多人非合作随机自适应博弈（英文）

本文考虑系数未知的离散时间线性随机系统多人非合作的自适应博弈问题,每个参与者运用最小二乘算法和"必然等价原则"来设计博弈策略组合,目的是自适应优化自身的一步超前收益函数.本文证明此自适应策略组合使得闭环系统全局稳定,并且在一定意义下是该博弈问题的渐近纳什均衡解.     

一种可信的自适应服务组合机制

提出一种可信的自适应服务组合机制.首先,将组合服务的可信性保证问题转换为自适应控制问题,可信性保证策略作为可调节控制器,组合服务作为被控对象,并设计了相应的系统结构;其次,在马尔可夫决策过程框架下建模和优化组合服务的可信维护过程和策略,并设计了相应的算法,实现了基于强化学习的直接自适应控制机制;最后,通过仿真实验,将组合服务的自适应维护与随机维护策略比较,表明组合服务的自适应维护具有明显的优越性.     

面向环境自适应组合服务系统的环境变化识别

环境自适应的组合服务系统是未来软件系统的一个发展方向,不同于普通组合服务系统之处在于这种系统对系统运行的网络环境进行监测,并根据监测结果对组合服务进行合适的调整以保证软件系统的服务质量.由于通常的类别匹配式环境感知策略不满足系统中服务QoS连续性的需求,本文经过分析环境自适应的组合服务系统的运行原理,提出一个基于动态QoS计算的环境变化识别方法,实现了从环境监测到输出变化事件的系统的环境感知功能,给出了环境监测及变化识别策略,设计了整体的变化识别算法以及其中具体的变化识别阈值计算算法,并通过实验结果表明了变化识别方法可以良好并高效地完成系统的环境感知需求.     

不对称约束多人非零和博弈的自适应评判控制

本文针对连续时间非线性系统的不对称约束多人非零和博弈问题, 建立了一种基于神经网络的自适应评判控制方法. 首先, 本文提出了一种新颖的非二次型函数来处理不对称约束问题, 并且推导出最优控制律和耦合Hamilton-Jacobi方程. 值得注意的是, 当系统状态为零时, 最优控制策略是不为零的, 这与以往不同. 然后, 通过构建单一评判网络来近似每个玩家的最优代价函数, 从而获得相关的近似最优控制策略. 同时, 在评判学习期间发展了一种新的权值更新规则. 此外, 通过利用Lyapunov理论证明了评判网络权值近似误差和闭环系统状态的稳定性. 最后, 仿真结果验证了本文所提方法的有效性     

基于事件驱动控制的混杂动态博弈系统的纳什均衡分析

本文研究了基于事件驱动控制的混杂动态博弈系统的纳什均衡分析问题. 首先, 分析了事件驱动机制对混 杂动态博弈过程的影响, 进而, 在进行状态空间描述的基础上, 给出了混杂动态博弈的纳什均衡的定义, 并建立了对 应博弈系统的策略型模型. 其次, 结合Lanchester方程, 分别讨论了两类混杂动态博弈系统的均衡问题, 包括事件驱 动策略设计和固定的情况, 获得了均衡解存在的必要条件. 最后, 通过数值模拟进行了应用分析, 验证了所取得结果 的合理性和科学性, 并总结了混杂动态博弈研究的未来工作.     

基于博弈学习的动态频谱分配算法研究

为了解决认知无线网络中的动态频谱分配问题,提高频谱利用率和避免干扰,提出了一种基于学习的库诺(Cournot)博弈模型,将授权用户对于空闲频谱的分配行为模拟为动态的博弈过程,并赋予授权用户学习的能力,通过对博弈过程中博弈者行为的学习和总结形成新的博弈策略,而且还比较了将最优反应学习算法和模拟退火算法应用到自适应博弈学习中系统的性能和用户的收益。仿真结果表明,两种算法均能够使授权用户通过学习达到策略的均衡,而有限理性下基于模拟退火的自适应博弈学习算法的鲁棒性更强,收敛性更好,且能够使授权用户获得更高的收益。     

具有可参数化不确定性系统的对偶自适应模型预测控制

控制系统中存在的不确定性为其性能优化带来诸多问题.自适应控制和鲁棒控制是针对系统存在的不确定性而采取的不同设计策略;前者没有充分考虑系统的未建模动态,而后者往往是针对不确定的最大界而设计,具有较强的保守性.本文试图将自适应控制和鲁棒控制的策略相结合,提出了一种在模型预测控制中利用未来不确定信息的对偶自适应模型预测控制策略.该策略将系统中由未建模动态引起的不确定性参数化表达,并为其设定边界约束,作为优化问题中新的约束,在优化控制目标的同时减小系统不确定性对控制的影响.仿真结果表明,本文提出的算法较传统自适应模型预测控制算法,对于系统存在的不确定性由于在迭代过程中采用参数化描述,得到了更好的系统性能,且具有更好的收敛性.     

