상세 보기
Knowledge-Driven Deep Reinforcement Learning for Wireless Networks
- Nguyen, Thi My Tuyen;
- Nguyen, The Vi;
- Do, Tung Son;
- Won, Dongwook;
- Cho, Sungrae
Citations
WEB OF SCIENCE
0Citations
SCOPUS
0초록
Deep reinforcement learning (DRL) is a promising technique for solving numerous optimization problems in wireless networks, owing to its high adaptability to dynamic and uncertain wireless environments. However, the lack of interpretability, inherent in the black-box nature of the deep neural networks (DNNs) within DRL, limits its deployment in real-world applications. In this paper, we focus on integrating domain knowledge into DRL to enhance robustness and learning efficiency. Specifically, we review a teacher-student framework, where a teacher agent utilizes knowledge from classical model-based methods to guide a student DRL agent toward improved decision-making.
키워드
Deep reinforcement learning (DRL); knowledge-driven DRL; Wireless networks
- 제목
- Knowledge-Driven Deep Reinforcement Learning for Wireless Networks
- 저자
- Nguyen, Thi My Tuyen; Nguyen, The Vi; Do, Tung Son; Won, Dongwook; Cho, Sungrae
- 발행일
- 2026
- 유형
- Proceedings Paper
- 페이지
- 426 ~ 428
- 언어
- ENG
- 출판사
- IEEE Computer Society
- 분량
- 3 페이지
- ISSN
- P 1976-7684