Your browser doesn't support javascript.
loading
High-efficiency reinforcement learning with hybrid architecture photonic integrated circuit.
Li, Xuan-Kun; Ma, Jian-Xu; Li, Xiang-Yu; Hu, Jun-Jie; Ding, Chuan-Yang; Han, Feng-Kai; Guo, Xiao-Min; Tan, Xi; Jin, Xian-Min.
Afiliación
  • Li XK; Center for Integrated Quantum Information Technologies (IQIT), School of Physics and Astronomy and State Key Laboratory of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • Ma JX; Hefei National Laboratory, Hefei, 230088, China.
  • Li XY; TuringQ Co., Ltd., Shanghai, 200240, China.
  • Hu JJ; TuringQ Co., Ltd., Shanghai, 200240, China.
  • Ding CY; Center for Integrated Quantum Information Technologies (IQIT), School of Physics and Astronomy and State Key Laboratory of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • Han FK; Hefei National Laboratory, Hefei, 230088, China.
  • Guo XM; Center for Integrated Quantum Information Technologies (IQIT), School of Physics and Astronomy and State Key Laboratory of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University, Shanghai, 200240, China.
  • Tan X; Hefei National Laboratory, Hefei, 230088, China.
  • Jin XM; Center for Integrated Quantum Information Technologies (IQIT), School of Physics and Astronomy and State Key Laboratory of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University, Shanghai, 200240, China.
Nat Commun ; 15(1): 1044, 2024 Feb 05.
Article en En | MEDLINE | ID: mdl-38316815
ABSTRACT
Reinforcement learning (RL) stands as one of the three fundamental paradigms within machine learning and has made a substantial leap to build general-purpose learning systems. However, using traditional electrical computers to simulate agent-environment interactions in RL models consumes tremendous computing resources, posing a significant challenge to the efficiency of RL. Here, we propose a universal framework that utilizes a photonic integrated circuit (PIC) to simulate the interactions in RL for improving the algorithm efficiency. High parallelism and precision on-chip optical interaction calculations are implemented with the assistance of link calibration in the hybrid architecture PIC. By introducing similarity information into the reward function of the RL model, PIC-RL successfully accomplishes perovskite materials synthesis task within a 3472-dimensional state space, resulting in a notable 56% improvement in efficiency. Our results validate the effectiveness of simulating RL algorithm interactions on the PIC platform, highlighting its potential to boost computing power in large-scale and sophisticated RL tasks.

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: Nat Commun Asunto de la revista: BIOLOGIA / CIENCIA Año: 2024 Tipo del documento: Article País de afiliación: China Pais de publicación: Reino Unido