Competing in a Complex Hidden Role Game with Information Set Monte Carlo Tree Search

TL;DR

This paper applies the SO-ISMCTS algorithm to the complex hidden role game Secret Hitler, demonstrating its competitive performance and potential in intricate imperfect information domains through extensive simulations.

Contribution

It introduces the application of SO-ISMCTS to a complex social deduction game, expanding the scope of ISMCTS in challenging imperfect information environments.

Findings

SO-ISMCTS performs as well as rule-based agents in Secret Hitler.

The algorithm demonstrates potential in complex information set domains.

Extensive simulations validate the approach's effectiveness.

Abstract

Advances in intelligent game playing agents have led to successes in perfect information games like Go and imperfect information games like Poker. The Information Set Monte Carlo Tree Search (ISMCTS) family of algorithms outperforms previous algorithms using Monte Carlo methods in imperfect information games. In this paper, Single Observer Information Set Monte Carlo Tree Search (SO-ISMCTS) is applied to Secret Hitler, a popular social deduction board game that combines traditional hidden role mechanics with the randomness of a card deck. This combination leads to a more complex information model than the hidden role and card deck mechanics alone. It is shown in 10108 simulated games that SO-ISMCTS plays as well as simpler rule based agents, and demonstrates the potential of ISMCTS algorithms in complicated information set domains.