检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4984-4995页

作者： Sun, Shaoqi Xu, Kele Feng, Dawei Ding, Bo National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410003 China

In recent years, multiagent reinforcement learning (MARL) has demonstrated considerable potential across diverse applications. However, in reinforcement learning environments characterized by sparse rewards, the scarcity of reward signals may give rise to reward conflicts among agents. In these scenarios, each agent tends to compete to obtain limited rewards, deviating from collaborative efforts aimed at achieving collective team objectives. This not only amplifies the learning challenge but also imposes constraints on the overall learning performance of agents, ultimately compromising the attainment of team goals. To mitigate the conflicting competition for rewards among agents in MARL, we introduce the bidirectional influence and interaction (BDII) MARL framework. This innovative approach draws inspiration from the collaborative ethos observed in human social cooperation, specifically the concept of "sharing joys and sorrows." The fundamental concept behind BDII is to empower agents to share their individual rewards with collaborators, fostering a cooperative rather than competitive behavioral paradigm. This strategic shift aims to resolve the pervasive issue of reward conflicts among agents operating in sparse-reward environments. BDII incorporates two key factors—namely, the Gaussian kernel distance between agents (physical distance) and policy diversity among agents (logical distance). The two factor collectively contribute to the dynamic adjustment of reward allocation coefficients, culminating in the formation of reward distribution weights. The incorporation of these weights facilitates the equitable sharing of agents’ contributions to rewards, promoting a cooperative learning environment. Through extensive experimental evaluations, we substantiate the efficacy of BDII in addressing the challenge of reward conflicts in MARL. Our research findings affirm that BDII significantly mitigates reward conflicts, ensuring that agents consistently align with the origi

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Auxo: an architecture-centric framework supporting the online tuning of software adaptivity

引用

Science China(Information Sciences) 2015年第9期58卷 31-45页

作者： WANG HuaiMin DING Bo SHI DianXi CAO JianNong Alvin T.S.Chan National Key Laboratory of Parallel and Distributed Processing College of ComputerNational University of Defense Technology Department of Computing Hong Kong Polytechnic University

Adaptivity is the capacity of software to adjust itself to changes in its environment. A common approach to achieving adaptivity is to introduce dedicated code during software development stage. However,since those code fragments are designed a priori, self-adaptive software cannot handle situations adequately when the contextual changes go beyond those that are originally anticipated. In this case, the original builtin adaptivity should be tuned. For example, new code should be added to provide the capacity to sense the unexpected environment or to replace outdated adaptation decision logic. The technical challenges in this process, especially that of tuning software adaptivity at runtime, cannot be understated. In this paper,we propose an architecture-centric application framework for self-adaptive software named Auxo. Similar to existing work, our framework supports the development and running of self-adaptive software. Furthermore,our framework supports the tuning of software adaptivity without requiring the running self-adaptive software to be terminated. In short, the architecture style that we are introducing can encapsulate not only general functional logic but also the concerns in the self-adaptation loop(such as sensing, decision, and execution)as architecture elements. As a result, a third party, potentially the operator or an augmented software entity equipped with explicit domain knowledge, is able to dynamically and flexibly adjust the self-adaptation concerns through modifying the runtime software architecture. To truly exercise, validate, and evaluate our approach,we describe a self-adaptive application that was deployed on the framework, and conducted several experiments involving self-adaptation and the online tuning of software adaptivity.

关键词： software architecture self-adaptive software architecture style application framework software adaptation

来源：评论

学校读者我要写书评

暂无评论

Jammer Localization for Wireless Sensor Networks

引用

电子学报(英文版) 2011年第4期20卷 735-738页

作者： SUN Yanqiang WANG Xiaodong ZHOU Xingming National Key Laboratory for Parallel and Distributed Processing College of Computer Science National University of Defense Technology Changsha China

Jamming attack can severely affect the performance of Wireless sensor networks (WSNs) due to the broadcast nature of wireless medium. In order to localize the source of the attacker, we in this paper propose a jammer localization algorithm named as Minimum-circlecovering based localization (MCCL). Comparing with the existing solutions that rely on the wireless propagation parameters, MCCL only depends on the location information of sensor nodes at the border of the jammed region. MCCL uses the plane geometry knowledge, especially the minimum circle covering technique, to form an approximate jammed region, and hence the center of the jammed region is treated as the estimated position of the jammer. Simulation results showed that MCCL is able to achieve higher accuracy than other existing solutions in terms of jammer's transmission range and sensitivity to nodes' density.

