.png){kind=icon}
.png){kind=icon}
Return
QER-LPD3QN: A quantum-Inspired Sequence-Aware deep reinforcement learning algorithm for path planning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2026.131575.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• QER-LPD3QN integrates LSTM and QER to handle temporal inconsistency. • QER rotations cut trajectory smoothness cost by 87.5% vs. IDDQN. • Achieves 100% success in dynamic scenes and exceeds PPO by 20% success. • Maintains sub-4 ms latency and improves sample efficiency by 5.4% vs. PER-LSTM.
Keywords:
QER-LPD3QN
LSTM
path planning
deep reinforcement learning
trajectory smoothness
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W