Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Woodgate, Jessica, Marshall, Paul, Ajmeri, Nirav
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909435359657984
author Woodgate, Jessica
Marshall, Paul
Ajmeri, Nirav
author_facet Woodgate, Jessica
Marshall, Paul
Ajmeri, Nirav
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents
Woodgate, Jessica
Marshall, Paul
Ajmeri, Nirav
Multiagent Systems
Artificial Intelligence
Machine Learning
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.
title Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.15163