A Novel Weighted Ensemble Learning Based Agent for the Werewolf Game

TL;DR

This paper introduces a sophisticated weighted ensemble learning agent for the Werewolf game that outperforms competitors by effectively aggregating strategies and learning from diverse participants, with potential applications to other communication-based games.

Contribution

The paper proposes a novel ensemble learning approach for creating an advanced agent in the Werewolf game, demonstrating improved performance over existing strategies.

Findings

The agent outperforms other competitors using basic strategies.

The approach effectively estimates other players' perceptions.

The method can be extended to other communication-dependent games.

Abstract

Werewolf is a popular party game throughout the world, and research on its significance has progressed in recent years. The Werewolf game is based on conversation, and in order to win, participants must use all of their cognitive abilities. This communication game requires the playing agents to be very sophisticated to win. In this research, we generated a sophisticated agent to play the Werewolf game using a complex weighted ensemble learning approach. This research work aimed to estimate what other agents/players think of us in the game. The agent was developed by aggregating strategies of different participants in the AI Wolf competition and thereby learning from them using machine learning. Moreover, the agent created was able to perform much better than other competitors using very basic strategies to show the approach's effectiveness in the Werewolf game. The machine learning technique used here is not restricted to the Werewolf game but may be extended to any game that requires communication and action depending on other participants.