Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria
Abstract
A key challenge in the study of multiagent cooperation is the need for individual agents not only to cooperate effectively, but to decide with whom to cooperate. This is particularly critical in situations when other agents have hidden, possibly misaligned motivations and goals. Social deduction games offer an avenue to study how individuals might learn to synthesize potentially unreliable information about others, and elucidate their true motivations. In this work, we present Hidden Agenda, a two-team social deduction game that provides a 2D environment for studying learning agents in scenarios of unknown team alignment. The environment admits a rich set of strategies for both teams. Reinforcement learning agents trained in Hidden Agenda show that agents can learn a variety of behaviors, including partnering and voting without need for communication in natural language.
Keywords
Cite
@article{arxiv.2201.01816,
title = {Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria},
author = {Kavya Kopparapu and Edgar A. Duéñez-Guzmán and Jayd Matyas and Alexander Sasha Vezhnevets and John P. Agapiou and Kevin R. McKee and Richard Everett and Janusz Marecki and Joel Z. Leibo and Thore Graepel},
journal= {arXiv preprint arXiv:2201.01816},
year = {2022}
}