自适应并行蚁群算法

蚁群算法是一种模拟进化算法,具有很强的全局搜索能力.本文提出一种自适应的并行蚁群算法(A-PACO),该算法可以根据不同的搜索阶段,自适应确定参数的最优组合,在一定程度上避免停滞现象的出现并加速算法收敛.而且自适应的迁移策略可以较大丰富系统多样性的同时也较大降低子蚁群间的通信量,有效提高算法的搜索质量和缩短算法的运行时间.最后选用中国CHN144问题对该算法进行检验,结果显示该算法具有较好的稳定性和较快的收敛速度.     

有限次重复囚徒博弈中的合作机制研究

模仿现实中人们的决策方式,提出类"触发策略"的策略思想,将原问题由双策略的多阶段博弈转换为多策略的一次性博弈,并建立起扩展的支付矩阵;然后运用进化博弈理论,将随机扰动引入复制子动态,从理论上说明有限次重复囚徒博弈之所以能够涌现合作是复制效应和变异效应共同作用的结果;最后通过建立多主体系统的仿真模型,进一步分析和验证了合作涌现的门限条件和稳定状态。     

基于博弈理论的经济网格资源配置研究

针对经济网格中,由于网格系统的复杂性和用户的私利性,使得网格用户在资源竞价过程中往往因相关信息的匮乏而导致资源竞价的盲目性问题,根据重复博弈分阶段执行的特点,将网格用户间对网格资源的竞争看作多阶段的重复博弈过程.用户依据前一阶段博弈的竞价值及竞价结果对当前阶段的竞价策略进行调整,通过有限次的阶段博弈达到均衡出价策略组合,实现用户最大效用下的资源分配.仿真表明,在不完全信息的网格环境中,该竞价模型可逐步改善网格用户的资源竞价策略,实现优化目标最大化下的网格资源分配.     

Learning through reinforcement for N-person repeated constrained games

The design and analysis of an adaptive strategy for N-person averaged constrained stochastic repeated game are addressed. Each player is modeled by a stochastic variable-structure learning automaton. Some constraints are imposed on some functions of the probabilities governing the selection of the player's actions. After each stage, the payoff to each player as well as the constraints are random variables. No information concerning the parameters of the game is a priori available. The "diagonal concavity" conditions are assumed to be fulfilled to guarantee the existence and uniqueness of the Nash equilibrium. The suggested adaptive strategy which uses only the current realizations (outcomes and constraints) of the game is based on the Bush-Mosteller reinforcement scheme in connection with a normalization procedure. The Lagrange multipliers approach with a regularization is used. The asymptotic properties of this algorithm are analyzed. Simulation results illustrate the feasibility and the performance of this adaptive strategy.     

An experimental study of adaptive testing for software reliability assessment

Adaptive testing is a new form of software testing that is based on the feedback and adaptive control principle and can be treated as the software testing counterpart of adaptive control. Our previous work has shown that adaptive testing can be formulated and guided in theory to minimize the variance of an unbiased software reliability estimator and to achieve optimal software reliability assessment. In this paper, we present an experimental study of adaptive testing for software reliability assessment, where the adaptive testing strategy, the random testing strategy and the operational profile based testing strategy were applied to the Space program in four experiments. The experimental results demonstrate that the adaptive testing strategy can really work in practice and may noticeably outperform the other two. Therefore, the adaptive testing strategy can serve as a preferable alternative to the random testing strategy and the operational profile based testing strategy if high confidence in the reliability estimates is required or the real-world operational profile of the software under test cannot be accurately identified.     

一种直接多变量自适应解耦控制算法

本文将广义最小方差控制策略和前馈控制策略结合进来,提出了解耦控制器并讨论了如何采用修改最小二乘辨识算法和直接方案对具有任意延时结构的一般随机多变量系统实现自适应解耦控制,本文还证明了所提出的自适应算法即使用于开环不稳定或非最小相位系统也具有整体稳定性和收敛性。     

基于自适应事件触发牵制控制的多时滞随机耦合神经网络簇同步

本文通过自适应事件触发牵制控制策略,研究了多时滞的随机耦合神经网络在均方意义下以指数速率进行簇同步的问题.在耦合神经网络中,同一簇中的节点只需与相应的孤立节点同步,而对于不同簇中节点之间的同步状态没有要求.首先,本文提出了一种事件触发牵制控制方法来解决耦合神经网络中节点数量众多、通讯复杂的问题.该方法不仅能减少耦合神经网络中控制器的数量,还可以减少控制信号的传输次数、减轻网络传输压力.然后根据M矩阵方法,建立了随机耦合神经网络均方指数稳定的充分条件.同时,利用自适应控制策略,给出了反馈增益的更新规律.最后,通过一个数值例子验证了所提出的自适应事件触发牵制控制策略的有效性和适用性.     

