… Selected aspects of communications and networking … , we analyze research papers applying reinforcementlearning to different aspects of communication and networking. We carefully …
… more convenient, which means that wireless communication … devices are connected to the communicationnetwork, the wireless … DRL to wireless communicationnetworks. An intelligent …
Z Xia, S Xue, J Wu, Y Chen, J Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… takes full advantage of reinforcementlearning and a fast … across the network’s links to suit the prevailing network conditions. … up the learning process to avoid wasting network resources, …
H Ye, GY Li, BHF Juang - IEEE Transactions on Vehicular …, 2019 - ieeexplore.ieee.org
… deep reinforcementlearning based resource management for unicast V2V communications … key parts in the reinforcementlearning are shown and the deep Q-network based proposed …
Y He, C Liang, FR Yu, Z Han - IEEE Transactions on Network …, 2018 - ieeexplore.ieee.org
… caching and device-to-device (D2D) communications. When considering the trust-… reinforcementlearning approach to automatically make a decision for optimally allocating the …
… to surveying the application of reinforcementlearning methods in different wireless IoT … scheduling optimization in a maritime communicationsnetwork based on Software Defined …
Q Wang, W Zhang, Y Liu, Y Liu - IEEE Communications Letters, 2019 - ieeexplore.ieee.org
… , we propose Dueling Deep Q-network (DDQN) algorithm which introduces neural networks and dueling structure into Q-learning. Simulation results demonstrate the proposed …
Z Mlika, S Cherkaoui - Annals of Telecommunications, 2021 - Springer
… network slicing architecture. We focus on a non-cellular network scenario where vehicles communicate … direct device-to-device interface (ie, sidelink communication). In such a vehicular …
C Zhong, MC Gursoy… - … Cognitive Communications …, 2020 - ieeexplore.ieee.org
… network edge using a deep reinforcementlearning framework with Wolpertinger architecture. In particular, we propose deep actorcritic reinforcementlearning … , communicationnetworks…