no code implementations • 10 May 2023 • Gennie Mansi, Mark Riedl
A core assumption of explainable AI systems is that explanations change what users know, thereby enabling them to act within their complex socio-technical environments.
1 code implementation • 10 Oct 2022 • Amal Alabdulkarim, Madhuri Singh, Gennie Mansi, Kaely Hall, Mark O. Riedl
However, RL agents discard the qualitative features of their training, making it difficult to recover user-understandable information for "why" an action is chosen.