arrow
返回

Variational quantum reinforcement learning via evolutionary optimization

delete2022-02-15
delete34
delete
OA
AI
S
Samuel Yen-Chi Chen *
C
Chih-Min Huang
C
Chia-Wei Hsing
H
Hsi‐Sheng Goan
Y
Ying-Jer Kao
DOI:10.1088/2632-2153/ac4559delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Recent advances in classical reinforcement learning (RL) and quantum computation point to a promising direction for performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here, we present two frameworks for deep quantum RL tasks using gradient-free evolutionary optimization. First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using amplitude encoding. Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL in the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.
Keyword:
quantum machine learning
artificial intelligence
variational quantum circuits
quantum neural networks
reinforcement learning
evolutionary optimization

期刊

M
Machine Learning-Science and Technology
IF:
4.6
论文数:
1.1K
被引数:
3.4K

机构

U
united states department of energy (doe)
学者数:
11.3W
论文数: 9.6W
被引数: 246
B
Brookhaven National Laboratory
学者数:
6.4K
论文数: 4.9K
被引数: 1.9W
引用论文

引用论文

err分享
err收藏
Fault-Diagnosis Applications
err
IF0
err2011-01-01
err0
PREAI
errRolf Isermann
err分享
err收藏
err分享
err收藏
学者 查看更多内容