检索结果-南通市图书馆

Ensemble successor representations for task generalization in offline-to-online reinforcement learning

Science China(Information Sciences) 2024年第7期67卷 240-255页

作者： Changhong WANG Xudong YU Chenjia BAI Qiaosheng zhang zhen WANG Space Control and Inertial Technology Research Center Harbin Institute of Technology Shanghai Artificial Intelligence Laboratory Shenzhen Research Institute of Northwestern Polytechnical University School of Cybersecurity Northwestern Polytechnical University

In reinforcement learning(RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline policy, which can be refined through online interactions. However, existing approaches primarily perform offline and online learning in the same task, without considering the task generalization problem in offline-to-online adaptation. In real-world applications, it is common that we only have an offline dataset from a specific task while aiming for fast online-adaptation for several tasks. To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning. We demonstrate that the conventional paradigm using successor features cannot effectively utilize offline data and improve the performance for the new task by online fine-tuning. To mitigate this, we introduce a novel methodology that leverages offline data to acquire an ensemble of successor representations and subsequently constructs ensemble Q functions. This approach enables robust representation learning from datasets with different coverage and facilitates fast adaption of Q functions towards new tasks during the online fine-tuning *** empirical evaluations provide compelling evidence showcasing the superior performance of our method in generalizing to diverse or even unseen tasks.

关键词： offline reinforcement learning online fine-tuning task generalization successor representations ensembles

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Musculoskeletal ultrasound to evaluate the efficacy of acupuncture: a review

引用

Journal of Traditional Chinese Medicine 2024年第3期44卷 629-632页

作者： WANG Dingyue YU Yana WANG Yiyuan zhang zhen Department of Ultrasound the First Affiliated Hospital of China Medical UniversityShenyang 110001China

Acupuncture is a typical example of Traditional Chinese Medicine and has been used in China for hundreds of years to treat a wide range of illnesses. However, in the clinic, issues and deficiencies were primarily seen in four areas: loss of accuracy in the operation process;difficulty understanding the depth of acupuncture;difficulty using reinforcing and reducing techniques;and lack of a clear dynamic effect of acupuncture points following acupuncture. Musculoskeletal ultrasonography may quantitatively evaluate the acupuncture location and display the distribution of small nerves near and within the fascia of the acupuncture point in real time. The subjects were asked how they felt about receiving Qi when the needle body reached different depths and different tissues. The Qi obtained from an acupuncture point and the connective tissue of the fascia can be further understood by combining the physiological response of the acupuncture point with the anatomical structure,which offers a new method for defining the nature of the acupuncture point and standardizing the acupuncture point.

关键词： musculoskeletal ultrasound acupuncture De Qi dynamic effect visualization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Finite-Time Convergent Analysis of Continuous Action Iterated Dilemma

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 563-565页

作者： zhen Wang Xiaoyue Jin Tao zhang Dengxiu Yu Northwestern Polytechnical University

Dear Editor,In this letter, a finite-time convergent analysis of continuous action iterated dilemma(CAID) is proposed. In traditional evolutionary game theory, the strategy of the player is binary(cooperation or defec... 详细信息

关键词： lemma letter convergent

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Experimental study on the effect of flexible joints of a deep-buried tunnel across an active fault under high in-situ stress conditions

引用

Underground Space 2024年第6期19卷 189-207页

作者： Jiawei zhang zhen Cui Qian Sheng Wanhua Zhao Liang Song State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil MechanicsChinese Academy of SciencesWuhan 430071China School of Civil Engineering and Architecture Wuhan Polytechnic UniversityWuhan 430023China

During dislocation,a tunnel crossing the active fault will be damaged to varying degrees due to its permanent stratum *** previous studies did not consider the influence of the tunnel’s deep burial and the high in-situ stress,so the results were not entirely *** this paper,the necessity of solving the anti-dislocation problem of deep-buried tunnels is systemically *** the model test of tunnels across active faults,the differences in failures between deep-buried tunnels and shallow-buried tunnels were compared,and the dislocation test of deep-buried segmental tunnels was carried out to analyze the external stress change,lining strain,and failure mode of *** results are as follows.(1)The overall deformation of deep-buried and shallow-buried tunnels is both *** failure mode of deep-buried tunnels is primarily characterized by shear and tensile failure,resulting in significant compressive deformation and a larger damaged *** contrast,shallow-buried tunnels mainly experience shear failure,with the tunnel being sheared apart at the fault crossing,leading to more severe damage.(2)After the segmental structure design of the deep-buried tunnel,the‘‘S”deformation pattern is transformed into a‘‘ladder”pattern,and the strain of the tunnel and the peak stress of the external rock mass are reduced;therefore,damages are significantly mitigated.(3)Through the analysis of the distribution of cracks in the tunnel lining,it is found that the tunnel without a segmental structure design has suffered from penetrating failure and that cracks affect the entire *** cracks in a flexible segmental tunnel affect about 66.6%of the entire length of the tunnel,and cracks in a tunnel with a short segmental tunnel only affect about 33.3%of the entire length of the ***,a deep-buried tunnel with a short segmental tunnel can yield a better anti-dislocation effect.(4)By comparing the shallow-buried segmental tunnel in previous

