Towards Learning to Play Piano with Dexterous Hands and Touch
This work addresses the challenge of robotic piano playing for applications in automation and AI, representing an incremental advance over hardcoded methods.
The paper tackles the problem of enabling a robotic agent to learn piano playing from music scores using reinforcement learning, achieving the ability to handle key positioning, rhythm, volume, and fingering requirements through a touch-augmented reward and task curriculum.
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.