Domain-Level Explainability – A Challenge for Creating Trust in Superhuman AI Strategies [article]

Jonas Andrulis, Ole Meyer, Grégory Schott, Samuel Weinbach, Volker Gruhn
2020 arXiv   pre-print
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
more » ... nd 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.
arXiv:2011.06665v1 fatcat:qwqpfzjz7nhmjg2ngx2bkip57i