# Training an Assassin AI for The Resistance: Avalon

arXiv: https://arxiv.org/abs/2209.09331 · HTML: https://mlsanity.com/paper/2209.09331/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 19 Sep 2022.

## Builds on (most cited first, 2 of 2)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Finding Friend and Foe in Multi-Agent Games](https://mlsanity.com/paper/1906.02330/) (2019)

## Built on by (most cited first, 3 of 3)

- [Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations](https://mlsanity.com/paper/2403.02090/) (2024)
- [Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games](https://mlsanity.com/paper/2212.08279/) (2022)
- [CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference](https://mlsanity.com/paper/2511.06175/) (2025)

## Abstract (arXiv)

The Resistance: Avalon is a partially observable social deduction game. This area of AI game playing is fairly undeveloped. Implementing an AI for this game involves multiple components specific to each phase as well as role in the game. In this paper, we plan to iteratively develop the required components for each role/phase by first addressing the Assassination phase which can be modeled as a machine learning problem. Using a publicly available dataset from an online version of the game, we train classifiers that emulate an Assassin. After trying various classification techniques, we are able to achieve above average human performance using a simple linear support vector classifier. The eventual goal of this project is to pursue developing an intelligent and complete Avalon player that can play through each phase of the game as any role.