… In this paper, we consider an overlay D2D network, in which multiple D2D pairs coexist on
… of D2D pairs is typically more than that of available channels, and thus multiple D2D pairs …

… In this paper, we proposed content caching strategies for mobile D2D networks based on
multi-agent reinforcement learning. Specifically, UEs are treated as agents, content items as …

… , the user may consider establishing a D2D link with the neighboring user to implement
the … the D2D link, we propose the novel schemes based on deep reinforcement learning to …

… Reinforcement Learning (DRL) algorithm to solve power allocation problem of D2D network
… ; Section III describes the deep reinforcement learning based Power control algorithm …

… mobile networks. The introduction of Millimeter Wave (mm-wave) communications into
D2D-… However, interference among cellular and D2D links remains severe due to spectrum …

… efficiency in D2D-enabled heterogeneous cellular networks. … D2D mode dynamically. We
employ deep deterministic policy gradient (DDPG), a model-free deep reinforcement learning …

… The challenge is that we assume D2D pairs have no idea of the access principles of …
reinforcement learning (DRL) theory, we design a double deep Q-network (DDQN) based D2D …

… problem for D2D-assisted cellular networks based on deep reinforcement learning (DRL), …
Specifically, we consider a timeslotted cellular network, where D2D nodes share the cellular …

… Aiming at maximizing the sum rate of the D2D network, we propose a deep-reinforcement-learning
approach, based on deep-Q-network, to activate D2D transmissions. Simulation …

… D2D communications model is adopted [6]. We adopt a partially connected D2D networks
where each CE-D2D … service area of the n-th CE-D2D user to transmit data within a circle of …