A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings

Author:

Vinitsky Eugene1ORCID,Köster Raphael2,Agapiou John P2,Duéñez-Guzmán Edgar A2,Vezhnevets Alexander S2,Leibo Joel Z2ORCID

Affiliation:

1. UC Berkeley, Berkeley, CA, USA

2. Deepmind, London, UK

Abstract

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.

Publisher

SAGE Publications

Reference74 articles.

1. The Economics of Caste and of the Rat Race and Other Woeful Tales

2. Avd O, Li Y, Vinyals O (2018) Representation learning with contrastive predictive coding. arXiv preprint arXiv:180703748.

3. Baker B. Emergent reciprocity and team formation from randomized uncertain social preferences. In: Advances in neural information processing systems 33: annual conference on neural information processing systems 2020, NeurIPS 2020, virtual, 6–12 December 2020.

4. Direct and indirect punishment among strangers in the field

5. The Power of Positive Sanctions

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Multi-agent, human-agent and beyond: A survey on cooperation in social dilemmas;Neurocomputing;2024-09

2. The IDEA of Us: An Identity-Aware Architecture for Autonomous Systems;ACM Transactions on Software Engineering and Methodology;2024-06-28

3. The emergence of division of labour through decentralized social sanctioning;Proceedings of the Royal Society B: Biological Sciences;2023-10-25

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3