|
Abstract : |
Evolution is a fundamental form of adaptation in a dynamic and complex environment. Genetic algorithms are an effective tool in the empirical study of evolution. This paper follows Axelrod's work [2] in using the genetic algorithm to evolve strategies for playing the game of Iterated Prisoner's Dilemma, using co-evolution, where each member of the population (each strategy) is evaluated by how it performs against the other members of the current population. This creates a dynamic environment in which the algorithm is optimising to a moving target instead of the usual evaluation against some fixed set of strategies. The hope is that this will stimulate an "arms race " of innovation [3]. We conduct two sets of experiments. The first set investigates what conditions evolve the best strategies. The second set studies the robustness of the strategies thus evolved, that is, are the strategies useful only in the round robin of its population or are they effective against a wide variety of opponents? Our results indicate that the population has nearly always converged by about 250 generations, by which time the bias in the population has almost always stabilised at 85%. Our, |