关键词：无线传感器网络干扰定位传感器节点位置信息覆盖技术定位算法无线传播几何知识

来源：评论

学校读者我要写书评

暂无评论

Slicing hierarchical automata for model checking UML statecharts 4th

Slicing hierarchical automata for model checking UML statech...

引用

4th International Conference on Formal Engineering Methods, ICFEM 2002

作者： Ji, Wang Wei, Dong Qi, Zhi-Chang National Laboratory for Parallel and Distributed Processing China

ISBN: (纸本)9783540000297

Hierarchical Automata has been widely used in modeling dynamic aspects of reactive software, such as in UML Statecharts. At the same time, model checking is an automatic technique to ensure the correctness of software models, where state space explosion is the main obstacle to applying this technique in large scale applications. The paper presents a method for slicing hierarchical automata with respect to properties to be verified. The considered formalism is Extended Hierarchical Automata (EHA), in which a set of dependence relations is specified after analyzing characteristics such as hierarchy, concurrency and synchronization. We present the algorithm of slicing EHA based on the slicing criterion in terms of states and transitions. The algorithm can remove the hierarchies and concurrent states which are irrelevant to the property, and reduce the state space efficiently in model checking UML Statecharts. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Fast garment simulation with aid of hybrid bones

引用

Journal of Central South University 2015年第6期22卷 2218-2226页

作者：吴博陈寅徐凯程志全熊岳山 College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory (National University of Defense Technology) Avatar Science Company

A data-driven method was proposed to realistically animate garments on human poses in reduced space. Firstly, a gradient based method was extended to generate motion sequences and garments were simulated on the sequences as our training data. Based on the examples, the proposed method can fast output realistic garments on new poses. Our framework can be mainly divided into offline phase and online phase. During the offline phase, based on linear blend skinning(LBS), rigid bones and flex bones were estimated for human bodies and garments, respectively. Then, rigid bone weight maps on garment vertices were learned from examples. In the online phase, new human poses were treated as input to estimate rigid bone transformations. Then, both rigid bones and flex bones were used to drive garments to fit the new poses. Finally, a novel formulation was also proposed to efficiently deal with garment-body penetration. Experiments manifest that our method is fast and accurate. The intersection artifacts are fast removed and final garment results are quite realistic.

关键词： data-driven linear blend skinning hybrid bones interactive

来源：评论

学校读者我要写书评

暂无评论

Mechanism of floating body effect mitigation via cutting off source injection in a fully-depleted silicon-on-insulator technology

引用

Chinese Physics B 2016年第3期25卷 283-289页

作者：黄鹏程陈书明陈建军 College of Computer National University of Defense Technology Changsha 410073 China National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

In this paper, the effect of floating body effect （FBE） on a single event transient generation mechanism in fully depleted （FD） silicon-on-insulator （SOI） technology is investigated using three-dimensional technology computer-aided design （3D- TCAD） numerical simulation. The results indicate that the main SET generation mechanism is not carder drift/diffusion but floating body effect （FBE） whether for positive or negative channel metal oxide semiconductor （PMOS or NMOS）. Two stacking layout designs mitigating FBE are investigated as well, and the results indicate that the in-line stacking （IS） layout can mitigate FBE completely and is area penalty saving compared with the conventional stacking layout.

关键词： floating body effect in-line stacking silicon-on-insulator source injection

来源：评论

学校读者我要写书评

暂无评论

Superscalar communication: A runtime optimization for distributed applications

引用

Science China(Information Sciences) 2010年第10期53卷 1931-1946页

作者： LI HuiBa , LIU ShengYun, PENG YuXing, LI DongSheng, ZHOU HangJun & LU XiCheng national laboratory for parallel and distributed processing, national University of Defense Technology, Changsha 410073, China 1. National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

