Computational design exploration of rocket nozzle using deep reinforcement learning by Aagashram Neelakandan, Arockia Selvakumar Arockia Doss, Natrayan Lakshmaiya

“…Additionally, the use of the Single-Step Proximal Policy Optimization (SSPPO) algorithm enhances the exploration of nozzle geometries by maximizing aerodynamic performance while balancing computational efficiency. …”
Get full text

MODELS OF STRATEGIC COMMUNICATION FOR ENSURING SOCIAL COHESION IN DE-OCCUPIED REGIONS by Tetiana Lushahina

“…It is proposed to consider strategic communication as a key instrument of state policy in the context of hybrid threats and post-conflict transformation. …”
Get full text

Volatility Spillover Between the Carbon Market and Traditional Energy Market Using the DGC-t-MSV Model by Jining Wang, Renjie Zeng, Lei Wang

“…This study employed the dynamic conditional correlation algorithm and incorporated the temporal dynamics of spillover effect to enhance the Multivariate Stochastic Volatility (MSV) model. …”
Get full text

Digital Intelligence Pathology Platform and Its Service Pattern by Xiaohong Chen, Liu Liu, Yajua Niu, Xiaoliang Liu, Xiaohai Li, Jianhua Zhou, Junpu Wang

“…Building on proprietary research achievements, we propose a tripartite middleware architecture comprising data, algorithm, and service platforms. The system architecture integrates standardized data management, AI-driven analytical modules, and interoperable service interfaces to optimize pathological workflows. …”
Get full text

LiDAR point cloud denoising for individual tree extraction based on the Noise4Denoise by Xiangfei Lu, Zongyu Ye, Liyong Fu, Huaiyi Wang, Kaiyu Wang, Yaquan Dou, Dongbo Xie, Xiaodi Zhao

Get full text

Enhanced Q learning and deep reinforcement learning for unmanned combat intelligence planning in adversarial environments by Xu Jianhong, Liang Gongqian

“…By integrating an attention mechanism and an adaptive reward mechanism, the algorithm effectively fuses image data, sensor data, and intelligent information, enabling collaborative multimodal data processing. …”
Get full text

Research on Ship Heave Motion Compensation Control Under Complex Sea State Environment Based on Improved Reinforcement Learning by ZHANG Qin, ZHOU Jingyi, WANG Xingyue, HU Xiong

“…Within this process, the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm assumes a central role as the core control strategy. …”
Get full text

Exploring the opportunities and challenges of using large language models to represent institutional agency in land system modelling by Y. Zeng, C. Brown, C. Brown, J. Raymond, M. Byari, R. Hotz, M. Rounsevell, M. Rounsevell, M. Rounsevell

“…The LLM agents provide simulated reasoning and policy action output. The agents' performance is benchmarked against two baseline scenarios: one without policy interventions and another implementing optimal policy actions determined through a genetic algorithm. …”
Get full text

A Hierarchical Reinforcement Learning Framework for Multi-Agent Cooperative Maneuver Interception in Dynamic Environments by Qinlong Huang, Yasong Luo, Zhong Liu, Jiawei Xia, Ming Chang, Jiaqi Li

“…At the low level, an improved prioritized experience replay multi-agent deep deterministic policy gradient algorithm (PER-MADDPG) is designed, integrating curriculum learning and prioritized experience replay mechanisms to effectively enhance the interception success rate against complex maneuvering targets. …”
Get full text

Online Self-Organizing Network Control with Time Averaged Weighted Throughput Objective by Zhicong Zhang, Shuai Li, Xiaohui Yan

“…To maximize the mean time averaged weighted throughput of the jobs through the network, we propose a reinforcement learning algorithm with time averaged reward to deal with the control decision model and obtain a control policy integrating the jobs routing selection strategy and the jobs sequencing strategy. …”
Get full text

UAV spatiotemporal crowdsourcing resource allocation based on deep reinforcement learning by Yaxi LIU, Xulong LI, Jiahao HUO, Wei HUANGFU

“…Our results show that the SAC algorithm achieves faster convergence speed and better solutions than existing state-of-the-art methods, such as the twin delayed deep deterministic policy gradient (TD3) and the deep deterministic policy gradient (DDPG) algorithms. …”
Get full text

