Towards reconciling usability and usefulness of policy explanations for sequential decision-making systems

• Published in: Frontiers in robotics and AI Vol. 11; p. 1375490
• Main Authors: Tambwekar, Pradyumna, Gombolay, Matthew
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 22.07.2024
• Subjects: explainable AI (XAI); human-factors; Interpretability; reinforcement learning; Robotics and AI; user study; explainable AI (XAI); human-factors; Interpretability; user study; reinforcement learning

Safefy-critical domains often employ autonomous agents which follow a sequential decision-making setup, whereby the agent follows a policy to dictate the appropriate action at each step. AI-practitioners often employ reinforcement learning algorithms to allow an agent to find the best policy. Howeve...