Image-based reinforcement learning for robust mode hop recovery in external-cavity diode lasers
Abstract
Conventional laser frequency stabilization techniques such as table-lookup or heuristic methods have significant limitations due to intrinsic hysteresis and stochastic mode competition. To overcome this challenge, we introduce a simple hysteresis-aware protocol and a tailored image-based reinforcement learning (RL) framework. This approach enables robust mode hop recovery in external-cavity diode lasers (ECDLs). Using a Rainbow deep Q-network (DQN) trained entirely in simulation, our RL agent achieves 100% recovery success rate across all 163 continuous temperature drifts produced under deliberately extreme perturbations during a three-day stress test. Under challenging discrete test conditions with abrupt current jumps, the success probability reaches 99.9%, with only one failure recorded out of one thousand trials. The controller generalizes well across environmental perturbations, such as temperature fluctuations, without requiring additional calibration. Our approach provides real-time adaptive control with minimal human intervention, marking a step toward fully autonomous operation in quantum experiments and precision optical systems.
Related
- Reinforcement learning for robust calibration of multiqudit quantum gates
- Design and fabrication of a silicon nitride double-ring Vernier filter for narrow-linewidth external-cavity laser in co-packaged optics
- Design of a thermal loading resilient optical enhancement cavity for operation at 515 nm for X-ray production through inverse Compton scattering in an energy recovery linac
- Discovering network resilience formulas with symbolized reinforcement learning
- Reinforcement learning to disentangle multiqubit quantum states from partial observations
BibTeX
@article{bae2026imagebased,
title = {{Image-based reinforcement learning for robust mode hop recovery in external-cavity diode lasers}},
author = {Jaeick Bae and Kyoungsik Yu and Yunheung Song and Jeong Ho Han and Jongchul Mun},
journal = {Communications Physics},
year = {2026},
month = oct,
doi = {10.1038/s42005-026-02931-x},
url = {https://www.nature.com/articles/s42005-026-02931-x},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Image-based reinforcement learning for robust mode hop recovery in external-cavity diode lasers
AU - Jaeick Bae
AU - Kyoungsik Yu
AU - Yunheung Song
AU - Jeong Ho Han
AU - Jongchul Mun
PY - 2026
DA - 2026/10/21
JO - Communications Physics
DO - 10.1038/s42005-026-02931-x
UR - https://www.nature.com/articles/s42005-026-02931-x
AB - Conventional laser frequency stabilization techniques such as table-lookup or heuristic methods have significant limitations due to intrinsic hysteresis and stochastic mode competition. To overcome this challenge, we introduce a simple hysteresis-aware protocol and a tailored image-based reinforcement learning (RL) framework. This approach enables robust mode hop recovery in external-cavity diode lasers (ECDLs). Using a Rainbow deep Q-network (DQN) trained entirely in simulation, our RL agent achieves 100% recovery success rate across all 163 continuous temperature drifts produced under deliberately extreme perturbations during a three-day stress test. Under challenging discrete test conditions with abrupt current jumps, the success probability reaches 99.9%, with only one failure recorded out of one thousand trials. The controller generalizes well across environmental perturbations, such as temperature fluctuations, without requiring additional calibration. Our approach provides real-time adaptive control with minimal human intervention, marking a step toward fully autonomous operation in quantum experiments and precision optical systems.
SN - 2399-3650
ER -