Abstract
We propose a knowledge distillation scheme for deep reinforcement learning-based optical networks. Distilling knowledge from the well-trained model of one traffic pattern to others traffic patterns, so that the latter's training more time-efficient and performance-effective.
© 2021 The Author(s)
PDF ArticleMore Like This
Yang Liu, Bin Chen, Gongchao Su, Mingjun Dai, and Xiaohui Lin
JS3C.1 Optoelectronics and Communications Conference (OECC) 2021
José Suárez-Varela, Albert Mestres, Junlin Yu, Li Kuang, Haoyu Feng, Pere Barlet-Ros, and Albert Cabellos-Aparicio
M2A.6 Optical Fiber Communication Conference (OFC) 2019
Suhao Zheng, Xiao Xiao, Yajie Li, Zebin Zeng, Zhengyin Liang, Yongli Zhao, and Jie Zhang
W2C.4 Asia Communications and Photonics Conference (ACP) 2021