Evaluating Human-like Explanations for Robot Actions in Reinforcement Learning Scenarios
This addresses the need for more accessible explainable AI in robotics for non-expert users, though it is incremental as it builds on existing explanation methods.
The paper tackled the problem of making robot action explanations understandable to non-experts by evaluating human-like explanations based on probability of success, finding that non-expert participants rated these explanations higher and with less variance than technical Q-value explanations.
Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations.