Reciprocal MIND MELD: Improving Learning From Demonstration via Personalized, Reciprocal Teaching

Mariah L Schrum, Erin Hedlund-Botti, Matthew Gombolay
Proceedings of The 6th Conference on Robot Learning, PMLR 205:956-966, 2023.

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).

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-schrum23a, title = {Reciprocal MIND MELD: Improving Learning From Demonstration via Personalized, Reciprocal Teaching}, author = {Schrum, Mariah L and Hedlund-Botti, Erin and Gombolay, Matthew}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {956--966}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/schrum23a/schrum23a.pdf}, url = {https://proceedings.mlr.press/v205/schrum23a.html}, 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).} }
Endnote
%0 Conference Paper %T Reciprocal MIND MELD: Improving Learning From Demonstration via Personalized, Reciprocal Teaching %A Mariah L Schrum %A Erin Hedlund-Botti %A Matthew Gombolay %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-schrum23a %I PMLR %P 956--966 %U https://proceedings.mlr.press/v205/schrum23a.html %V 205 %X 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).
APA
Schrum, M.L., Hedlund-Botti, E. & Gombolay, M.. (2023). Reciprocal MIND MELD: Improving Learning From Demonstration via Personalized, Reciprocal Teaching. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:956-966 Available from https://proceedings.mlr.press/v205/schrum23a.html.

Related Material