A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings
Collective Intelligence · 2023-04 · 2 (2) · 263391372311620
DOI: 10.1177/26339137231162025 ↗Kurz gefasst
Fachartikel in der Zeitschrift Collective Intelligence, online erschienen am 17.04.2023. Verfasst von Eugene Vinitsky und 5 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Society is characterized by the presence of a variety of social norms: collective patterns of sanctioning that can prevent miscoordination and free-riding. Inspired by this, we aim to construct learning dynamics where potentially beneficial social norms can emerge. Since social norms are underpinned by sanctioning, we introduce a training regime where agents can access all sanctioning events but learning is otherwise decentralized. This setting is technologically interesting because sanctioning events may be the only available public signal in decentralized multi-agent systems where reward or policy-sharing is infeasible or undesirable. To achieve collective action in this setting, we construct an agent architecture containing a classifier module that categorizes observed behaviors as approved or disapproved, and a motivation to punish in accord with the group. We show that social norms emerge in multi-agent systems containing this agent and investigate the conditions under which this helps them achieve socially beneficial outcomes.
Zitieren
APA
Vinitsky, E., Köster, R., Agapiou, J. P., Duéñez-Guzmán, E. A., Vezhnevets, A. S., & Leibo, J. Z. (2023). A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings. Collective Intelligence, 2(2), 263391372311620. https://doi.org/10.1177/26339137231162025
Vancouver
Vinitsky E, Köster R, Agapiou JP, Duéñez-Guzmán EA, Vezhnevets AS, Leibo JZ. A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings. Collective Intelligence. 2023;2(2):263391372311620. doi:10.1177/26339137231162025
BibTeX
@article{Vinitsky2023,
author = {Vinitsky, Eugene and Köster, Raphael and Agapiou, John P and Duéñez-Guzmán, Edgar A and Vezhnevets, Alexander S and Leibo, Joel Z},
title = {A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings},
journal = {Collective Intelligence},
year = {2023},
volume = {2},
number = {2},
pages = {263391372311620},
doi = {10.1177/26339137231162025}
}
EUVIMED