Abstract
We propose a multi-task-learning-aided knowledge transferring approach for effective and scalable deep reinforcement learning in EONs. Case studies with RMSA show that this approach can achieve ∼ 4× learning time reduction and ∼17.7% lower blocking probability.
© 2020 The Author(s)
PDF ArticleMore Like This
Qi Chen, Min Zhu, Tianyu Shen, Jiahua Gu, Chunping Yan, and Pingping Gu
M4A.185 Asia Communications and Photonics Conference (ACP) 2020
Xiaoliang Chen, Jiannan Guo, Zuqing Zhu, Roberto Proietti, Alberto Castro, and S. J. B. Yoo
W4F.2 Optical Fiber Communication Conference (OFC) 2018
Huy Tran Quang, Omar Houidi, Javier Errea-Moreno, Dominique Verchere, and Djamal Zeghlache
Mo4B.3 European Conference and Exhibition on Optical Communication (ECOC) 2022