Emergence of cooperation in the one-shot Prisoner’s dilemma through Discriminatory and Samaritan AIs
Journal of The Royal Society Interface · 2024-09 · 21 (218)
DOI: 10.1098/rsif.2024.0212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of The Royal Society Interface, online erschienen am 25.09.2024. Verfasst von Filippo Zimmaro und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, University of Bologna , Bologna, Italy. Hauptthemen laut MEDLINE: Prisoner Dilemma, Artificial Intelligence, Cooperative Behavior. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: María de Maeztu Program, Future of Life Institute, Agencia Estatal de Investigación.
Abstract (Originalsprache)
As artificial intelligence (AI) systems are increasingly embedded in our lives, their presence leads to interactions that shape our behaviour, decision-making and social interactions. Existing theoretical research on the emergence and stability of cooperation, particularly in the context of social dilemmas, has primarily focused on human-to-human interactions, overlooking the unique dynamics triggered by the presence of AI. Resorting to methods from evolutionary game theory, we study how different forms of AI can influence cooperation in a population of human-like agents playing the one-shot Prisoner’s dilemma game. We found that Samaritan AI agents who help everyone unconditionally, including defectors, can promote higher levels of cooperation in humans than Discriminatory AI that only helps those considered worthy/cooperative, especially in slow-moving societies where change based on payoff difference is moderate (small intensities of selection). Only in fast-moving societies (high intensities of selection), Discriminatory AIs promote higher levels of cooperation than Samaritan AIs. Furthermore, when it is possible to identify whether a co-player is a human or an AI, we found that cooperation is enhanced when human-like agents disregard AI performance. Our findings provide novel insights into the design and implementation of context-dependent AI systems for addressing social dilemmas.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics, University of Bologna , Bologna, Italy.
- Department of Computer Science, University of Pisa , Pisa, Italy.
- Instituto de Física Interdisciplinar y Sistemas Complejos IFISC (CSIC-UIB) , Palma de Mallorca, Spain.
- Universidad de Las Palmas de Gran Canaria , Las Palmas de Gran Canaria, Spain.
- International Center for Future Generations , Brussels, Belgium.
- Institut für Mathematik, Freie Universität Berlin , Berlin, Germany.
ORCID-Profile: The Anh Han
Förderung
- María de Maeztu Program
- Future of Life Institute
- Agencia Estatal de Investigación
- Ministerio de Ciencia e Innovación
- European Regional Development Fund
- EPSRC grant
Zitieren
APA
Zimmaro, F., Miranda, M., Fernández, J. M. R., Moreno López, J. A., Reddel, M., Widler, V., Antonioni, A., & Han, T. A. (2024). Emergence of cooperation in the one-shot Prisoner’s dilemma through Discriminatory and Samaritan AIs. Journal of The Royal Society Interface, 21(218). https://doi.org/10.1098/rsif.2024.0212
Vancouver
Zimmaro F, Miranda M, Fernández JMR, Moreno López JA, Reddel M, Widler V, et al. Emergence of cooperation in the one-shot Prisoner’s dilemma through Discriminatory and Samaritan AIs. Journal of The Royal Society Interface. 2024;21(218). doi:10.1098/rsif.2024.0212
BibTeX
@article{Zimmaro2024,
author = {Zimmaro, Filippo and Miranda, Manuel and Fernández, José María Ramos and Moreno López, Jesús A and Reddel, Max and Widler, Valeria and Antonioni, Alberto and Han, The Anh},
title = {Emergence of cooperation in the one-shot Prisoner’s dilemma through Discriminatory and Samaritan AIs},
journal = {Journal of The Royal Society Interface},
year = {2024},
volume = {21},
number = {218},
doi = {10.1098/rsif.2024.0212}
}
EUVIMED