Transparent Robot Learning

Robots reveal reward learning when asking questions

Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today’s robots optimize for informative questions that actively probe the human’s preferences as efficiently as possible. But while informative questions make sense from the robot’s perspective, human onlookers may find them arbitrary and misleading. For example, consider an assistive robot learning to put away the dishes. Based on your answers to previous questions this robot knows where it should stack each dish; however, the robot is unsure about right height to carry these dishes. A robot optimizing only for informative questions focuses purely on this height: it shows trajectories that carry the plates near or far from the table, regardless of whether or not they stack the dishes correctly. As a result, when we see this question, we mistakenly think that the robot is still confused about where to stack the dishes! We formalize active preference-based learning from the human’s perspective.

A robot asking multiple-choice questions to learn the human’s reward function.

We hypothesize that — from the human’s point-of-view — the robot’s questions reveal what the robot has and has not learned. Our insight enables robots to use questions to make their learning process transparent to the human operator. We develop and test a model that robots can leverage to relate the questions they ask to the information these questions reveal. We then introduce a trade-off between informative and revealing questions that considers both human and robot perspectives: a robot that optimizes for this trade-off actively gathers information from the human while simultaneously keeping the human up to date with what it has learned. We evaluate our approach across simulations, online surveys, and in-person user studies. We find that robots which consider the human’s point of view learn just as quickly as state-of-the-art baselines while also communicating what they have learned to the human operator.