关键词： Tunnel project Crossing active fault High in-situ stress Segmental structure design Flexible joint

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

ControlService: a containerized solution for control-algorithm-as-a-service in cloud control systems

引用

Science China(Information Sciences) 2024年第8期67卷 172-189页

作者： Chenggang SHAN Runze GAO zhen YANG Wei zhang Yuanqing XIA School of Artificial Intelligence Zaozhuang University School of Automation Beijing Institute of Technology

As an extension of networked control systems, cloud control systems(CCSs) have emerged as a new control paradigm to improve the service quality of emerging control missions, such as data-driven modeling and automated vehicles. Existing studies have used the workflow-based restructured method to optimize the computation-intensive algorithms in the CCSs. However, the challenges here are how to define and submit these algorithms' workflows as cloud services and execute these algorithms' workflows in a containerized manner. Based on these challenges, we propose a containerized solution for the control-algorithm-as-a-service(C3aS) in the CCSs, namely Control Service. It offers the control algorithm as a cloud workflow service and uses a customized workflow engine to realize the containerized execution. First, we employ a cloud workflow representation method to define a control algorithm into an abstract cloud workflow form. Afterward, we provide a cloud service representation of the abstract cloud workflow. Next, we design a workflow engine and submit the cloud service to this workflow engine to implement containerized execution of this cloud service in the CCSs. In the experiment, we discuss the cloud service form and containerized implementation of the subspace identification method. Experimental results show that the proposed Control Service has significant performance advantages in computational time, reduction percentage, and speedup ratio compared with the baseline method.

关键词： cloud control systems control-algorithm-as-a-service containerization workflow engine cloud workflow service subspace identification

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

SPNS1 ablation drives skeletal muscle atrophy by disrupting mitophagy,mitochondrial function,and apoptosis in mice

引用

Genes & Diseases 2024年第5期11卷 25-28页

作者： Xianzhong zhang Fengmin zhang Haofan Wu zhen Yu Chengle Zhuang Department of Gastrointestinal Surgery Shanghai Tenth People's HospitalSchool of MedicineTongji UniversityShanghai200092China Colorectal Cancer Center Shanghai Tenth People's HospitalSchool of MedicineTongji UniversityShanghai 200072China

Sarcopenia is characterized by a dramatic decline in muscle mass and function during aging,which of ten leads to reduced mobility,diminished quality of life,and shortened *** recent advances in sarcopenia,the mechanisms that mediate skeletal muscle dysfunction remain unclear.1 Lysosomal plays a vital role in digesting and recycling macromolecules,and several studies have shown that lysosomal acidification and autophagy decrease with age,which may impair the clearance of damaged mitochondria.

关键词： skeletal function spite

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Ni-catalyzed highly regio- and stereo-selective diborylative cyclization of 1,6-enynes with diboron reagent

引用

Science China Chemistry 2024年第3期67卷 981-989页

作者： Qitao Guan zhen Shen Yiqiang Tian Genping Huang Chun zhang Institute of Molecular Plus Tianjin Key Laboratory of Molecular Optoelectronic ScienceDepartment of ChemistrySchool of SciencesTianjin UniversityTianjin 300072China State Key Laboratory of Elemento-Organic Chemistry Nankai UniversityTianjin 300071China

The Ni-catalyzed highly selective diborylative cyclization of 1,6-enynes with diboron reagent has been developed. When pinB-Bdan was used, multiple types of boron-containing functional groups could be installed into organic molecule with great chemoselectivity and regioselectivity though this reaction. Meanwhile, if B_2pai_2 was employed, the asymmetric diborylative cyclization could be well induced by using strategy of dynamic kinetic resolution. Importantly, the above reactions could afford desired product with 100% atomic economy, and could be compatible with different series of substituents. The studies of further transformation well illustrated that different type products could serve diverse synthetic strategy. Notably, the reaction mechanism was intensively studied by density functional theory(DFT) calculations, which could reveal the mechanism of regio- and enantio-selective control.

