基于强化学习的鱼群自组织行为模拟

自组织行为广泛存在于自然界中。为了通过学习的方式模拟鱼群自组织行为,构建了鱼群模拟环境模型、智能体模型和奖励机制,并提出了一种基于赫布迹和行动者-评价者框架的多智能体强化学习方法。该方法利用赫布迹加强游动策略的学习记忆能力,基于同构思想实现了多智能体的分布式学习。仿真结果表明,该方法能够适用于领航跟随、自主漫游、群体导航等场景中鱼群自组织行为学习,并且基于学习方法模拟的鱼群展现的行为特性与基于博德规则计算模拟的鱼群行为类似。     

Data-driven research in retail operations—A review

We review the operations research/management science literature on data-driven methods in retail operations. This line of work has grown rapidly in recent years, thanks to the availability of high-quality data, improvements in computing hardware, and parallel developments in machine learning methodologies. We survey state-of-the-art studies in three core aspects of retail operations—assortment optimization, order fulfillment, and inventory management. We then conclude the paper by pointing out some interesting future research possibilities for our community.     

基于深度森林的网络流量分类方法

随着网络应用的迅猛发展,流量分类在网络资源分配、流量调度和网络安全等诸多研究领域受到广泛关注。现有的机器学习流量分类方法对流量数据特征的选取和分布要求苛刻,导致在实际应用中的复杂流量场景下分类精确度和稳定度难以提高。为了解决样本特征属性的复杂性给分类性能带来的不利影响,引入了基于深度森林的流量分类方法。该算法通过级联森林和多粒度扫描机制,能够在样本数量规模和特征属性选取规模有限的情况下,有效地提高流量整体分类性能。通过网络流量公开数据集Moore对支持向量机、随机森林和深度森林机器学习算法进行训练和测试,结果表明基于深度森林的网络流量分类器的分类准确率能够达到96. 36%,性能优于其他机器学习模型。     

频谱感知次序的在线最优选择

动态频谱接入是解决无线电频谱资源短缺和频谱使用效率低下问题的有效方法,它允许次级用户在授权频谱空闲时动态地接入,以进行数据传输。而频谱感知是实现动态频谱接入的关键挑战之一。由于次级用户的感知能力有限,为了获得更多的频谱接入机会,需要尽快找到频谱空闲概率最大的频段,并研究频谱感知次序问题。考虑到频谱空闲概率对次级用户是不可知的,并且会随时间变化,提出了在线学习框架,把频谱感知次序问题归纳成经典多摇臂赌博机问题,并利用在线学习方法——满意折现汤普森抽样算法处理优化问题。仿真结果表明,和其他算法相比,所提算法可以获得更多的频谱接入机会并且能够跟踪频谱空闲概率的变化。     

基于强化学习的移动自组织网络分步路由算法*

移动自组织网络是一种无基础设施、由移动通信节点组成的无线网络,具有高度的动态特性。传统的路由协议并不能适应节点移动性带来的频繁拓扑变化,简单的洪泛路由也会因开销过大降低网络的性能。针对如何在移动自组织网络中自适应地进行路由选择,提出了一种基于强化学习的分步路由选择算法。该算法以最小链路总往返时延为目标,基于强化学习进行路由搜寻,在筛选出符合目标需求节点集合的基础上,结合置信度选择路由。在链路变得不可靠时,数据包被广播给筛选出的邻居节点集来提升路由可靠性并降低开销。对提出的算法在分组到达率和路由开销等主要性能指标进行数值仿真分析,仿真结果表明,提出的分步路由算法相比于基于强化学习的智能鲁棒路由,在降低开销的同时,保持着相当的吞吐率。     

建构主义教学论与教学模式改革

建构主义学习观强调学习的建构性、社会性和情境性 ,对促进教学方法的变革将有重要意义。文章运用建构教学观辨证分析了传统教学模式 ,综合现代以知识为中心、以学生为中心和行为主义理论等现代教育思想 ,分析了传授———建构教学法、合作、探究学习方法。     

A Bayesian analysis on the effect of multiple supply options in a quick response environment

In the apparel industry, vendors often suffer from high mismatches in supply and demand. To cope with this problem, they procure the same style product from different suppliers with different manufacturing costs. Especially in the quick response environment, which allows vendors to monitor trends in customer demand and search for available suppliers through the electronic market, they have additional opportunities to improve their decision‐making. In this paper, we propose an analytical profit maximization model and develop efficient decision tools to help both the middle and lower level managers pursuing this strategy. Furthermore, we have shown how significantly the vendors' potential competitive edge can be improved by exploiting multiple supply options, even at the expense of high premium procurement costs for late orders. The effect is critical, especially in a highly competitive market, and it has important implications for the top managers. © 2003 Wiley Periodicals, Inc. Naval Research Logistics, 2003     

公安现役部队干部培训之我见

受普通教育影响,公安现役部队干部教育培训模式有普教化现象。根据干部学习特点,研究适应其教育培训的方式方法,在实践中创造性地运用多种教学方式和手段,有利于提高干部培训的效益。     

高中数学研究性学习的实践与研究

在中学开设研究性学习课程,是基础教育课程改革的具体目标之一。针对现有课程体系的弊端,重知识传授而轻过程和技能训练,重学科知识体系而不关心社会实践活动。重间接经验的传授而忽视学生的直接体验积累。为培养学生乐于探究勤于动手的学习精神,分析和解决的能力,本人在几年的教学实践中,不断探究,积累了一些经验。本文就此问题谈谈高中数学研究性学习的实践与体会。     

What you should know about approximate dynamic programming

Approximate dynamic programming (ADP) is a broad umbrella for a modeling and algorithmic strategy for solving problems that are sometimes large and complex, and are usually (but not always) stochastic. It is most often presented as a method for overcoming the classic curse of dimensionality that is well‐known to plague the use of Bellman's equation. For many problems, there are actually up to three curses of dimensionality. But the richer message of approximate dynamic programming is learning what to learn, and how to learn it, to make better decisions over time. This article provides a brief review of approximate dynamic programming, without intending to be a complete tutorial. Instead, our goal is to provide a broader perspective of ADP and how it should be approached from the perspective of different problem classes. © 2009 Wiley Periodicals, Inc. Naval Research Logistics 2009