Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents
This addresses fairness issues in AI agents for societal simulations, though it appears incremental as it applies an existing ethical principle to a specific domain.
The authors tackled the problem of unfair norms emerging in multi-agent systems by introducing RAWL-E, a method that operationalizes Rawlsian maximin fairness in norm-learning agents, resulting in enhanced social welfare, fairness, and higher minimum experience in simulated harvesting scenarios.
Social norms are standards of behaviour common in a society. However, when agents make decisions without considering how others are impacted, norms can emerge that lead to the subjugation of certain agents. We present RAWL-E, a method to create ethical norm-learning agents. RAWL-E agents operationalise maximin, a fairness principle from Rawlsian ethics, in their decision-making processes to promote ethical norms by balancing societal well-being with individual goals. We evaluate RAWL-E agents in simulated harvesting scenarios. We find that norms emerging in RAWL-E agent societies enhance social welfare, fairness, and robustness, and yield higher minimum experience compared to those that emerge in agent societies that do not implement Rawlsian ethics.