Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents

Autor:	Woodgate, Jessica, Marshall, Paul, Ajmeri, Nirav
Rok vydání:	2024
Předmět:	Computer Science - Multiagent Systems Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: 14 pages, 7 figures, 8 tables (and supplementary material with reproducibility and additional results), accepted at AAAI 2025
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.15163 Zobrazit plný text záznamu View this record from Arxiv