Quantifying Feature Importance of Games and Strategies via Shapley Values

TL;DR

This paper introduces two methods using Shapley values to quantify feature importance in games and strategies, enhancing interpretability and human understanding of AI strategies.

Contribution

The paper proposes novel methods to interpret game strategies and AI decisions using Shapley values, bridging game informatics and explainable AI.

Findings

Methods produce intuitive explanations

Enhance understanding of AI strategies

Applicable to diverse games

Abstract

Recent advances in game informatics have enabled us to find strong strategies across a diverse range of games. However, these strategies are usually difficult for humans to interpret. On the other hand, research in Explainable Artificial Intelligence (XAI) has seen a notable surge in scholarly activity. Interpreting strong or near-optimal strategies or the game itself can provide valuable insights. In this paper, we propose two methods to quantify the feature importance using Shapley values: one for the game itself and another for individual AIs. We empirically show that our proposed methods yield intuitive explanations that resonate with and augment human understanding.