mlsanityData to 14 Oct 2026

Automating Experimental Optics with Sample Efficient Machine Learning Methods

arXiv 2503.14260 ↗First posted 18 Mar 2025physics.optics cs.LGcited by 0

Not on the map. Why?

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.

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

11 of 50 references.

References · 11

  1. 2018World Modelscited by 1,513
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  3. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  4. 2019Exploring Model-based Planning with Policy Networkscited by 90
  5. 2020Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unitcited by 65
  6. 2021An optical neural network using less than 1 photon per multiplicationcited by 30
  7. 2020Deep reinforcement learning for optical systems: A case study of mode-locked laserscited by 5
  8. 2020Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environmentscited by 3
  9. 2021Aligning an optical interferometer with beam divergence control and continuous action spacecited by 2
  10. 2024Model-free reinforcement learning with noisy actions for automated experimental control in opticscited by 2
  11. 2016Quantum-limited measurements of optical signals from a geostationary satellitecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Model-free Optical Processors using In Situ Reinforcement Learning with Proximal Policy Optimization
  2. 2025Active Alignments of Lens Systems with Reinforcement Learning
  3. 2025Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits
  4. 2026OPTIAGENT: A Physics-Driven Agentic Framework for Automated Optical Design
  5. 2024Inverse Design of Photonic Crystal Surface Emitting Lasers is a Sequence Modeling Problem
  6. 2026On-sky demonstration of reinforcement learning for adaptive optics control
  7. 2025Shaping Laser Pulses with Reinforcement Learning
  8. 2024Meent: Differentiable Electromagnetic Simulator for Machine Learning