Deep reinforcement learning control of white-light continuum generation

White-light continuum (WLC) generation in bulk media finds numerous applications in ultrafast optics and spectroscopy. Due to the complexity of the underlying spatiotemporal dynamics, WLC optimization typically follows empirical procedures. Deep reinforcement learning (RL) is a branch of machine learning dealing with the control of automated systems using deep neural networks. In this Letter, we demonstrate the capability of a deep RL agent to generate a long-term-stable WLC from a bulk medium without any previous knowledge of the system dynamics or functioning. This work demonstrates that RL can be exploited effectively to control complex nonlinear optical experiments. (C) 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Automated summary

This study demonstrates the ability of a deep reinforcement learning agent to generate a long-term stable white-light continuum in a bulk medium without prior knowledge of the system dynamics. It shows that deep reinforcement learning can effectively be used to control complex nonlinear optical experiments.