (h) x 0.43 (d)

Table of Contents

List of Figures ix
List of Tables xvi
Foreword xvii
Preface xix
1. Complex Systems Approach xx
2. Towards ACS2 xxiii
3. ACS2 xxiv
4. Road Map xxv
Acknowledgments xxvii
1. Background 1
1. Anticipations 2
1.1. Psychology Discovers Anticipations 2
1.2. Theory of Anticipatory Behavioral Control 3
1.3. Importance of Anticipations 4
2. Genetic Algorithms 6
2.1. Evolutionary Principles 6
2.2. GA Framework 8
2.3. An Illustrative Example 10
3. Learning Classifier Systems 11
3.1. Holland's Cognitive System 13
3.2. LCS framework 14
3.3. Problems in Traditional LCSs 15
3.4. XCS Classifier System 16
2. ACS2 23
1. Framework 25
1.1. Environmental Interaction 25
1.2. Knowledge Representation 26
1.3. A Behavioral Act 27
2. Reinforcement Learning 29
3. The Anticipatory Learning Process 30
3.1. The Process in Detail 30
3.2. The ALP in Action: A Simple Gripper Problem 33
3.3. Causes for Over-Specialization 35
4. Genetic Generalization in ACS2 37
4.1. Accurate, Maximally General Classifiers in ACS2 38
4.2. The GA Idea 39
4.3. How the GA Works 41
5. Interaction of ALP, GA, RL, and Behavior 43
5.1. Subsumption 44
5.2. Evolutionary Pressures of ALP and GA 45
5.3. All Interactions 47
3. Experiments with ACS2 51
1. Gripper Problem Revisited 52
1.1. Population without GA 52
1.2. Population with GA 54
2. Multiplexer Problem 55
2.1. Environmental Setting 56
2.2. Evolution of a Multiplexer Model 57
2.3. ACS2 as a Classifier 63
3. Maze Environment 64
3.1. Environmental Setting 65
3.2. Maze6 66
3.3. Woods14 68
4. Blocks World 69
4.1. Environmental Setting 71
4.2. Model Learning 73
5. Hand-Eye Coordination Task 76
5.1. Environmental Setting 76
5.2. Model Learning 78
6. Result Summary 79
4. Limits 81
1. GA Challenges 81
1.1. Overlapping Classifiers 82
1.2. Interfering Specificities 85
2. Non-determinism and a First Approach 87
2.1. ACS2 in a Non-determinism Task 88
2.2. Probability-Enhanced Effects 89
3. Model Aliasing 93
5. Model Exploitation 99
1. Improving Model Learning 99
1.1. Increasing Exploration 100
1.2. Combining Exploration with Action Planning 104
2. Enhancing Reinforcement Learning 107
2.1. Response-Effect Learning Task 107
2.2. Mental Acting 108
2.3. Lookahead Action Selection 110
2.4. ACS2 in the Response-Effect Task 111
2.5. Stimulus-Response-Effect Task 112
3. Model Exploitation Recapitulation 113
6. Related Systems 115
1. Estimated Learning Algorithm 115
2. Dyna 117
3. Schema Mechanism 118
4. Expectancy Model SRS/E 119
7. Summary, Conclusions, and Future Work 121
1. Summary 121
2. Model Representation Enhancements 123
2.1. Classifier Structure 123
2.2. ACS2 Structure 126
3. Model Learning Modifications 127
3.1. Observations in Nature 127
3.2. Relevance and Influence 130
3.3. Attentional Mechanisms 131
3.4. Additional Memory 133
4. Adaptive Behavior 134
4.1. Reinforcement Learning Processes 135
4.2. Behavioral Module 136
5. ACS2 in the Future 137
Appendices 139
Appendix A Parameters in ACS2 139
Appendix B Algorithmic Description of ACS2 141
1. Initialization 141
2. The Main Execution Loop 142
3. Formation of the Match Set 143
4. Choosing an Action 143
5. Formation of the Action Set 144
6. Application of the ALP 144
7. Reinforcement Learning 149
8. GA Application 149
9. Subsumption 152
Appendix C ACS2 C++ Code Documentation 153
1. Getting Started 153
2. Structure of the Code 154
2.1. The Controller - ACSConstants.h 154
2.2. The Executer - acs2++.cc 156
2.3. Environments 157
2.4. ACS2 modules 159
3. Performance Output 160
Appendix D Glossary 161
References 165
Index 171
Read More Show Less

Customer Reviews

Be the first to write a review
( 0 )
Rating Distribution

5 Star

(0)

4 Star

(0)

3 Star

(0)

2 Star

(0)

1 Star

(0)

Your Rating:

Your Name: Create a Pen Name or

Barnes & Noble.com Review Rules

Our reader reviews allow you to share your comments on titles you liked, or didn't, with others. By submitting an online review, you are representing to Barnes & Noble.com that all information contained in your review is original and accurate in all respects, and that the submission of such content by you and the posting of such content by Barnes & Noble.com does not and will not violate the rights of any third party. Please follow the rules below to help ensure that your review can be posted.

Reviews by Our Customers Under the Age of 13

We highly value and respect everyone's opinion concerning the titles we offer. However, we cannot allow persons under the age of 13 to have accounts at BN.com or to post customer reviews. Please see our Terms of Use for more details.

What to exclude from your review:

Please do not write about reviews, commentary, or information posted on the product page. If you see any errors in the information on the product page, please send us an email.

Reviews should not contain any of the following:

  • - HTML tags, profanity, obscenities, vulgarities, or comments that defame anyone
  • - Time-sensitive information such as tour dates, signings, lectures, etc.
  • - Single-word reviews. Other people will read your review to discover why you liked or didn't like the title. Be descriptive.
  • - Comments focusing on the author or that may ruin the ending for others
  • - Phone numbers, addresses, URLs
  • - Pricing and availability information or alternative ordering information
  • - Advertisements or commercial solicitation

Reminder:

  • - By submitting a review, you grant to Barnes & Noble.com and its sublicensees the royalty-free, perpetual, irrevocable right and license to use the review in accordance with the Barnes & Noble.com Terms of Use.
  • - Barnes & Noble.com reserves the right not to post any review -- particularly those that do not follow the terms and conditions of these Rules. Barnes & Noble.com also reserves the right to remove any review at any time without notice.
  • - See Terms of Use for other conditions and disclaimers.
Search for Products You'd Like to Recommend

Recommend other products that relate to your review. Just search for them below and share!

Create a Pen Name

Your Pen Name is your unique identity on BN.com. It will appear on the reviews you write and other website activities. Your Pen Name cannot be edited, changed or deleted once submitted.

 
Your Pen Name can be any combination of alphanumeric characters (plus - and _), and must be at least two characters long.

Continue Anonymously

    If you find inappropriate content, please report it to Barnes & Noble
    Why is this product inappropriate?
    Comments (optional)