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.

Deep reinforcement learning control of white-light continuum generation

Valensise C. M.;Cerullo G.;Polli D.
2021-01-01

Abstract

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.
2021
File in questo prodotto:
File Dimensione Formato  
106 - Valensise - Optica 2021 (Deep Reinforcement Learning).pdf

accesso aperto

Descrizione: PDF dalla rivista
: Publisher’s version
Dimensione 3.8 MB
Formato Adobe PDF
3.8 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1175516
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 16
social impact