Social and moral norms are a fabric for holding human societies together and helping them to function. As such they will also become a means of evaluating the performance of future human-machine systems. While machine ethics has offered various approaches to endowing machines with normative competence, from the more logic-based to the more data-based, none of the proposal so far have consider the challenge of capturing the "spirit of a norm" which often eludes rigid interpretation and complicates doing the right thing. We present some paradig- matic scenarios across contexts to illustrate why the spirit of a norm can be critical to make explicit and why it exposes the inadequacies of mere data-driven "value alignment" techniques such as reinforcement learning RL for interactive, real-time human-robot interaction. Instead, we argue that norm learning, in particular, learning to capture the spirit of a norm, requires combining common-sense inference-based and data-driving approaches.
@article{arnoldscheutz23aimag,
title={Understanding the spirit of a norm: Challenges for norm-learning agents},
author={Thomas Arnold and Matthias Scheutz},
year={2023},
journal={AI Magazine},
url={https://hrilab.tufts.edu/publications/arnoldscheutz23aimag.pdf}
}