Machine Learning Approaches For Motor Learning: A Short Review

Baptiste Caramiaux (1) , Jules Françoise (2) , Wanyu Liu (3) , Téo Sanchez (1) , Frédéric Bevilacqua (3, 4)

1 EX-SITU - Extreme Interaction
2 AMI - Architecture et Modèles pour l'Interaction
3 STMS - Sciences et Technologies de la Musique et du Son
4 Interaction Son Musique Mouvement [Paris]

Machine learning approaches have seen considerable applications in human movement modeling, but remain limited for motor learning. Motor learning requires accounting for motor variability, and poses new challenges as the algorithms need to be able to differentiate between new movements and variation of known ones. In this short review, we outline existing machine learning models for motor learning and their adaptation capabilities. We identify and describe three types of adaptation: Parameter adaptation in probabilistic models, Transfer and meta-learning in deep neural networks, and Planning adaptation by reinforcement learning. To conclude, we discuss challenges for applying these models in the domain of motor learning support systems.

Keywords: Movement; Computational Modelling; Machine Learning; Motor Control; Motor Learning; Adaptive Models

Domains: Machine Learning [cs.LG]; Psychology and behavior

Baptiste Caramiaux, Jules Françoise, Wanyu Liu, Téo Sanchez, Frédéric Bevilacqua. Machine Learning Approaches For Motor Learning: A Short Review. Frontiers in Computer Science, inPress. ⟨hal-02558779⟩