GENETIC EVOLUTION AND CO-EVOLUTION OF GAME STRATEGIES
John R. Koza · 2004
The problem of discovering a strategy for playing a game can be viewed as requiring discovery of a computer program. This paper describes the recently developed "genetic programming" paradigm which genetically breeds populations of hierarchical computer programs to solve problems. The computer programs are evolved using the Darwinian principle of survival of the fittest and the genetic operation of sexual recombination. 1 INTRODUCTION AND OVERVIEW The problem of discovering a strategy for playing a game is an important problem in game theory. This problem can be viewed as requiring discovery of a computer program. The desired computer program takes either the entire history of past moves in the game or the current state of the game as its input and produces the next move as its output. This paper describes the recently developed "genetic programming" paradigm which genetically breeds populations of computer programs to solve problems. In genetic programming, the individuals in the po...