随机非线性系统基于事件触发机制的自适应神经网络控制

针对一类具有严格反馈结构且控制方向未知的随机非线性系统，提出了基于事件触发机制的自适应神经网络（Adaptive neural network，ANN）输出反馈控制方法.利用径向基神经网络逼近系统中未知的非线性函数.通过引入Nussbaum增益函数并设计滤波器，解决了系统控制方向未知的问题.通过设计具有相对阈值的事件触发机制，保证了闭环随机非线性系统的有界性.最后给出数值仿真例子验证所提控制方法的有效性.     

Adaptive neural network control of bilateral teleoperation with unsymmetrical stochastic delays and unmodeled dynamics

In this paper, adaptive NN control is proposed for bilateral teleoperation system with dynamic uncertainties, unknown external disturbances, and unsymmetrical stochastic delays in communication channel to achieve transparency and robust stability. Compared with previous passivity‐based teleoperation framework, the communication delays are unsymmetrical and stochastic. By partial feedback linearization using nominal dynamics, the nonlinear dynamics of the teleoperation system are transformed into two subsystems: local master/slave dynamics control and time‐delay motion tracking. By integrating Markov jump systems and adaptive parameters updating, adaptive NN control strategy is developed. The stability of the closed‐loop system and the boundedness of tracking errors are proved using Lyapunov–Krasovskii functional synthesis under specific linear matrix inequalities conditions. The proposed adaptive NN control is robust against motion disturbances, parametric uncertainties, and unsymmetrical stochastic delay, which effectiveness is validated by extensive simulation studies. Copyright © 2013 John Wiley & Sons, Ltd.     

Neural-network-based stochastic linear quadratic optimal tracking control scheme for unknown discrete-time systems using adaptive dynamic programming

In this paper, a stochastic linear quadratic optimal tracking scheme is proposed for unknown linear discrete-time (DT) systems based on adaptive dynamic programming (ADP) algorithm. First, an augmented system composed of the original system and the command generator is constructed and then an augmented stochastic algebraic equation is derived based on the augmented system. Next, to obtain the optimal control strategy, the stochastic case is converted into the deterministic one by system transformation, and then an ADP algorithm is proposed with convergence analysis. For the purpose of realizing the ADP algorithm, three back propagation neural networks including model network, critic network and action network are devised to guarantee unknown system model, optimal value function and optimal control strategy, respectively. Finally, the obtained optimal control strategy is applied to the original stochastic system, and two simulations are provided to demonstrate the effectiveness of the proposed algorithm.     

A new decentralized implicit adaptive regulator for large-scale systems described by discrete-time state-space mathematical models

In this paper, we treat the problem of decentralized implicit adaptive regulation for large-scale stochastic systems composed into a set of interconnected systems that are described by discrete-time state-space mathematical models with unknown parameters. The key idea in the decentralized regulation method is to design local regulator using only local information such that the state of each interconnected system is regulated to a certain constant reference signal. The main contribution is the proposition of a decentralized implicit adaptive regulator based on state-feedback strategy that can be applied to stochastic interconnected systems with unknown parameters. Furthermore, the practical implementation of the proposed decentralized implicit adaptive regulator can be made easily (low-cost implementation of the electronic components, short computation of the decentralized control law, etc.). A theorem is established and proved which gives sufficient stability conditions of the resulting closed-loop interconnected systems by using the Lyapunov method. An example of numerical simulation is treated to test the performance of the proposed decentralized implicit adaptive regulator.     

AdaSVRG：自适应学习率加速SVRG

在深度学习任务中,随机方差衰减梯度法通过降低随机梯度方差,因此,其具有较好的稳定性和较高的计算效率。然而,这类方法在学习过程中均使用恒定的学习率,降低了随机方差衰减梯度法的计算效率。基于随机方差衰减梯度法,借鉴动量加速思想并对梯度估计采取加权平均策略,对学习率利用历史梯度信息进行自动调整,提出了自适应随机方差衰减梯度法。基于MNIST和CIFAR-10数据集,验证提出的自适应随机方差衰减梯度法的有效性。实验结果表明,自适应随机方差衰减梯度法在收敛速度和稳定性方面优于随机方差衰减梯度法和随机梯度下降法。     

一类随机逼近问题的最优迭代次数分配*

本文考虑一类各分量相对独立的多维随机逼近问题。从最小渐近方差的要求出发,分析出各分量最优迭代次数分配比例,并给出实现这种迭代次数分配的策略及策略参数的适应性的递推估计公式。