Aligning an optical interferometer with beam divergence control and continuous action space
This work addresses a domain-specific problem in optical physics by applying reinforcement learning to real-world experimental setups.
The paper tackled the problem of aligning an optical interferometer with beam divergence control using reinforcement learning in a continuous action space, achieving performance that significantly outperformed existing solutions and human experts.
Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly outperforms an existing solution and a human expert.