UAV Coverage Path Planning With Quantum-Based Recurrent Deep Deterministic Policy Gradient
- Authors
- Silvirianti; Narottama, Bhaskara; Shin, Soo Young
- Issue Date
- May-2024
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Autonomous aerial vehicles; Training; Optimization; NOMA; Encoding; Vehicle dynamics; Resource management; Deep deterministic policy gradient; energy efficiency; quantum embedding; recurrent; UAV communications
- Citation
- IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, v.73, no.5, pp 7424 - 7429
- Pages
- 6
- Journal Title
- IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
- Volume
- 73
- Number
- 5
- Start Page
- 7424
- End Page
- 7429
- URI
- https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/28805
- DOI
- 10.1109/TVT.2023.3347219
- ISSN
- 0018-9545
1939-9359
- Abstract
- This study proposes quantum-based deep deterministic policy gradient (Q-DDPG) and quantum-based recurrent DDPG (Q-RDDPG) schemes for time-series optimization in UAV communications. Herein, Q-DDPG-based actor-critic reinforcement learning is utilized to optimize action selections in a large state and continuous action space. In this scheme, quantum models are exploited to reduce computational complexity and training loss. As a particular case, Q-DDPG and Q-RDDPG are employed for trajectory optimization and dynamic resource allocation in UAV communications. The results demonstrate that Q-DDPG and Q-RDDPG schemes achieved higher rewards with lower training losses compared to classical DDPG.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - School of Electronic Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/28805)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.