# Interferobot: aligning an optical interferometer by a reinforcement learning agent

arXiv: https://arxiv.org/abs/2006.02252 · HTML: https://mlsanity.com/paper/2006.02252/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2020.

## Built on by (most cited first, 12 of 12)

- [Reinforcement learning for optimization of variational quantum circuit architectures](https://mlsanity.com/paper/2103.16089/) (2021)
- [A Study of Bayesian Neural Network Surrogates for Bayesian Optimization](https://mlsanity.com/paper/2305.20028/) (2023)
- [Bayesian Optimization with High-Dimensional Outputs](https://mlsanity.com/paper/2106.12997/) (2021)
- [Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information](https://mlsanity.com/paper/2103.07084/) (2021)
- [Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks](https://mlsanity.com/paper/2404.03099/) (2024)
- [Active Alignments of Lens Systems with Reinforcement Learning](https://mlsanity.com/paper/2503.02075/) (2025)
- [Aligning an optical interferometer with beam divergence control and continuous action space](https://mlsanity.com/paper/2107.04457/) (2021)
- [Scalable Bayesian optimization with high-dimensional outputs using randomized prior networks](https://mlsanity.com/paper/2302.07260/) (2023)
- [Model-free reinforcement learning with noisy actions for automated experimental control in optics](https://mlsanity.com/paper/2405.15421/) (2024)
- [A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems](https://mlsanity.com/paper/2603.21496/) (2026)
- [Adaptation of Quadruped Robot Locomotion with Meta-Learning](https://mlsanity.com/paper/2107.03741/) (2021)
- [Trajectory-Level Data Augmentation for Offline Reinforcement Learning](https://mlsanity.com/paper/2605.13401/) (2026)

## Abstract (arXiv)

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.