Socially Intelligent Genetic Agents for the Emergence of Explicit Norms

TL;DR

This paper introduces socially intelligent agents that use genetic algorithms and reinforcement learning to develop explicit norms, improving societal cohesion and goal achievement through explanation-based reasoning.

Contribution

It presents a novel approach combining genetic algorithms and reinforcement learning for the emergence of explicit norms with explanation capabilities.

Findings

Explanation-based norms enhance societal cohesion

Norms are stable across different societal attitudes

Agents effectively learn and adapt norms through proposed methods

Abstract

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.