Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI
Abstract
Pluralistic alignment is concerned with ensuring that an AI system’s objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of agentic AI, and in particular in the context of an agent that is trying to learn a policy in a manner that is mindful of the values and perspective of others in the environment. To this end, we show how being considerate of the future wellbeing and agency of other (human) agents can promote a form of pluralistic alignment.
Cite
Text
Alamdari et al. "Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.Markdown
[Alamdari et al. "Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI." NeurIPS 2024 Workshops: Pluralistic-Alignment, 2024.](https://mlanthology.org/neuripsw/2024/alamdari2024neuripsw-considerate/)BibTeX
@inproceedings{alamdari2024neuripsw-considerate,
title = {{Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI}},
author = {Alamdari, Parand A. and Klassen, Toryn Q. and Icarte, Rodrigo Toro and McIlraith, Sheila A.},
booktitle = {NeurIPS 2024 Workshops: Pluralistic-Alignment},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/alamdari2024neuripsw-considerate/}
}