Building distributed applications is difficult mostly because of concurrency management. Existing approaches primarily include events and threads. Researchers and developers have been debating for decades to prove which is superior. Although the conclusion is far from obvious, this long debate clearly shows that neither of them is perfect. One of the problems is that they are both complex and error-prone. Both events and threads need the programmers to explicitly manage concurrencies, and we believe it is just the source of difficulties. In this paper, we propose a novel approach—superscalar communication, in which concurrencies are automatically managed by the runtime system. It dynamically analyzes the programs to discover potential concurrency opportunities; and it dynamically schedules the communication and the computation tasks, resulting in automatic concurrent execution. This approach is inspired by the idea of superscalar technology in modern microprocessors, which dynamically exploits instruction-level parallelism. However, hardware superscalar algorithms do not fit software in many aspects, thus we have to design a new scheme completely from scratch. Superscalar communication is a runtime extension with no modification to the language, compiler or byte code, so it is good at backward compatibility. Superscalar communication is likely to begin a brand new research area in systems software, which is characterized by dynamic optimization for networking programs.

关键词： network programming concurrency event thread superscalar

来源：评论

学校读者我要写书评

暂无评论

Simulation analysis of heavy-ion-induced single-event response for nanoscale bulk-Si FinFETs and conventional planar devices

引用

Science China(Technological Sciences) 2017年第3期60卷 459-466页

作者： YU JunTing CHEN ShuMing CHEN JianJun HUANG PengCheng College of Computer National University of Defense Technology Changsha 410073 China National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

FinFET technologies are becoming the mainstream process as technology scales *** on 28-nm bulk-Si FinFETs and

关键词： charge collection bipolar amplification reversed bipolar effect single-event effect(SEE) single-event transient(SET) FinFET planar device

来源：评论

学校读者我要写书评

暂无评论

MPtostream:an OpenMP compiler for CPU-GPU heterogeneous parallel systems

引用

Science China(Information Sciences) 2012年第9期55卷 1961-1971页

作者： YANG XueJun,TANG Tao ,WANG GuiBin,JIA Jia & XU XinHai national laboratory for parallel and distributed processing,national University of Defense Technology,Changsha 410073,China 1. National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

In light of GPUs’ powerful floating-point operation capacity,heterogeneous parallel systems incorporating general purpose CPUs and GPUs have become a highlight in the research field of high performance computing(HPC).However,due to the complexity of programming on GPUs,porting a large number of existing scientific computing applications to the heterogeneous parallel systems remains a big *** OpenMP programming interface is widely adopted on multi-core CPUs in the field of scientific *** effectively inherit existing OpenMP applications and reduce the transplant cost,we extend OpenMP with a group of compiler directives,which explicitly divide tasks among the CPU and the GPU,and map time-consuming computing fragments to run on the GPU,thus dramatically simplifying the *** have designed and implemented MPtoStream,a compiler of the extended OpenMP for AMD’s stream processing *** experimental results show that programming with the extended directives deviates from programming with OpenMP by less than 11% modification and achieves significant speedup ranging from 3.1 to 17.3 on a heterogeneous system,incorporating an Intel Xeon E5405 CPU and an AMD FireStream 9250 GPU,over the execution on the Xeon CPU alone.

关键词： GPGPU stream OpenMP compiler

来源：评论

学校读者我要写书评

暂无评论

Speeding up the MATLAB complex networks package using graphic processors

引用

Chinese Physics B 2011年第9期20卷 460-467页

作者：张百达唐玉华吴俊杰李鑫 National laboratory for Parallel and Distributed Processing School of ComputerNational University of Defense Technology Department of Computer Science and Technology School of ComputerNational University of Defense Technology

The availability of computers and communication networks allows us to gather and analyse data on a far larger scale than previously. At present, it is believed that statistics is a suitable method to analyse networks with millions, or more, of vertices. The MATLAB language, with its mass of statistical functions, is a good choice to rapidly realize an algorithm prototype of complex networks. The performance of the MATLAB codes can be further improved by using graphic processor units （GPU）. This paper presents the strategies and performance of the GPU implementation of a complex networks package, and the Jacket toolbox of MATLAB is used. Compared with some commercially available CPU implementations, GPU can achieve a speedup of, on average, 11.3x. The experimental result proves that the GPU platform combined with the MATLAB language is a good combination for complex network research.

关键词： complex networks graphic processors unit MATLAB Jacket Toolbox

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：