Information based explanation methods for deep learning agents -- with applications on large open-source chess models

TL;DR

This paper introduces a novel explainable AI method for large open-source chess models, providing exhaustive, domain-specific visual explanations with strict information flow guarantees, demonstrated on standard chess.

Contribution

It re-implements domain knowledge detection for open-source models and proposes a new explainability method with strict information control guarantees for discrete domains.

Findings

Achieved similar results to AlphaZero using open-source models.

Developed a visual explanation method with strict information flow control.

Validated the method on standard 8x8 chess.

Abstract

With large chess-playing neural network models like AlphaZero contesting the state of the art within the world of computerised chess, two challenges present themselves: The question of how to explain the domain knowledge internalised by such models, and the problem that such models are not made openly available. This work presents the re-implementation of the concept detection methodology applied to AlphaZero in McGrath et al. (2022), by using large, open-source chess models with comparable performance. We obtain results similar to those achieved on AlphaZero, while relying solely on open-source resources. We also present a novel explainable AI (XAI) method, which is guaranteed to highlight exhaustively and exclusively the information used by the explained model. This method generates visual explanations tailored to domains characterised by discrete input spaces, as is the case for chess. Our presented method has the desirable property of controlling the information flow between any input vector and the given model, which in turn provides strict guarantees regarding what information is used by the trained model during inference. We demonstrate the viability of our method by applying it to standard 8x8 chess, using large open-source chess models.