… In this paper, we proposed federated deep reinforcement learning as a tool to solve a
distributed power control problem in a wireless multi-cell network. We investigated the perfor…

… and sub-6 GHz band) wireless network where both orthogonal and non-… reinforcement
learning technique are proposed. The latter are based on multiple parallel deep neural networks …

… We adopt the reinforcement learning (RL) framework to learn the optimal controller for each
UE, which makes HO decisions. We incorporate the situation and exploration information of …

… to exploit the dynamic nature of network traffic in reducing energy … reinforcement learning
algorithm for the base station such that it can continuously adapt to the ever-changing network …

… By utilising Reinforcement Learning (RL) techniques, we provide an adaptive framework,
which continuously performs weak training in an energy-aware system. We motivate this using …

… service requirements, and communicate via industrial wireless networks (IWNs). However, …
To address this problem, a deep reinforcement learningbased dynamic priority multichannel …

… The control loop is built on top of a software-defined wireless network controller (in our case,
the Ethanol [10] communication layer). Both programs run in the same host, and both run as …

… In this paper a reinforcement learning-based sleep scheduling for coverage (RLSSC)
algorithm is proposed for solarpowered wireless sensor networks. We adopt a two-stage sleep …

… In this paper, we proposed a reinforcement learning for lifetime optimisation, named
R2LTO, that optimises energy usage by choosing the optimal path to the sink in a dynamic and …

… In this paper, we present MRL-QRP, a multi-agent cooperative reinforcement learning … a
distributed reinforcement learning algorithm, only locally observed network information and …