Computational Intelligence in GamesNorio Baba The most powerful computers in the world are not only used for scientific research, defence, and business, but also in game playing. Computer games are a multi-billion dollar industry. Recent advances in computational intelligence paradigms have generated tremendous interest among researchers in the theory and implementation of games. Game theory is a branch of operational research dealing with decision theory in a competitive situation. Game theory involves the mathematical calculations and heuristics to optimize the efficient lines of play. This book presents a sample of the most recent research on the application of computational intelligence techniques in games. This book contains 7 chapters. The first chapter, by Chen, Fanelli, Castellano, and Jain, is an introduction to computational intelligence paradigms. It presents the basics of the main constituents of compu tational intelligence paradigms including knowledge representation, probability-based approaches, fuzzy logic, neural networks, genetic algorithms, and rough sets. In the second chapter, Chellapilla and Fogel present the evolution of a neural network to play checkers without human expertise. This chapter focuses on the use of a population of neural networks, where each network serves as an evaluation function to describe the quality of the current board position. After only a little more than 800 generations, the evolutionary process has generated a neural network that can play checkers at the expert level as designated by the u.s. Chess Federation rating system. The program developed by the authors has also competed well against commercially available software. |
Contents
I | 1 |
II | 3 |
III | 6 |
IV | 7 |
V | 8 |
VI | 9 |
VII | 10 |
VIII | 11 |
LVII | 74 |
LVIII | 77 |
LIX | 79 |
LX | 80 |
LXII | 81 |
LXIII | 82 |
LXIV | 83 |
LXV | 84 |
IX | 14 |
X | 15 |
XI | 16 |
XIII | 18 |
XIV | 19 |
XVI | 20 |
XVII | 21 |
XVIII | 22 |
XX | 23 |
XXI | 24 |
XXII | 25 |
XXIII | 26 |
XXIV | 27 |
XXV | 29 |
XXVI | 31 |
XXVII | 32 |
XXVIII | 33 |
XXIX | 34 |
XXX | 35 |
XXXI | 36 |
XXXII | 37 |
XXXIII | 39 |
XXXIV | 41 |
XXXV | 45 |
XXXVI | 47 |
XXXVII | 52 |
XXXVIII | 53 |
XXXIX | 55 |
XL | 57 |
XLI | 58 |
XLII | 60 |
XLIII | 61 |
XLIV | 63 |
XLVIII | 65 |
XLIX | 66 |
L | 67 |
LII | 69 |
LIII | 71 |
LIV | 72 |
LVI | 73 |
LXVI | 85 |
LXVII | 86 |
LXVIII | 87 |
LXX | 88 |
LXXI | 89 |
LXXII | 90 |
LXXIII | 91 |
LXXV | 92 |
LXXVI | 95 |
LXXVII | 96 |
LXXVIII | 99 |
LXXIX | 102 |
LXXX | 104 |
LXXXI | 105 |
LXXXII | 107 |
LXXXIII | 111 |
LXXXIV | 112 |
LXXXV | 113 |
LXXXVI | 114 |
LXXXVII | 117 |
LXXXVIII | 123 |
LXXXIX | 124 |
XC | 129 |
XCI | 130 |
XCII | 131 |
XCIII | 133 |
XCIV | 136 |
XCV | 138 |
XCVII | 139 |
XCVIII | 140 |
XCIX | 146 |
C | 147 |
CI | 150 |
CII | 151 |
CIII | 154 |
CIV | 155 |
CV | 155 |
155 | |
Other editions - View all
Common terms and phrases
1-Player 100 players 99 players agent applied approach artificial neural networks basic board positions checkers chess CMAC model computational intelligence computer simulations denote empty hexagons evaluation function evolutionary algorithms Evolutionary Computation example Figure filters fuzzy if-then rules fuzzy logic fuzzy rule-based strategy fuzzy sets game of Go genetic algorithms hidden layer high high IDSIA input components ISBN knowledge representation learning rule low high Machine Learning market selection game Metaprogramming methods mimic strategy minimum transportation cost moves neurons nodes obtain high payoff opponent optimal strategy output paradigms parameters pattern databases performance PIPE play players adopted population Ppart predicate predicate logic previous actions probability theory problem Q-function Q-learning Q-learning-based strategy Q-value random reinforcement learning represent Retrograde analysis Schmidhuber score selected market soccer solutions space string supervised learning transportation cost strategy update vector virtual connection weights