Exploring reinforcement learning to enhance focal plane wavefront correction for vortex coronagraphs

High Contrast Imaging (HCI) on ground-based telescopes suffers from phase aberrations on the observed wave front caused by atmospheric turbulence. Adaptive Optics (AO) systems are adept at correcting these aberrations, but fall short in the correction of non-common path aberrations (NCPAs). NCPAs arise because the wavefront sensor (WFS) measures and corrects a wavefront that is different from that affecting the science images, thus requiring additional intervention. This work makes use of focal-plane wavefront sensing and reinforcement learning (RL) to address the wavefront aberrations caused by NCPAs. The PO4NCPA algorithm utilizes sequential phase diversity to address phase ambiguities and is tested on a simulation designed for the Mid-infrared ELT Imager and Spectrograph (METIS) instrument. In this paper, we present the performance of PO4NCPA with scalar and vector vortex coronagraphs to demonstrate its flexibility.