论文标题
干涉物：对齐钢筋学习剂的光学干涉仪
Interferobot: aligning an optical interferometer by a reinforcement learning agent
论文作者
论文摘要
获取培训数据的局限性限制了深入增强学习（RL）方法对现实世界机器人培训的潜在应用。在这里，我们训练RL代理以对齐马赫·泽尔德干涉仪，这是许多光学实验的重要组成部分，基于单眼摄像机获得的干扰条纹图像。该代理在模拟环境中进行训练，没有任何手工编码的功能或有关物理学的先验信息，然后转移到物理干涉仪中。由于一组域随机化模拟了物理测量中的不确定性，该代理在没有任何微调的情况下成功地对准了该干涉仪，从而达到了人类专家的绩效水平。
Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots. Here we train an RL agent to align a Mach-Zehnder interferometer, which is an essential part of many optical experiments, based on images of interference fringes acquired by a monocular camera. The agent is trained in a simulated environment, without any hand-coded features or a priori information about the physics, and subsequently transferred to a physical interferometer. Thanks to a set of domain randomizations simulating uncertainties in physical measurements, the agent successfully aligns this interferometer without any fine tuning, achieving a performance level of a human expert.
