Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy

Author:

Kramár János,Eccles Tom,Gemp Ian,Tacchetti Andrea,McKee Kevin R.ORCID,Malinowski Mateusz,Graepel Thore,Bachrach YoramORCID

Abstract

AbstractThe success of human civilization is rooted in our ability to cooperate by communicating and making joint plans. We study how artificial agents may use communication to better cooperate in Diplomacy, a long-standing AI challenge. We propose negotiation algorithms allowing agents to agree on contracts regarding joint plans, and show they outperform agents lacking this ability. For humans, misleading others about our intentions forms a barrier to cooperation. Diplomacy requires reasoning about our opponents’ future plans, enabling us to study broken commitments between agents and the conditions for honest cooperation. We find that artificial agents face a similar problem as humans: communities of communicating agents are susceptible to peers who deviate from agreements. To defend against this, we show that the inclination to sanction peers who break contracts dramatically reduces the advantage of such deviators. Hence, sanctioning helps foster mostly truthful communication, despite conditions that initially favor deviations from agreements.

Publisher

Springer Science and Business Media LLC

Subject

General Physics and Astronomy,General Biochemistry, Genetics and Molecular Biology,General Chemistry,Multidisciplinary

Reference70 articles.

1. Henrich, J. The Secret of Our Success (Princeton University Press, 2015).

2. Nowak, M. A. & Highfield, R. SuperCooperators (Canongate Edinburgh, 2011).

3. Stone, P. et al. Artificial Intelligence And Life in 2030: The One Hundred Year Study on Artificial Intelligence (Stanford University, 2016).

4. Rahwan, I. et al. Machine behaviour. Nature 568, 477–486 (2019).

5. Sierra, C., Jennings, N. R., Noriega, P. & Parsons, S. A framework for argumentation-based negotiation. in International Workshop on Agent Theories, Architectures, and Languages 177–192 (Springer, 1997).

Cited by 5 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

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