Domain-Level Explainability -- A Challenge for Creating Trust in Superhuman AI Strategies
This work identifies a critical gap in XAI for enabling trust in superhuman AI strategies, which is essential for safe real-world applications but remains an incremental step in the field.
The paper addresses the challenge of building trust in superhuman AI strategies by highlighting the lack of domain-level explainability for expert users in strategic situations, despite the success of DRL in learning advanced solutions beyond human capabilities.
For strategic problems, intelligent systems based on Deep Reinforcement Learning (DRL) have demonstrated an impressive ability to learn advanced solutions that can go far beyond human capabilities, especially when dealing with complex scenarios. While this creates new opportunities for the development of intelligent assistance systems with groundbreaking functionalities, applying this technology to real-world problems carries significant risks and therefore requires trust in their transparency and reliability. With superhuman strategies being non-intuitive and complex by definition and real-world scenarios prohibiting a reliable performance evaluation, the key components for trust in these systems are difficult to achieve. Explainable AI (XAI) has successfully increased transparency for modern AI systems through a variety of measures, however, XAI research has not yet provided approaches enabling domain level insights for expert users in strategic situations. In this paper, we discuss the existence of superhuman DRL-based strategies, their properties, the requirements and challenges for transforming them into real-world environments, and the implications for trust through explainability as a key technology.