A set of reinforcement learning (RL) methods for predictive control in adaptive optics.
Through trial and error we learn a function that maps information of a wavefront sensor (WFS) to commands to a deformable mirror to correct for wavefront distortions created by the atmosphere when observing with ground-based telescopes. We have tested different wavefront sensors and instrument simulations.
![](https://www.bsc.es/sites/default/files/public/styles/bscw2_-_simple_crop_style/public/bscw2/content/software-app/logo/ao-rl.png?itok=JZhw6mXu&sc=afc389776174c44985ffaaa4b1e4ec9f)
Contacte:
License: