… , we propose deep reinforcementlearning (DRL) … wirelessnetworks for smart cities. For this purpose, we use one of the DRL models, Q-learning, for MAC-RA in dense wirelessnetworks …
K Shah, M Kumar - … Conference on Mobile Adhoc and Sensor …, 2007 - ieeexplore.ieee.org
… In this paper, we advocate the use of reinforcementlearning to address the issue of … use of reinforcementlearning for task adaptation and scheduling in wireless sensor networks. We …
J Yang, S He, Y Xu, L Chen, J Ren - Sensors, 2019 - mdpi.com
… We introduce the reinforcementlearning algorithm to dynamically learn this information, and all of the information will be captured by the reinforcementlearning model of the routing …
N Abuzainab, T Erpek, K Davaslioglu… - MILCOM 2019-2019 …, 2019 - ieeexplore.ieee.org
… We develop a deep reinforcementlearning solution for nodes to decide on whether to participate in communication, defend the network, or attack other transmissions for the sake of …
Y Li, W Zhang, CX Wang, J Sun… - … and Networking, 2020 - ieeexplore.ieee.org
… We consider a wirelessnetwork containing N correlated channels whose states can be either vacant (0) or occupied (1). The joint state transition of these channels follows a 2N -states …
… In this paper, one reinforcementlearning method, Q-Learning… retransmissions in single-hop networks. A similar approach has … of the application of reinforcementlearning to the medium …
… reinforcementlearning for RRAM in wirelessnetworks, we included the following terms during the search stage along with ”AND/OR” combinations of them; ”deep reinforcementlearning…
… This MDP is then solved using a Deep Q-Network, a recent deep reinforcementlearning algorithm that is at once scalable and model-free. We compare our scheduling algorithm to …
… For example, we know that the expected transmission time of a packet in a wireless network is 20 minutes. However, this information may not be so meaningful because it may …