Biologically inspired artificial intelligence for computer games / Darryl Charles ... [and others].

Format:

Book

Contributor:

Charles, Darryl.

Louis A. Duhring Fund.

Language:

English

Subjects (All):

Artificial intelligence--Computer games.

Artificial intelligence.

Artificial intelligence--Biological applications.

Research--Computer games.

Research.

Genre:

Computer games.

Physical Description:

xiv, 262 pages : illustrations ; 27 cm

Place of Publication:

Hershey, PA : Medical Information Science Reference, [2008]

Summary:

"This book examines modern artificial intelligence to display how it may be applied to computer games. It spans the divide that exists between the academic research community working with advanced artificial intelligence and the games programming community which must create and release new and interesting games, creating an invaluable collection supporting both technological research and the gaming industry"--Provided by publisher.

Contents:

Chapter I Contemporary Video Game AI 1

The Dawn of the Computer Video Game 1

Contemporary Video Game AI 5

Biological Neural Networks 13

Artificial Neural Networks 14

Neural Networks Classification 17

Learning in Artificial Neural Networks 21

Chapter III Supervised Learning with Artificial Neural Networks 24

The Delta Rule 24

Multipayered Perceptrons 28

The Backpropagation 28

Issues in Backpropagation 31

Chapter IV Case Study: Supervised Neural Networks in Digital Games 41

Robocode 41

Chapter V Unsupervised Learning in Artificial Neural Networks 48

Unsupervised Learning 48

Hebbian Learning 49

Hebbian Learning and Information Theory 51

Anti-Hebbian Learning 59

Independent Component Analysis 61

A Case Study: Independent Component Analysis 62

Competitive Learning 68

Applications 77

Case Study: The Self-Organizing Map and Pong 77

Chapter VI Fast Learning in Neural Networks 91

Radial Basis Functions 91

Error Descent 100

Pong: A Comparative Study, MLP vs. RBF 101

Chapter VII Genetic Algorithms 105

Genetic Algorithms 106

A First Example 114

Case Study: GA and Backproagation ANN for Motocross Controllers 116

Chapter VIII Beyond the GA: Extensions and Alternatives 121

The Iterated Prisoners' Dilemma (IPD) 130

N-Persons Iterated Prisoners' Dilemma (NIPD) 132

Chapter IX Evolving Solutions for Multiobjective Problems and Hierarchical AI 139

Multiobjective Problems 140

Coevolution in Hierarchical AI for Strategy Games 141

Chapter X Artificial Immune Systems 150

The Immue System 151

Artificial Immune Systems 153

Hypermutations 156

The Immune Network 158

Agent Wars 160

Cooperating Strategies 162

Incomplete Information 164

Changing the Game 166

Duelling 167

Comparision with Gas 170

Chapter XI Ant Colony Optimisation 180

Foraging Behaviour of Ants 181

Simulating Artificial Ant Colonies with the S-ACO Algorithm 183

Improvements to the S-ACO Algorithm 188

Case Study: S-ACO and Combat 193

Chapter XII Reinforcement Learning 202

The Main Elements 203

Finding the Best Policy 205

Temporal Difference Learning 211

TD([lambda] Methods 213

Continuous State Spaces 214

Immediate Rewards 218

The Bernoulli Learner 219

The Gaussian Learner 221

Application to Games 223

Comparison with Other Methods 224

Chapter XIII Adaptivity within Games 227

Existing Approaches to Adaptivity in Games 229

Adaptive Technologies 229

Developing Adaptive Solutions 234

Emergent Gameplay 236

Chapter XIV Turing's Test and Believable AI 239

Introduction: Contemporary Game AI 239

The Popular Turing Test 240

The Real Turing Test? 242

Playing the Turing Test 243

Generalising the Turing Test 243

Measuring Believability 245

Believable Computer Players 247

Unbelievable Characters 251

The Embedded Turing Test 251.

Notes:

Includes bibliographical references and index.

Local Notes:

Acquired for the Penn Libraries with assistance from the Louis A. Duhring Fund.

ISBN:

9781591406464

1591406463

9781591406488

159140648X

OCLC:

144769295