In this paper, a new type of 3D bin packing problem (BPP) is proposed, in which a number of cuboidshaped items must be put into a bin one by one orthogonally. The objective is to find a way to place these items that can minimize the surface area of the bin. This problem is based on the fact that there is no fixed-sized bin in many real business scenarios and the cost of a bin is proportional to...

Deep reinforcement learning (DRL) has been widely adopted recently for its ability to solve decision-making problems that were previously out of reach due a combination nonlinear and high dimensionality. In the last few years, it spread in field air traffic control (ATC), particularly conflict resolution. this work, we conduct detailed review existing DRL applications resolution problems. This ...

This article proposes an end-to-end framework for solving multiobjective optimization problems (MOPs) using deep reinforcement learning (DRL), that we call DRL-based algorithm (DRL-MOA). The idea of decomposition is adopted to decompose the MOP into a set scalar subproblems. Then, each subproblem modeled as neural network. Model parameters all subproblems are optimized collaboratively according...

This paper presents a novel and effective deep reinforcement learning (DRL)-based approach to addressing joint resource management (JRM) in practical multi-carrier non-orthogonal multiple access (MC-NOMA) system, where hardware sensitivity imperfect successive interference cancellation (SIC) are considered. We first formulate the JRM problem maximize weighted-sum system throughput. Then, is dec...

OBJECTIVE Despite the obligatory recording of doses administered to patients during CT scans, this data is not easily accessible. The objective of this study was to implement and validate a computerised automated dose-recording system for CT scans, for a single radiology department. MATERIAL AND METHODS Every patient undergoing a CT scan in our department over a one-year period was included i...

The navigation problem is classically approached in two steps: an exploration step, where mapinformation about the environment is gathered; and an exploitation step, where this information is used to navigate efficiently. Deep reinforcement learning (DRL) algorithms, alternatively, approach the problem of navigation in an end-to-end fashion. Inspired by the classical approach, we ask whether DR...

Due to the scarcity in wireless spectrum and limited energy resources especially mobile applications, efficient resource allocation strategies are critical networks. Motivated by recent advances deep reinforcement learning (DRL), we address multi-agent DRL-based joint dynamic channel access power control a interference network. We first propose DRL algorithm with centralized training (DRL-CT) t...

In this letter, we investigate the hybrid beamforming based on deep reinforcement learning (DRL) for millimeter Wave (mmWave) multi-user (MU) multiple-input-single-output (MISO) system. A multi-agent DRL method is proposed to solve exploration efficiency problem in DRL. method, prioritized replay buffer and more informative reward are applied accelerate convergence. Simulation results show that...