Reinforcement Learning with Time-dependent Goals for Robotic Musicians

2020/11/11 by Thilo Fryen, Fryen, Thilo, Manfred Eppe +7
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Music Technology and Sound Studies #Music and Audio Processing #Reinforcement Learning in Robotics #Robotics (cs.RO) #cs.AI #cs.RO

paper · pdf · doi:10.48550/arxiv.2011.05715

Preprint, submitted to IEEE Robotics and Automation Letters (RA-L) 2021 with International Conference on Robotics and Automation Conference Option (ICRA) 2021

arxiv created 2020/11/11 · openalex publication_date 2020/11/11 · arxiv updated 2020/11/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Reinforcement learning is a promising method to accomplish robotic control tasks. The task of playing musical instruments is, however, largely unexplored because it involves the challenge of achieving sequential goals - melodies - that have a temporal dimension. In this paper, we address robotic musicianship by introducing a temporal extension to goal-conditioned reinforcement learning: Time-dependent goals. We demonstrate that these can be used to train a robotic musician to play the theremin instrument. We train the robotic agent in simulation and transfer the acquired policy to a real-world robotic thereminist. Supplemental video: https://youtu.be/jvC9mPzdQN4

Citations

• Continuous control with deep reinforcement learning
• Hindsight Experience Replay
• Solving Rubik's Cube with a Robot Hand

Related

• Music Generation using Human-In-The-Loop Reinforcement Learning
• TEACH: Temporal Variance-Driven Curriculum for Reinforcement Learning
• Time as a Control Dimension in Robot Learning
• Learning to Play Piano in the Real World
• Dexterous Robotic Piano Playing at Scale