Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents

Raphael Köster, Dylan Hadfield-Menell, Richard Everett, Laura Weidinger, Gillian K. Hadfield and Joel Z. Leibo
Additional contact information
Raphael Köster: a DeepMind, London EC4A 3TW, United Kingdom;
Dylan Hadfield-Menell: b Computer Science and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139;; c Center for Human-Compatible AI, University of California, Berkeley, CA 94720;
Richard Everett: a DeepMind, London EC4A 3TW, United Kingdom;
Laura Weidinger: a DeepMind, London EC4A 3TW, United Kingdom;
Gillian K. Hadfield: c Center for Human-Compatible AI, University of California, Berkeley, CA 94720;; d Faculty of Law, University of Toronto, Toronto, ON M5S 3E6, Canada;; e Rotman School of Management, University of Toronto, Toronto, ON M5S 3E6, Canada;; f Schwartz Reisman Institute for Technology and Society, University of Toronto, Toronto, ON M5G 1L7, Canada;; g Vector Institute for Artificial Intelligence, Toronto, ON M5G 1M1, Canada;; h OpenAI, San Francisco, CA 94110
Joel Z. Leibo: a DeepMind, London EC4A 3TW, United Kingdom;

Proceedings of the National Academy of Sciences, 2022, vol. 119, issue 3, e2106028118

Abstract: The fact that humans enforce and comply with norms is an important reason why humans enjoy higher levels of cooperation and welfare than other animals. Some norms are relatively easy to explain: They may prohibit obviously harmful or uncooperative actions. But many norms are not easy to explain. For example, most cultures prohibit eating certain kinds of foods, and almost all societies have rules about what constitutes appropriate clothing, language, and gestures. Using a computational model focused on learning shows that apparently pointless rules can have an indirect effect on welfare. They can help agents learn how to enforce and comply with norms in general, improving the group’s ability to enforce norms that have a direct effect on welfare.

Keywords: multiagent reinforcement learning; norms; third-party punishment; cultural evolution; social norms (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.pnas.org/content/119/3/e2106028118.full (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nas:journl:v:119:y:2022:p:e2106028118

Access Statistics for this article

More articles in Proceedings of the National Academy of Sciences from Proceedings of the National Academy of Sciences
Bibliographic data for series maintained by PNAS Product Team ().