… Particularly, the optimization of the … reinforcement learning (DRL) on resolving complicated
control problems, we develop a DRL based framework to solve this non-convex optimization …

… Overall, it could be shown that Bayesian optimization can be used very … optimization
was better suited than reinforcement learning for the aim of this project to optimize the surface …

… paper, we study an intelligent reflecting surface (IRS)-aided … , a design problem for jointly
optimizing the base station (BS)’… optimization problem, a novel deep reinforcement learning (…

… optimized … reinforcement learning algorithm (DRL) is exploited to solve our problem.
Specifically, we opt to apply a DRL framework based on proximal policy optimization (PPO) to learn …

… the system to reach multiple sliding surfaces in a finite time. As a … utilizing reinforcement
learning in order to truly optimize the … perturbed conditions using the optimized set of parameters. …

… a reinforcement learning (RL) strategy to address the robust optimal tracking control problem
for an intelligent surface … A neural network (NN) identifier is constructed to learn uncertain …

… DRL for performing shape optimization, we present in this article the first application of deep
… we introduce our reinforcement learning approach and its application to shape optimization. …

… surface polishing robot and the parameter optimization method based on reinforcement learning
… The impedance control parameter method based on reinforcement learning algorithm is …

… reinforcement machine learning to solve difficult environments, namely, potential energy
surfaces, with … extending reinforcement learning to more complicated optimization problems and …

… optimized so as to improve users’ data rates and reduce the BS power consumption. In this
paper, the problem of energy efficiency optimization … based on deep reinforcement learning is …