Highest-contrast imaging with ELT-PCS requires a highly performant and robust control system. The main science case of nearby Exo-Earths calls for high contrast at very small angular separations of tens of milliarcseconds where the contrast is affected by quickly changing eXtreme AO residuals and quasi-static speckles. Data-driven control methods such as Reinforcement Learning (RL), a subfield of machine learning where system control is learned through interaction with the environment, hold great promise and now receive a lot of interest in the XAO field. Model-based RL provides automated, self-tuning control for AO while being efficient to execute and train. It can handle temporal and misregistration errors and adapt to non-linear wavefront sensing. In addition, the concept of RL has a huge potential for focal plane wavefront control to tackle the quasi-static speckles.

This talk will discuss recent advances, motivation, and prospects of RL methods for adaptive optics wavefront sensor control and focal plane wavefront control. I will present our RL approach called Policy Optimizations for AO (PO4AO), summarize the tests with the GHOST test bench at ESO headquarters, and discuss the prospects of running PO4AO on-sky with an optimized RTC implementation.

Jalo Nousiainen, LUT University