Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria
This work addresses the challenge of cooperation in multiagent systems with unknown team alignments, but it is incremental as it builds on existing social deduction game frameworks.
The authors tackled the problem of multiagent cooperation with hidden motivations by introducing Hidden Agenda, a two-team social deduction game, and found that reinforcement learning agents could learn diverse behaviors like partnering and voting without language communication.
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.