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
1 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