Abstract
We propose a deep reinforcement learning-based spectrum assignment with a multi-metric reward function and assignable boundary slot mask. The mask restricts options to assignable ones and multi-metric function provides informative clues for training, outperforming first-fit.
© 2021 The Author(s)
PDF ArticleMore Like This
Huy Tran Quang, Omar Houidi, Javier Errea-Moreno, Dominique Verchere, and Djamal Zeghlache
Mo4B.3 European Conference and Exhibition on Optical Communication (ECOC) 2022
Xin Wang, Yue-Cai Huang, Jie Liu, and Siyuan Yu
M4A.211 Asia Communications and Photonics Conference (ACP) 2019
Xiaoliang Chen, Jiannan Guo, Zuqing Zhu, Roberto Proietti, Alberto Castro, and S. J. B. Yoo
W4F.2 Optical Fiber Communication Conference (OFC) 2018