检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yao, Yifei He, Wentao Gu, Chenyu Du, Jiaheng Tan, Fuwei Zhu, Zhen Lu, Junguo All authors are with Machine Vision and Autonomous System Laboratory Department of Automation School of Electrical Information and Electronic Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework’s capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

The missing base molecules in atmospheric acid-base nucleation

引用

National Science Review 2022年第10期9卷 196-208页

作者： Runlong Cai Rujing Yin Chao Yan Dongsen Yang Chenjuan Deng Lubna Dada Juha Kangasluoma Jenni Kontkanen Roope Halonen Yan Ma Xiuhui Zhang Pauli Paasonen Tuukka Pet?j? Veli-Matti Kerminen Yongchun Liu Federico Bianchi Jun Zheng Lin Wang Jiming Hao James N.Smith Neil M. Donahue Markku Kulmala Douglas R.Worsnop Jingkun Jiang State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Institute for Atmospheric and Earth System Research/Physics Faculty of Science University of Helsinki Aerosol and Haze Laboratory Beijing Advanced Innovation Center for Soft Matter Science and Engineering Beijing University of Chemical Technology Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology Laboratory of Atmospheric Chemistry Paul Scherrer Institute Center for Joint Quantum Studies and Department of Physics School of Science Tianjin University Key Laboratory of Cluster Science Ministry of Education of China School of Chemistry and Chemical Engineering Beijing Institute of Technology Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention (LAP3) Department of Environmental Science and Engineering Fudan University Chemistry Department University of California Center for Atmospheric Particle Studies Carnegie Mellon University Department of Chemistry Carnegie Mellon University Aerodyne Research Inc.

Transformation of low-volatility gaseous precursors to new particles affects aerosol number concentration,cloud formation and hence the *** clustering of acid and base molecules is a major mechanism driving fast nucleation and initial growth of new particles in the ***,the acid-base cluster composition,measured using state-of-the-art mass spectrometers,cannot explain the measured high formation rate of new *** we present strong evidence for the existence of base molecules such as amines in the smallest atmospheric sulfuric acid clusters prior to their detection by mass *** demonstrate that forming（H2SO4）1（amine）1is the rate-limiting step in atmospheric H2SO4-amine nucleation and the uptake of（H2SO4）1（amine）1is a major pathway for the initial growth of *** proposed mechanism is very consistent with measured new particle formation in urban Beijing,in which dimethylamine is the key base for H2SO4nucleation while other bases such as ammonia may contribute to the growth of larger *** findings further underline the fact that strong amines,even at low concentrations and when undetected in the smallest clusters,can be crucial to particle formation in the planetary boundary layer.

关键词： new particle formation acid-base nucleation aerosol polluted urban environment

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Core Real- Time Scheduling Based on Reinforcement Learning

Adaptive Multi-Core Real- Time Scheduling Based on Reinforce...

引用

International Conference on control and Automation (ICCA)

作者： Yonghui Liang Hui Li Fei Shen Qimin Xu Shuna Hua Shanying Zhu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Re-search Center of Intelligent Control and Management Shanghai China Key Laboratory of Wireless Sensor Network and Communications Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China North Information Control Research Academy Group Company Ltd. Nanjing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

With the transformation towards industrial intel-ligence, multi-core processors are increasingly being applied in real-time networked control systems to ensure secure exe-cution of sensing, computing and actuating tasks under time constraints. However, existing scheduling methods result in either low CPU utilization or many missed task deadlines in dynamic systems. In this paper, we propose a two-layer scheduling architecture to address this issue by fully exploring the complex dependency between real-time tasks. To be specific, the local layer determines task execution priorities considering both dependency between tasks and deadline constraints by utilizing a reinforcement learning approach. Moreover, to better utilize the parallel capabilities of multi-core processors and reduce temporal collisions, this paper minimizes the requested core count for the task set based on a greedy strategy. The global layer designs a scheduling algorithm based on the pre-empt method and provides schedulability analysis of multiple task sets. Experimental results validate the correctness of the proposed scheduling approach, and efficiency is demonstrated through comparisons with baseline method.

关键词： Job shop scheduling Multicore processing Scheduling algorithms Networked control systems Reinforcement learning Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Distributed Generalized Nash Equilibria Learning for Online Stochastic Aggregative Games

arXiv

引用

arXiv 2025年

作者： Du, Kaixin Meng, Min Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China Department of Control Science and Engineering College of Electronics and Information Engineering National Key Laboratory of Autonomous Intelligent Unmanned System Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai Research Institute for Intelligent Autonomous Systems Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai China

This paper investigates online stochastic aggregative games subject to local set constraints and time-varying coupled inequality constraints, where each player possesses a time-varying expectation-valued cost function relying on not only its own decision variable but also an aggregation of all the players’ variables. Each player can only access its local individual cost function and constraints, necessitating partial information exchanges with neighboring players through time-varying unbalanced networks. Additionally, local cost functions and constraint functions are not prior knowledge and only revealed gradually. To learn generalized Nash equilibria of such games, a novel distributed online stochastic algorithm is devised based on push-sum and primal-dual strategies. Through rigorous analysis, high probability bounds on the regret and constraint violation are provided by appropriately selecting decreasing stepsizes. Moreover, for a time-invariant stochastic strongly monotone game, it is shown that the generated sequence by the designed algorithm converges to its variational generalized Nash equilibrium (GNE) almost surely, and the time-averaged sequence converges sublinearly with high probability. Finally, the derived theoretical results are illustrated by numerical simulations. Copyright © 2025, The Authors. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of the Impact of a 5 Day Interim Relaxation at 21 Days in 42 days Lockdown Strategy on COVID-19 Transmission in India

Mathematical Modeling of the Impact of a 5 Day Interim Relax...

