Emergent Cooperation and Deception in Public Good Games

Nicole Orzan, Erman Acar, Davide Grossi, Roxana Radulescu

Onderzoeksoutput: Unpublished paper


Communication is a widely used mechanism to promote cooperation in multi-agent systems. In the field of emergent communication agents are usually trained on a particular type of environment: cooperative, competitive, or mixed-motive. Motivated by the idea that real-world settings are characterised by incomplete information and that humans face daily interactions under a wide spectrum of incentives, we hypothesise that emergent communication could be simultaneously exploited in the totality of these scenarios.
In this work we pursue this line of research by focusing on social dilemmas, and develop an extended version of the Public Goods Game which allows us to train independent reinforcement learning agents simultaneously on different scenarios where incentives are aligned (or misaligned) to various extents.
Additionally, we introduce uncertainty regarding the alignment of incentives, and we equip agents with the ability to learn a communication policy, to study the potential of emergent communication for overcoming uncertainty.
We show that in settings where all agents have the same level of uncertainty, communication can help improve the cooperation level of the system, while, when uncertainty is asymmetric, certain agents learn to use communication to deceive and exploit their uncertain peers.
Originele taal-2English
Aantal pagina's9
StatusPublished - mei 2023
Evenement2023 Adaptive and Learning Agents Workshop at AAMAS - London, United Kingdom
Duur: 29 mei 202330 mei 2023


Workshop2023 Adaptive and Learning Agents Workshop at AAMAS
Verkorte titelALA 2023
Land/RegioUnited Kingdom
Internet adres


Duik in de onderzoeksthema's van 'Emergent Cooperation and Deception in Public Good Games'. Samen vormen ze een unieke vingerafdruk.

Citeer dit