J Zheng, X Tang, X Wei, H Shen… - IEEE Wireless …, 2021 - ieeexplore.ieee.org
… The performance of hybrid NOMA systems depends on resource allocation including power and channel. In this paper, we focus on the channelassignment. Since channelassignment …
SM Senouci, G Pujoile - 10th International Conference on …, 2003 - ieeexplore.ieee.org
… We consider in this paper not only channelassignment task but also the call admission control problem in a cellular network. We consider a DCA system handling not only one class of …
S Singh, D Bertsekas - Advances in neural information …, 1996 - proceedings.neurips.cc
… the channelassignment problem … reinforcementlearning (RL) (eg, Barto, Bradtke and Singh, 1995, or the recent textbook by Bertsekas and Tsitsiklis, 1996). Our method learns channel …
J Nie, S Haykin - IEEE Transactions on Neural Networks, 1999 - ieeexplore.ieee.org
… channelassignment (DCA) problem by using a form of realtime reinforcementlearning known as Q-learning in … is designed to learn an optimal channelassignment policy by directly …
J Nie, S Haykin - IEEE Transactions on Vehicular Technology, 1999 - ieeexplore.ieee.org
… channelassignment (DCA) problem through a form of real-time reinforcementlearning known as Q learning. … , the system is designed to learn an optimal assignment policy by directly …
Y Wang, K Zheng, D Tian, X Duan, J Zhou - Frontiers of Information …, 2020 - Springer
… learn the proper policies of its channel selection and backoff adaptation with the goal of avoiding channel … achieve collaborative optimization of their channelassignments, we propose a …
X Ye, Y Yu, L Fu - IEEE Transactions on Wireless …, 2021 - ieeexplore.ieee.org
This paper investigates a new medium access control (MAC) protocol for multi-channel heterogeneous networks (HetNets) based on deep reinforcementlearning (DRL), referred to as …
HV Vu, M Farzanullah, Z Liu… - 2022 IEEE 95th …, 2022 - ieeexplore.ieee.org
… the problem of joint channelassignment and power … channel information might not be viable in C-V2X systems with large number of users. Utilizing a multi-agent reinforcementlearning (…