关键词： nickel-catalyzed organoboron cyclization regioselectivity enantioselectivity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Doped low-density parity-check codes

引用

Digital Communications and Networks 2024年第1期10卷 217-226页

作者： yong Li Rui Liu Xianlong Jiao Youqiang Hu zhen Luo Francis C.M.Lau College of Computer Science Chongqing UniversityChongqing400044China School of Automation Chongqing UniversityChongqing400044China College of Electronic and Information Engineering Southwest UniversityChongqing400715China Future Wireless Networks and IoT Focusing Area Department of Electronic and Information EngineeringHong Kong Polytechnic UniversityHong KongChina

In this paper,we propose a doping approach to lower the error floor of Low-Density Parity-Check(LDPC)*** doping component is a short block code in which the information bits are selected from the coded bits of the dominant trapping sets of the LDPC ***,an algorithm for selecting the information bits of the short code is proposed,and a specific two-stage decoding algorithm is *** results demonstrate that the proposed doped LDPC code achieves up to 2.0 dB gain compared with the original LDPC code at a frame error rate of 10^(-6)Furthermore,the proposed design can lower the error floor of original LDPC Codes.

关键词： LDPC codes Doped LDPC codes Tanner graph Quadratic residue codes Trapping sets

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A High-Accuracy Curve Boundary Recognition Method Based on the Lattice Boltzmann Method and Immersed Moving Boundary Method

引用

Computer Modeling in Engineering & Sciences 2024年第9期140卷 2533-2557页

作者： Jie-Di Weng yong-zheng Jiang Long-Chao Chen Xu zhang Guan-yong zhang Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment Hunan University of Science and TechnologyXiangtan411201China School of Mechanical Engineering Hunan Chemical Vocational Technology CollegeZhuzhou412000China

Applying numerical simulation technology to investigate fluid-solid interaction involving complex curved bound-aries is vital in aircraft design,ocean,and construction ***,current methods such as Lattice Boltzmann(LBM)and the immersion boundary method based on solid ratio(IMB)have limitations in identifying custom curved ***,IBM based on velocity correction(IBM-VC)suffers from inaccuracies and numerical ***,this study introduces a high-accuracy curve boundary recognition method(IMB-CB),which identifies boundary nodes by moving the search box,and corrects the weighting function in LBM by calculating the solid ratio of the boundary nodes,achieving accurate recognition of custom curve *** addition,curve boundary image and dot methods are utilized to verify *** findings revealed that IMB-CB can accurately identify the boundary,showing an error of less than 1.8%with 500 ***,the flow in the custom curve boundary and aerodynamic characteristics of the NACA0012 airfoil are calculated and compared to *** showed that IMB-CB yields lower lift and drag coefficient errors than IBM-VC,with a 1.45%drag coefficient *** addition,the characteristic curve of IMB-CB is very stable,whereas that of IBM-VC is *** the moving boundary problem,LBM-IMB-CB with discrete element method(DEM)is capable of accurately simulating the physical phenomena of multi-moving particle flow in complex curved *** research proposes a new curve boundary recognition method,which can significantly promote the stability and accuracy of fluid-solid interaction simulations and thus has huge applications in engineering.

关键词： Fluid-solid interaction curve boundary recognition method Lattice Boltzmann method immersed moving boundary method

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Oxidation behavior of low-grade vanadiferous titanomagnetite concentrate with high titanium

引用

Journal of Iron and Steel Research International 2024年第2期31卷 329-341页

作者： Jin-sheng Liu zhen-xing Xing Gong-jin Cheng Xue-yong Ding Xiang-xin Xue School of Metallurgy Northeastern UniversityShenyang110819LiaoningChina Liaoning Key Laboratory of Recycling Science for Metallurgical Resources Shenyang110819LiaoningChina Innovation Research Institute of Vanadium and Titanium Resource Industry Technology Northeastern UniversityShenyang110819LiaoningChina

In order to clarify the oxidation mechanisms and make better use of the low-grade vanadiferous titanomagnetite concentrate with high titanium(LVTC),the oxidation behavior of LVTC was *** results showed that oxidation degree was achieved within 90 min when temperature was not lower than 700°C,and the main phases of the oxidized LVTC consisted of Fe9TiO15,Fe2O3,CaSiTiO5 and a small amount of *** temperature is favorable to the formation of *** surface of LVTC gradually becomes rough,with fine particles of needle-like and granular shape appearing on the surface,which finally turn from laminar to creamy,spread out,and are interspersed with many tiny *** phase oxidation paths in LVTC were as follows:(1)Fe2.75Ti0.25O4→Fe9TiO15+Fe2O3;(2)Fe2.75Ti0.25O4→Fe2O3+FeTiO3→Fe2TiO5;(3)FeTiO3→Fe2O3+Fe2Ti3O9→*** is predominantly mesoporous whether oxidized or not,with the pores mainly distributed in the range of 2–40 nm,and the specific surface area of LVTC decreases significantly with increasing temperature.

关键词： Low-grade vanadiferous titanomagnetite concentrate Oxidation degree Phase transformation Micromorphology Oxidation path Pore structure

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：