Socially Intelligent Genetic Agents for the Emergence of Explicit Norms
This work addresses the problem of regulating multi-agent systems for researchers in AI and social simulation, though it is incremental in applying existing methods to a specific domain.
The paper tackled the emergence of explicit norms in societies by developing agents that use explanations for norm violations, genetic algorithms, and reinforcement learning, resulting in norms that improve cohesion and goal satisfaction with stable outcomes across varying generosity levels.
Norms help regulate a society. Norms may be explicit (represented in structured form) or implicit. We address the emergence of explicit norms by developing agents who provide and reason about explanations for norm violations in deciding sanctions and identifying alternative norms. These agents use a genetic algorithm to produce norms and reinforcement learning to learn the values of these norms. We find that applying explanations leads to norms that provide better cohesion and goal satisfaction for the agents. Our results are stable for societies with differing attitudes of generosity.