Reciprocal MIND MELD: Improving Learning From Demonstration via Personalized, Reciprocal TeachingDownload PDF

16 Jun 2022, 10:45 (modified: 14 Nov 2022, 15:12)CoRL 2022 PosterReaders: Everyone
Student First Author: yes
Keywords: meta-learning, personalization, imitation learning
TL;DR: To reduce the problem of suboptimal demonstrations, we introduce Reciprocal MIND MELD which learns a semantically meaningful embedding space to provide actionable robotic feedback to demonstrators to improve upon the quality of their demonstrations.
Abstract: Endowing robots with the ability to learn novel tasks via demonstrations will increase the accessibility of robots for non-expert, non-roboticists. However, research has shown that humans can be poor teachers, making it difficult for robots to effectively learn from humans. If the robot could instruct humans how to provide better demonstrations, then humans might be able to effectively teach a broader range of novel, out-of-distribution tasks. In this work, we introduce Reciprocal MIND MELD, a framework in which the robot learns the way in which a demonstrator is suboptimal and utilizes this information to provide feedback to the demonstrator to improve upon their demonstrations. We additionally develop an Embedding Predictor Network which learns to predict the demonstrator’s suboptimality online without the need for optimal labels. In a series of human-subject experiments in a driving simulator domain, we demonstrate that robotic feedback can effectively improve human demonstrations in two dimensions of suboptimality (p < .001) and that robotic feedback translates into better learning outcomes for a robotic agent on novel tasks (p = .045).
Supplementary Material: zip
19 Replies