Towards evolutionary self-optimization of large multi-agent systems

The development of IoT technologies raises the question of their self-optimization. For this purpose we propose an approach based on a multi-agent interpretation, modeling discrete space and time by Cellular Automata (CA), and applying a game-theoretical model known as spatial Prisoner's Dilemma (SPD). A 2D space is occupied by agents which belong to species with certain strategies. Each agent participates in games with neighbors and its goal is to maximize its cumulated payoff. Species competing for space apply locally a mechanism of evolutionary selection, where the cumulated payoff is considered as fitness. As a result of the competition, more profitable species replace less profitable ones. While agents act locally to maximize their incomes we study conditions of emerging collective behavior measured by the global average total payoff of which the players are not aware. We show that collective behavior based on achieving in a fully distributed way a Nash equilibrium (NE) can emerge if some conditions of the game are fulfilled, in particular when an "income sharing mechanism" is introduced.