mlsanityData to 7 Oct 2026

Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria

arXiv 2201.01816 ↗First posted 5 Jan 2022cs.AI cs.LG cs.MAcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 5 Jan 2022.

Builds on

18 of 36 references.

References · 18

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  3. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  4. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 400
  5. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
  6. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 308
  7. 2017Multi-agent Reinforcement Learning in Sequential Social Dilemmascited by 206
  8. 2020Open Problems in Cooperative AIcited by 167
  9. 2018Inequity aversion improves cooperation in intertemporal social dilemmascited by 106
  10. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
  11. 2017A multi-agent reinforcement learning model of common-pool resource appropriationcited by 68
  12. 2020Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learningcited by 65
6 more
  1. 2020Social diversity and social preferences in mixed-motive reinforcement learningcited by 49
  2. 2019Finding Friend and Foe in Multi-Agent Gamescited by 42
  3. 2017Hindsight policy gradientscited by 36
  4. 2020DeepMind Lab2Dcited by 12
  5. 2021RLupus: Cooperation through emergent communication in The Werewolf social deduction gamecited by 10
  6. 2020Competing in a Complex Hidden Role Game with Information Set Monte Carlo Tree Searchcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1; 2025: 2.

6 papers.

  1. 2023Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Modelscited by 46
  2. 2024Enhance Reasoning for Large Language Models in the Game Werewolfcited by 44
  3. 2025Training Language Models for Social Deduction with Multi-Agent Reinforcement Learningcited by 15
  4. 2025Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategiescited by 9
  5. 2022Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environmentscited by 2
  6. 2022A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayalcited by 0