… investigate the IW decision problem in mobile edge computing, that is to adaptively adjust
ini… policy (a neural network function) using deep reinforcement learning. We propose several …

… We regard the mobile edge computing as a cloud-edge collaborative network N. Several
important variables are defined as following. \(S=\{s_0,...,s_i,...,s_{|S|}\}\) denotes the set of …

… We formulate the problem as a partially observable Markov decision process (POMDP),
which is solved by a policy gradient deep reinforcement learning (DRL) based approach. …

… of mobile devices and the mean slowdown of tasks in the queue, we propose a deep
reinforcement learning(… The simulation results show that the deep reinforcement learning based …

… Tyson, “Deep reinforcement learning in cache-aided MEC networks,” in 2019 IEEE … with
general task graph in mobile edge computing: A deep reinforcement learning approach,” arXiv …

… Abstract—Mobile Edge Computing (MEC) meets the delay requirements of … to the edge of
the networks. Service caching is to cache application services and related databases at Edge …

… with mobile edge computing. We put our emphasis to investigate the design of a stochastic
computation offloading policy for a representative MU and use deep reinforcement learning …

… with considering mobile vehicles as mobile edge servers in vehicular edge … deep reinforcement
learning based computation offloading with mobile vehicles in vehicular edge computing…

… Based on the multi-agent deep reinforcement learning, we propose a priority driven cooperative
task offloading algorithm. We summarize the main contributions of this paper as follows: …

Device-to-Device (D2D) caching assists Mobile Edge Computing (MEC) based caching in …
Due to the complexity and dynamics of the problems, a deep reinforcement learning approach …