引用

International Conference on Biosignals, Images and Instrumentation (ICBSII)

作者： Flavia Immaculyne BakiyaAmbikapathy Kamalanand Krishnamurthy Lourduraj De Britto Schlumberger- Reda Production System Benoi Cresent Singapore Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India Department of Instrumentation Engineering MIT Campus Anna University Chennai India Indian Council of Medical Research Vector Control Research Centre Puducherry India

ISBN: (数字)9798350350951

ISBN: (纸本)9798350350968

As of the first week of May 2020, the COVID-19 pandemic is present in 212 nations globally. Many countries have enforced lockdown measures strategically to slow down the epidemic's spread, with the objective of relieving pressure on healthcare systems. Mathematical modelling serves as a useful tool for the prediction of the future numbers of the infected population and for analyzing the effects of various intervention strategies. In this work, a mathematical model based on ordinary differential equations has been developed for analyzing the impact of an interim relaxation of 5 days at 21 days in a 42 days lockdown period. Results of the simulation demonstrate that the relaxation of 5 days during the 42 days lockdown does not result in any adverse effects if the transmission rate remains the same. However, the model-based analysis suggests that an increase in the transmission rate by a factor of 1.2 times during the relaxation period due to the possible aggregation of the susceptible with the infected, it could shift the growth pattern of infected cases from sub-exponential to exponential.

关键词： COVID-19 Analytical models Biological system modeling Sociology Predictive models Ordinary differential equations Routing

来源：评论

学校读者我要写书评

暂无评论

Correlation Analysis and Predictive Factors for Building a Mathematical Model 1

引用

7th Computational Methods in systems and Software, CoMeSySo 2023

作者： Nelyub, V.A. Tynchenko, V.S. Gantimurov, A.P. Degtyareva, K.V. Kukartseva, O.I. Artificial Intelligence Technology Scientific and Education Center Bauman Moscow State Technical University Moscow105005 Russia Peter the Great St. Petersburg Polytechnic University Saint Petersburg Russia Information-Control Systems Department Institute of Computer Science and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Technological Machines and Equipment of Oil and Gas Complex School of Petroleum and Natural Gas Engineering Siberian Federal University Krasnoyarsk660041 Russia Department of Information Economic System Institute of Engineering and Economics Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Systems Analysis and Operations Research Institute of Informatics and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia

ISBN: (数字)9783031535499

ISBN: (纸本)9783031535482

The study, published in the journal Nature Medicine, looked at data on 1,000 people from China who were tracked over an average period of six years. The participants were divided into two groups: those who lived in areas with high levels of air pollution and those who lived in areas with low levels of air pollution. The study analyzed data on patients with lung cancer, including their age, gender, exposure to air pollution, alcohol consumption, dust allergy, occupational hazards, genetic risk, chronic lung disease, balanced diet, obesity, smoking, passive smoking, chest pain, cough, hemoptysis, fatigue, weight loss, shortness of breath, wheezing, difficulty swallowing, nail thickening and snoring. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

Analysis of a Data Set to Determine the Dependence of Airline Passenger Satisfaction 7th

Analysis of a Data Set to Determine the Dependence of Airlin...

引用

7th Computational Methods in systems and Software, CoMeSySo 2023

作者： Tynchenko, V.S. Borodulin Kleshko, I.I. Nelyub, V.A. Rukosueva Artificial Intelligence Technology Scientific and Education Center Bauman Moscow State Technical University Moscow105005 Russia Peter the Great St. Petersburg Polytechnic University Saint Petersburg Russia Department of Information Economic System Institute of Engineering and Economics Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Systems Analysis and Operations Research Institute of Informatics and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Information-Control Systems Department Institute of Computer Science and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk660037 Russia Department of Technological Machines and Equipment of Oil and Gas Complex School of Petroleum and Natural Gas Engineering Siberian Federal University Krasnoyarsk660041 Russia

