arrow
返回

QER-LPD3QN: A quantum-Inspired Sequence-Aware deep reinforcement learning algorithm for path planning

delete2026-02-07
delete0
PRE
AI
H
He Guo
Z
Zhengyi Chai
Y
Ya-Lun Li
DOI:10.1016/j.eswa.2026.131575delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• QER-LPD3QN集成了LSTM和QER以处理时序不一致性。• QER旋转使轨迹平滑成本比IDDQN降低了87.5%。• 在动态场景中实现100%成功率,超过PPO 20%的成功率。• 保持低于4 ms的延迟,并比PER-LSTM提高5.4%的样本效率。
Keyword:
QER-LPD3QN
LSTM
path planning
deep reinforcement learning
trajectory smoothness

期刊

Expert Systems with Applications 封面图
Expert Systems with Applications
IF:
7.5
论文数:
3.0W
被引数:
10.2W

机构

T
Tiangong University
学者数:
1.2W
论文数: 7.7K
被引数: 1.1W
引用论文

引用论文

MOQEA/D: Multi-Objective QEA With Decomposition Mechanism and Excellent Global Search and Its Application
err2024-09-01
err40
PREAI
errDeng, Wu; Cai, Xing; Wu, Daqing; Song, Yingjie; Chen, Huiling; Ran, Xiaojuan; Zhou, Xiangbing; Zhao, Huimin
err分享
err收藏
A review of recent advances in quantum-inspired metaheuristics
err2022-10-23
err0
errOAAI
errShahin Hakemi; Mahboobeh Houshmand; Esmaeil KheirKhah; Seyyed Abed Hosseini
err分享
err收藏
学者 查看更多内容