论文标题
强化学习与时间相关的机器人音乐家的目标
Reinforcement Learning with Time-dependent Goals for Robotic Musicians
论文作者
论文摘要
强化学习是完成机器人控制任务的一种有前途的方法。但是，演奏乐器的任务在很大程度上没有探索，因为它涉及实现具有时间维度的顺序目标的挑战。在本文中，我们通过将时间扩展到目标条件的强化学习：时间依赖于时间依赖的目标来解决机器人音乐。我们证明这些可以用来训练机器人音乐家弹奏Theremin乐器。我们在模拟中训练机器人代理，并将获得的政策转移到现实世界的机器人秘密主义者。补充视频：https：//youtu.be/jvc9mpzdqn4
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