ISBN: (纸本)9783031535512

This paper presents an analysis of a data set to determine the factors influencing airline passenger satisfaction. The study examines various criteria such as gender, customer type, age, travel type, class, and range to assess their impact on passenger satisfaction. The dataset consists of 25 columns, including attributes like Wi-Fi availability, convenience of online booking, seat comfort, in-flight entertainment, baggage handling, and overall satisfaction. The sample is relatively balanced, with equal representation of men and women, predominantly repeat customers, and a majority flying for business purposes. Key findings include a strong correlation between departure and arrival delays, higher satisfaction among passengers in business class, and positive ratings for Wi-Fi service correlating with overall satisfaction. Correlation analysis reveals interdependencies between different attributes, such as the influence of cleanliness on seat comfort and food and beverage ratings. In addition, a neural network forecasting model is used to estimate the average ratings of passengers, although with low accuracy, which was later excluded. Finally, a decision tree algorithm is utilized to identify the most significant attributes affecting passenger satisfaction words. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Baggage handling

来源：评论

学校读者我要写书评

暂无评论

Virtual Inertia control Strategy for Photovoltaic Power Generation Based on Improved Incremental Conductance Method 7

Virtual Inertia Control Strategy for Photovoltaic Power Gene...

引用

7th Asia Conference on Power and Electrical engineering, ACPEE 2022

作者： Gao, Zhimin Cao, Yongji Zhang, Hengxu Qin, Hao Yang, Dong Ma, Huan Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Jinan China Technical University of Denmark Department of Electrical Engineering Kgs. Lyngby Denmark Institute State Grid Shandong Electric Power Company State Grid Shandong Electric Power Research Jinan China

ISBN: (纸本)9781665418195

The large-scale integration of renewable energy units such as wind and photovoltaic power has greatly reduced the equivalent rotational inertia of the power system. PV arrays are static generating elements and have no inertial response without additional control. In order to improve the stability of renewable energy grid operation, this paper proposes a virtual inertia control strategy for photovoltaic power generation by improving the incremental conductance method. This paper firstly introduces the working principle and model of the PV array, and then improves the incremental conductance method based on PI controller to propose PV power generation power reserve control strategy. The PV output is changed for inertial support based on droop control and virtual inertia control by detecting grid frequency changes. Simulation results show that this control strategy results in a better inertial response of the photovoltaic power system. © 2022 IEEE.

关键词： Power control

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of Frequency Dynamics in Real Power system 7

Quantitative Analysis of Frequency Dynamics in Real Power Sy...

引用

7th Asia Conference on Power and Electrical engineering, ACPEE 2022

作者： Qin, Hao Cao, Yongji Zhang, Hengxu Gao, Zhimin Yang, Dong Ma, Huan Shandong University Key Laboratory of Power System Intelligent Dispatch and Control of the Ministry of Education Jinan China Technical University of Denmark Department of Electrical Engineering Kgs. Lyngby Denmark State Grid Shandong Electric Power Company State Grid Shandong Electric Power Research Institute Jinan China

ISBN: (纸本)9781665418195

As the proportion of renewable energy sources increases, the randomness and volatility of the frequency increase, and its dynamic behaviors are becoming more complex. In order to clearly characterize the frequency fluctuation characteristics of the power system, the long-term statistical characteristics are analyzed based on the measured data. The bimodal normal distribution is used, and the measured frequency is decomposed into continuous and short-time-scale components using the moving average method. Based on historical data, the derivation law of the frequency fluctuation characteristics of regional power system is explored, and it is found that the frequency fluctuation characteristics of different regions continue to differentiate, and the characteristics of the sending-end power system frequency being higher than the rated frequency and relatively drastic fluctuations are becoming more and more obvious. © 2022 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Two-step Optimal Allocation of Stationary and Mobile Energy Storage systems in Resilient Distribution Networks

引用

Journal of Modern Power systems and Clean Energy 2021年第4期9卷 788-799页

作者： Xinyi Jiang Jian Chen Qiuwei Wu Wen Zhang Yicheng Zhang Jie Liu Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education Shandong UniversityJinan 250061China Center for Electric Power and Energy(CEE) Department of Electrical EngineeringTechnical University of Denmark(DTU)2800 Kongens LyngbyDenmark Institute for Infocomm Research(I2R) Agency for ScienceTechnology and Research(A*STAR)Singapore State Grid Yantai Power Supply Company YantaiChina

Energy storage systems (ESSs) are acknowledged to be a promising option to cope with issues in high penetration of renewable energy and guarantee a highly reliable power supply. In this paper, a two-step optimal allocation model is proposed to obtain the optimal allocation (location and size) of stationary ESSs (SESSs) and mobile ESSs (MESSs) in the resilient distribution networks (DNs). In the first step, a mixed-integer linear programming (MILP) problem is formulated to obtain the preselected location of ESSs with consideration of different scenarios under normal operation conditions. In the second step, a two-stage robust optimization model is established to get the optimal allocation results of ESSs under failure operation conditions which are solved by column-and-constraint generation (C&CG) algorithm. A hybrid ESS allocation strategy based on the subjective and objective weight analysis is proposed to give the final allocation scheme of SESSs and MESSs. Finally, the proposed two-step optimal allocation model is demonstrated on a modified IEEE 33-bus system to show its effectiveness and merits.

关键词： Resilient distribution network stationary energy storage system mobile energy storage system optimal allocation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：