English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For strategic problems, intelligent systems based on Deep ReinforcementLearning (DRL) have demonstrated an impressive ability to learn advancedsolutions that can go far beyond human capabilities, especially when dealingwith complex scenarios. While this creates new opportunities for thedevelopment of intelligent assistance systems with groundbreakingfunctionalities, applying this technology to real-world problems carriessignificant risks and therefore requires trust in their transparency andreliability. With superhuman strategies being non-intuitive and complex bydefinition and real-world scenarios prohibiting a reliable performanceevaluation, the key components for trust in these systems are difficult toachieve. Explainable AI (XAI) has successfully increased transparency formodern AI systems through a variety of measures, however, XAI research has notyet provided approaches enabling domain level insights for expert users instrategic situations. In this paper, we discuss the existence of superhumanDRL-based strategies, their properties, the requirements and challenges fortransforming them into real-world environments, and the implications for trustthrough explainability as a key technology.

Domain-Level Explainability -- A Challenge for Creating Trust in Superhuman AI Strategies