skip to main content

Photonic architecture for reinforcement learning

Flamini, Fulvio ; Hamann, Arne ; Jerbi, Sofiène ; Trenkwalder, Lea M ; Nautrup, Hendrik Poulsen ; Briegel, Hans J

New journal of physics, 2020-04, Vol.22 (4), p.45002 [Periódico revisado por pares]

Bristol: IOP Publishing

Texto completo disponível

Citações Citado por
  • Título:
    Photonic architecture for reinforcement learning
  • Autor: Flamini, Fulvio ; Hamann, Arne ; Jerbi, Sofiène ; Trenkwalder, Lea M ; Nautrup, Hendrik Poulsen ; Briegel, Hans J
  • Assuntos: Algorithms ; Architecture ; Artificial intelligence ; Computer simulation ; Finite element method ; integrated photonic circuits ; Machine learning ; Photonics ; Physics ; quantum photonics ; reinforcement learning
  • É parte de: New journal of physics, 2020-04, Vol.22 (4), p.45002
  • Notas: NJP-111292.R1
  • Descrição: The last decade has seen an unprecedented growth in artificial intelligence and photonic technologies, both of which drive the limits of modern-day computing devices. In line with these recent developments, this work brings together the state of the art of both fields within the framework of reinforcement learning. We present the blueprint for a photonic implementation of an active learning machine incorporating contemporary algorithms such as SARSA, Q-learning, and projective simulation. We numerically investigate its performance within typical reinforcement learning environments, showing that realistic levels of experimental noise can be tolerated or even be beneficial for the learning process. Remarkably, the architecture itself enables mechanisms of abstraction and generalization, two features which are often considered key ingredients for artificial intelligence. The proposed architecture, based on single-photon evolution on a mesh of tunable beamsplitters, is simple, scalable, and a first integration in quantum optical experiments appears to be within the reach of near-term technology.
  • Editor: Bristol: IOP Publishing
  • Idioma: Inglês

Buscando em bases de dados remotas. Favor aguardar.