The iterated prisoner's dilemma is a widely used computational model of cooperation and conflict. Many studies report emergent cooperation in populations of agents trained to play prisoner's dilemma with an evolutionary algorithm. Cellular representation is the practice of evolving a set of instructions for constructing a desired structure. This paper presents a cellular encoding for finite state automata and specializes it to play the iterated prisoner's dilemma. The impact on the character and behavior of finite state agents that results from using the cellular representation is investigated. For the cellular representation presented a statistically significant drop in the level of cooperation is found. Other differences in the character of the automaton generated with a direct and cellular representation are reported. This paper forms part of an ongoing study of the impact of representation on evolved agents for playing prisoner's dilemma.
展开▼
