A meta unit for co-constructing a computational scaffold model to guide human motor learning

Published: 09 Oct 2024, Last Modified: 02 Dec 2024NeurIPS 2024 Workshop IMOL PosterEveryoneRevisionsBibTeXCC BY 4.0
Track: Full track
Keywords: computational scaffolding, motor learning, embodiment modeling
TL;DR: Under the assumption of difference in embodiments between the teacher and the learner, our approach aims to enable the learner to discover their own optimal learning policy, while being guided by the teacher on-demand.
Abstract: Learning of e.g. a dexterous motor skill, which is common in medical training, sports, or playing a musical instrument, is time-costly and needs supervision from a teacher, to avoid injury and to progress. Importantly, learning a motor skill requires active practice, and adjusting one’s own individual embodiment to perform the target movement. We introduce a meta unit for co-constructing a computational scaffold for learning. It targets to optimize the learning process of a student, as well as the intervention of their teacher. This approach aims to enable the student to discover their own optimal learning policy while being guided by the teacher on demand, with the ultimate goal of improving beyond the capacity of the teacher.
Submission Number: 25
Loading