Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies

Abstract

We present a computational framework capable of inferring the existence of groups, built upon social networks of re- ciprocal friendship, in Complex Adaptive Artificial Societies (CAAS). Our modelling framework infers the group identi- ties by following two steps: first, it aims to learn the on- going levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups. Ex- perimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum Game, show that a cooperation learning phase, based on Reinforce- ment Learning, can provide highly promising results for min- imising the mismatch between the existing and the inferred groups, for two different society sizes under investigation.