… In this work, we solve the VNF-FGE problem by means of a Reinforcement Learning approach
to model a placement policy in a Network Function Virtualization infrastructure. For that …

… First, we propose two activation functions for neural network function approximation in
reinforcement learning: the sigmoid-weighted linear unit (SiLU) and its derivative function (dSiLU). …

… ) to model the dynamic network state transitions. To jointly … , we first devise a customized
Deep Reinforcement Learning (DRL) … network behavior within the general framework of network …

… physical network resources and costs through Network Function … -Defined Networks (SDNs)
are used to reconfigure the network … Learning mechanisms, such as Deep Reinforcement …

… the network conditions, available pool of resources, and the VNF requirements, with the goal
of minimizing a cost function … a solution based on deep reinforcement learning (DRL). More …

… reinforcement learning (DRL), which is an indepth combination of artificial neural network
(ANN) and reinforcement learning … multiple layers of neural network that replicate the structure …

… , network function virtualization (NFV) technique is used to access resources of the network
and a reinforcement learning … problem of resource allocation in IoT networks. The traffic of IoT …

… neural network function approximation difficult in practice. … of a reinforcement learning task
that requires effective function … Q-learning with a series of manually designed neural networks …

… networks [1, 4, 5]. SDN creates a programmable network by centralizing the control functions
of routing devices while NFV decouples various network functions from physical network …

… Abstract—This paper proposes an effective and novel multiagent deep reinforcement learning
(MADRL)-based method for solving the joint virtual network function (VNF) placement and …