The impact of varying resources available to Iterated Prisoner's Dilemma agents

Abstract

The Iterated Prisoner's Dilemma is a simultaneous two-player game widely used in studies on cooperation and conflict. Past work has shown that the choice of representation of evolving agents has a dominant impact on their behavior. In this study we also examine the impact of varying available resources. A variety of different resources can be varied, including amount and type of past information available to agents, number of neurons in a neural net, number of probability levels available to encode a probabilistic strategy, and number of states in a finite state machine. All these resources are shown to have an impact on the character of evolved agents assessed using both play profiles and a total score measure. Play profiles bin the ranges of score space while total score is a global assessment of the type of play that occurs over the course of evolution. The largest effect is found for the probabilistic agents, followed by finite state agents, lookup tables, and finally neural nets exhibit the least effect.