Demand-Adapting Charging Strategy for Battery-Swapping Stations by Benjamín Pla, Pau Bares, Andre Aronis, Augusto Perin

“…Battery tests were conducted to assess charging time variability, and traffic density measurements were collected in the city of Valencia across multiple days to provide a realistic scenario, while real-time data of the electricity cost is integrated into the control proposal. The results show that incorporating traffic and electricity price forecasts into the control algorithm can reduce electricity costs by up to 11% and decrease associated <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>CO</mi><mn>2</mn></msub></semantics></math></inline-formula> emissions by more than 26%.…”
Get full text

Machine learning-based detection of medical service anomalies: Kazakhstan’s health insurance data by Maksut Kulzhanov, Alexander Wagner, Abylkair Skakov, Iliyas Mukhamejan, Saya Zhorabek, Ainur B. Qumar

Get full text

Deep reinforcement learning enhanced PID control for hydraulic servo systems in injection molding machines by Xiaoxi Hao, Zengmiao Xin, Weizhuo Huang, Sicheng Wan, Guangfan Qiu, Tianlei Wang, Zhu Wang

“…In particular, this work innovatively integrates the DDPG algorithm with an auxiliary servo valve structure for PID parameter optimization and dynamic performance enhancement, offering new ideas and technical pathways for adaptive control of complex hydraulic systems.…”
Get full text

Optimal Power Flow for High Spatial and Temporal Resolution Power Systems with High Renewable Energy Penetration Using Multi-Agent Deep Reinforcement Learning by Liangcai Zhou, Long Huo, Linlin Liu, Hao Xu, Rui Chen, Xin Chen

“…A heterogeneous multi-agent proximal policy optimization (H-MAPPO) DRL algorithm is introduced for multi-area power systems. …”
Get full text

A predictive framework using advanced machine learning approaches for measuring and analyzing the impact of synthetic agrochemicals on human health by Sahezpreet Singh, Puneet Kaur, Inderdeep Kaur, Gurpreet Singh, Satinder Kaur, Parminder Kaur

“…Although, the incorporation of machine learning algorithms for accurate risk evaluation and predictive modeling still underexplored, requiring novel solutions. …”
Get full text

What patients and caregivers want to know when consenting to the use of digital behavioral markers by Anika Sonig, Christine Deeney, Meghan E. Hurley, Eric A. Storch, John Herrington, Gabriel Lázaro-Muñoz, Casey J. Zampella, Birkan Tunc, Julia Parish-Morris, Jenny Blumenthal-Barby, Kristin Kostick-Quenet

Get full text

Research on malicious code variants detection based on texture fingerprint by Xiao-guang HAN, UWu Q, AOXuan-xia Y, UOChang-you G, Fang ZHOU

“…In the detection phase, according to the generation policy for malicious code texture fingerprint, the prototype system for texture fingerprint extraction and detection is con-structed by employing the integrated weight method to multi-segmented texture fingerprint similarity matching to de-tect variants and unknown malicious codes. …”
Get full text

Real-time torque distribution simulation of parallel hybrid vehicle engine by Jing Wang

“…This study aims to develop a high-precision, robust torque distribution model to enhance energy utilization while addressing interference from environmental noise and extreme temperatures.MethodsA real-time torque distribution model integrates three core components: a Markov Decision Process framework transforms torque allocation into a mathematical optimization problem; the Proximal Policy Optimization algorithm enhanced with Prioritized Experience Replay dynamically generates control strategies; and Fiber Bragg Grating sensors achieve millisecond-level torque measurement by correlating shaft strain forces with wavelength shifts. …”
Get full text

Multi-Objective-Based Multi-Heterogeneous- Agent Deep Reinforcement Learning for Minimization of Voltage Deviation and Operation Cost in Active Distribution System by Anurak Deanseekeaw, Watcharakorn Pinthurat, Boonruang Marungsri

“…The proposed framework employs a multi-objective optimization approach, integrating three advanced algorithms: multi-agent proximal policy optimization (MAPPO), multi-agent asynchronous actor-critic (MAA2C), and multi-agent twin delayed deep deterministic policy gradient (MATD3). …”
Get full text