A modern Bayesian look at the multi‐armed bandit

A multi‐armed bandit is an experiment with the goal of accumulating rewards from a payoff distribution with unknown parameters that are to be learned sequentially. This article describes a heuristic for managing multi‐armed bandits called randomized probability matching, which randomly allocates observations to arms according the Bayesian posterior probability that each arm is optimal. Advances in Bayesian computation have made randomized probability matching easy to apply to virtually any payoff distribution. This flexibility frees the experimenter to work with payoff distributions that correspond to certain classical experimental designs that have the potential to outperform methods that are ‘optimal’ in simpler contexts. I summarize the relationships between randomized probability matching and several related heuristics that have been used in the reinforcement learning literature. Copyright © 2010 John Wiley & Sons, Ltd.     

关于概率论学习障碍的分析与对策

对大学生学习概率论的障碍因素进行分析,得出影响概率论学习的障碍因素包含三方面:直观能力,概率思维品质,心理因素及情感,并分析了这几方面因素,给出克服这些障碍的相应对策,以期能从根本上改进传统教学方法,更新传统教学理念.     

基于可信性测度的模糊线性不等式组的确定性等价

在模糊优化决策问题中,约束条件包含模糊线性不等式组.如何把它们转化为确定性的等价形式,这在模糊控制和模糊决策中起着重要的作用.可信性测度是模糊数学实现公理化体系的一个基础.本文在可信性测度的基础上,探讨了模糊约束在一定的满意度水平之下转化为确定性的等价式,同时就三角形模糊变量给出了模糊线性不等式组的确定性等价的具体表达式.     

模糊化的Egoroff定理

在一般模糊测度空间上,针对可测模糊值函数序列给出了几乎处处收敛,几乎一致收敛和伪几乎一致收敛的概念,并在此基础上,进一步研究了这几种收敛的蕴涵关系,从而获得了模糊化的Egoroff定理,使模糊值函数序列的理论得到进一步丰富.     

DURATION OF NEGATIVE SURPLUS FOR A TWO STATE MARKOV-MODULATED RISK MODEL

We consider a continuous time risk model based on a two state Markov process, in which after an exponentially distributed time, the claim frequency changes to a different level and can change back again in the same way. We derive the Laplace transform for the first passage time to surplus zero from a given negative surplus and for the duration of negative surplus. Closed-form expressions are given in the case of exponential individual claim. Finally, numerical results are provided to show how to estimate the moments of duration of negative surplus.     

有随机投资回报的随机保费模型的渐近破产概率(英文)

本文研究了随机投资回报环境下扰动的随机保费模型的破产问题.利用鞅方法和随机分析的理论讨论了盈余过程的一些基本性质,得到了一个可以用来求解破产时刻的Laplace变换的积分微分方程,结果推广了已有的随机投资问报风险模型的结论.     

非倍测度条件下由Marcinkiewicz积分与RBMO函数生成的交换子在Herz空间中的有界性

本文研究了非倍测度条件下的一类由Marcinkiewica积分与RBMO函数生成交换子的有界性.通过Marcinkiewica积分及该交换子在Lebesgue空间中的有界性,得到了此交换子在Herz空间中的有界性.     

Synchronization of Takagi–Sugeno fuzzy stochastic discrete-time complex networks with mixed time-varying delays

In this paper, we propose and investigate a new general model of fuzzy stochastic discrete-time complex networks (SDCNs) described by Takagi–Sugeno (T–S) fuzzy model with discrete and distributed time-varying delays. The proposed model takes some well-studied models as special cases. By employing a new Lyapunov functional candidate, we utilize some stochastic analysis techniques and Kronecker product to deduce delay-dependent synchronization criteria that ensure the mean-square synchronization of the proposed T–S fuzzy SDCNs with mixed time-varying delays. These sufficient conditions are computationally efficient as it can be solved numerically by the LMI toolbox in Matlab. A numerical simulation example is provided to verify the effectiveness and the applicability of the proposed approach.     

Stochastic chance constrained mixed-integer nonlinear programming models and the solution approaches for refinery short-term crude oil scheduling problem

Stochastic chance constrained mixed-integer nonlinear programming (SCC-MINLP) models are developed in this paper to solve the refinery short-term crude oil scheduling problem which concerns crude oil unloading, mixing, transferring and multilevel inventory control under demands uncertainty of distillation units. The objective of these models is the minimum expected value of total operation cost. It is the first time that the uncertain demands of Crude oil Distillation Units (CDUs) in these problems are set as random variables which have discrete and continuous joint probability distributions. This situation is close to the real world industry use. To reduce the computation complexity, these SCC-MINLP models are transformed into their equivalent stochastic chance constrained mixed-integer linear programming models (SCC-MILP). Stochastic simulation and stochastic sampling technologies are introduced in detail to solve these complex SCC-MILP models. Finally, case studies are effectively solved with the proposed approaches.     

气体开关自击穿概率的分析方法比较

利用实测的多间隙气体开关自击穿电压,比较了高斯正态函数和威布尔函数在分析气体开关自击穿概率方面的异同。检验了自击穿电压的正态性和威布尔性,通过参数估计分别确定了自击穿电压的正态分布和威布尔分布函数。计算表明:两种概率分布得出的概率分析结果基本一致,在相同电压下放电概率差别一般不大于1%,最大为2%（当放电概率大于90%时）;在电压高于威布尔分布的阈值参数时,两种方法在相同概率下的放电电压计算结果差别不超过0.3%。