Ethically Aligned Multi-agent Coordination to Enhance Social Welfare

In multi-agent systems (MASs), the complex interactions among self-interested agents can be modelled as stochastic games. Existing decision support approaches dealing with such situations focus on minimizing individual agent's regret through outperforming other agents in the competitive aspect of the game. Such an approach often results in social welfare not being maximized in the process. In this paper, we propose the regret-minimization-social-welfare-maximization (RMSM) approach. It contains a novel method to quantify how an agent's sacrifice increases and decreases over time based on queueing system dynamics. In this way, ensuring fairness of distribution of sacrifice among agents and compensating for their previous sacrifices can be translated into maintaining the stability of a queueing system.