Towards Learning to Play Piano with Dexterous Hands and Touch

TL;DR

This paper presents a reinforcement learning approach for training simulated dexterous robotic hands to play piano directly from music scores, handling complex musical and technical requirements.

Contribution

It introduces a novel RL framework with touch-augmented rewards and curriculum learning for end-to-end piano playing from scratch.

Findings

RL agents can accurately find correct key positions

Agents handle rhythmic, volume, and fingering variations

Study identifies key factors enabling learning success

Abstract

The virtuoso plays the piano with passion, poetry and extraordinary technical ability. As Liszt said (a virtuoso)must call up scent and blossom, and breathe the breath of life. The strongest robots that can play a piano are based on a combination of specialized robot hands/piano and hardcoded planning algorithms. In contrast to that, in this paper, we demonstrate how an agent can learn directly from machine-readable music score to play the piano with dexterous hands on a simulated piano using reinforcement learning (RL) from scratch. We demonstrate the RL agents can not only find the correct key position but also deal with various rhythmic, volume and fingering, requirements. We achieve this by using a touch-augmented reward and a novel curriculum of tasks. We conclude by carefully studying the important aspects to enable such learning algorithms and that can potentially shed light on future research in this direction.