Direct imaging of Earth-like exoplanets is one of the significant scientific drivers of the next generation of ground-based telescopes. Typically, Earth-like exoplanets are located at tiny angular separations from their host stars rendering their identification difficult. Consequently, the adaptive optics (AO) system’s control algorithm must be carefully designed to distinguish the exoplanet from the residual light produced by the host star.
A new promising avenue of research aimed at improving AO control builds on data-driven control methods such as Reinforcement Learning (RL) methods. It is an active branch of the machine learning research field, where control of a system is learned through interaction with the environment. Thus, RL can be seen as an automated approach for AO control. In particular, model-based reinforcement learning (MBRL) has been shown to cope with both temporal and misregistration errors. Similarly, it has been demonstrated to adapt to non-linear wavefront sensing while being efficient to train and execute.
In this work, we implement and adapt an RL method called Policy Optimizations for AO (PO4AO) to the GHOST test bench at ESO headquarters, where we show strong performance on cascaded AO system lab simulation. Further, the results align with the previously obtained results with the method.
