# Automating Experimental Optics with Sample Efficient Machine Learning Methods

arXiv: https://arxiv.org/abs/2503.14260 · HTML: https://mlsanity.com/paper/2503.14260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Exploring Model-based Planning with Policy Networks](https://mlsanity.com/paper/1906.08649/) (2019)
- [Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit](https://mlsanity.com/paper/2008.11659/) (2020)
- [An optical neural network using less than 1 photon per multiplication](https://mlsanity.com/paper/2104.13467/) (2021)
- [Deep reinforcement learning for optical systems: A case study of mode-locked lasers](https://mlsanity.com/paper/2006.05579/) (2020)
- [Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environments](https://mlsanity.com/paper/2011.04424/) (2020)
- [Aligning an optical interferometer with beam divergence control and continuous action space](https://mlsanity.com/paper/2107.04457/) (2021)
- [Model-free reinforcement learning with noisy actions for automated experimental control in optics](https://mlsanity.com/paper/2405.15421/) (2024)
- [Quantum-limited measurements of optical signals from a geostationary satellite](https://mlsanity.com/paper/1608.03511/) (2016)

## Abstract (arXiv)

As free-space optical systems grow in scale and complexity, troubleshooting becomes increasingly time-consuming and, in the case of remote installations, perhaps impractical. An example of a task that is often laborious is the alignment of a high-finesse optical resonator, which is highly sensitive to the mode of the input beam. In this work, we demonstrate how machine learning can be used to achieve autonomous mode-matching of a free-space optical resonator with minimal supervision. Our approach leverages sample-efficient algorithms to reduce data requirements while maintaining a simple architecture for easy deployment. The reinforcement learning scheme that we have developed shows that automation is feasible even in systems prone to drift in experimental parameters, as may well be the case in real-world applications.