| Autor: |
Xuan-Kun Li, Jian-Xu Ma, Xiang-Yu Li, Jun-Jie Hu, Chuan-Yang Ding, Feng-Kai Han, Xiao-Min Guo, Xi Tan, Xian-Min Jin |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
Nature Communications, Vol 15, Iss 1, Pp 1-10 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2041-1723 |
| DOI: |
10.1038/s41467-024-45305-z |
| Popis: |
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. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full text from SpringerLink