Computational intelligence in games

Más información sobre el libro

The world's most powerful computers are utilized not only for scientific research, defense, and business but also in the thriving multi-billion dollar gaming industry. Recent advancements in computational intelligence have sparked significant interest in the theory and implementation of games. Game theory, a branch of operational research, focuses on decision-making in competitive scenarios, employing mathematical calculations and heuristics to optimize gameplay. This book showcases recent research on applying computational intelligence techniques in gaming, comprising seven chapters. The first chapter, authored by Chen, Fanelli, Castellano, and Jain, introduces computational intelligence paradigms, covering key components such as knowledge representation, probability-based approaches, fuzzy logic, neural networks, genetic algorithms, and rough sets. In the second chapter, Chellapilla and Fogel explore the evolution of a neural network designed to play checkers autonomously. They detail a population of neural networks, each acting as an evaluation function for board positions. Remarkably, after just over 800 generations, this evolutionary process produced a neural network capable of playing checkers at an expert level, as recognized by the U.S. Chess Federation rating system. The authors' program has also demonstrated competitive performance against commercial software.