Speaker
Description
The PhD project explores the application of Deep Reinforcement Learning (DRL) to optimize the locking procedure of high-finesse Fabry-Pérot (FP), critical components in gravitational wave (GW) detectors such as Advanced Virgo, LIGO and KAGRA. Speeding up the locking procedure and establishing the resonance condition of these cavities are crucial aspects to improve the detector’s duty cycle, enhancing the time within the interferometers are able to detect new significant signals. However, the process is highly challenging due to several non-linear effects, such as cavity ringing and resonance drift caused by thermal effect and radiation pressure. These effects spoil the main optical signals as the optical power and the Pound Drever Hall error signal, crucial cavity state witnesses for control purposes. To address these challenges, we propose a DRL-based solution capable of adapting to the dynamic and non-linear nature of the cavity’s behavior. A simulator was developed to model the optical response of a FP cavity, taking into account the ring down effect. Subsequently, the simulator was used to develop a custom Gymnasium environment with which the RL agent could interact and learn the best action policy. Lastly, the critical challenge of the SimToReal transfer and the problems arising from the reality gap is also covered, laying the groundwork for future applications of this technique on real optical set-ups and potentially providing a predictive and adaptive alternative for managing the complex dynamics of FP cavities, aiming to significantly improve lock acquisition efficiency and reliability compared to traditional methods.