解决一类博弈问题的神经网络系统

从博弈问题的固有属性出发，探讨了解决博弈问题的新途径，并阐述了如何建造解决一类博弈问题的神经网络系统。所建的对弈实验系统运行效果良好，这表明用神经网络来解决博弈问题有着广阔的前景。     

非对称博弈的表示和求解

非对称博弈是一种普遍存在的博奔现象,现实中大量的博弈都呈现出非对称的特性.但是非对称博弈的表示问题在多-Agent影响图中是一个难以解决的问题,存在表示复杂和求解效率低的情况.针对该问题,借鉴了单-Agent决策系统中非对称性表示的方法,提出了一种新的博弈模型,有效的解决了非对称博弈的表示问题.给出了该模型详细的求解算...     

用于辩证分析的多方对话协议

在基于辩论的多agent系统研究中,agent之间的对话博弈一般是双方的,然而现实中的辩论却常常涉及到多方参与者,如何实现多agent系统的多方对话博弈是当前的研究热点之一。用于多方论据博弈的辩证分析模型(DAM-MAG)是一种借鉴中国武术擂台比武思想,将多方对话博弈转化为若干个双方对话博弈的理论模型。DAM-MAG的难点在于多方对话博弈协议的设计和实现。为此,基于该理论模型提出了一种多方对话博弈协议。该协议提供了通过双方对话博弈来解决多方对话博弈问题的方法,为解决多agent系统的多方对话博弈提供了新的途径。     

数独问题的一个分布式物理博弈求解

数独问题已被证明是一个NP完全问题。采用分布式势博弈方法求解该问题。首先建立其效用函数并证明数独问题可以转化为势博弈模型,然后使用学习动力逐步优化参与者的状态以达到势博弈的最优状态—纳什均衡点。同时势博弈现有大部分研究结果限于计算机仿真,为此给出数独问题一个物理的博弈实现,物理博弈过程参与者通过三个手机体现。实验结果表明新的解决方式能够快速收敛。     

基于概率的剪枝算法

以alpha—beta剪枝算法为研究对象，提出一种基于alpha—beta剪枝和概率剪枝因素相结合的概率剪枝算法．来解决博弈树搜索问题。利用概率剪枝算法，可减少博弈树搜索深度，从而加快搜索进程。     

面向人工智能专业课程的棋类博弈教学辅助平台

针对人工智能类课程博弈算法理论性太强、算法较复杂和抽象等问题,设计并实现功能较为完整、用户界面友好的棋类博弈教学辅助平台,平台允许用户上传编写好的博弈程序,实现博弈程序间对弈、人与博弈程序对弈以及人人对弈。本文阐述了棋类博弈教学辅助平台的总体设计、主要功能模块以及搭建平台采用的核心技术。棋类博弈教学平台的设计有益于培养学生依据所学理论知识来解决实际问题的能力,促进学生对计算机博弈程序和人工智能方法的不断探索改进,以达到更好的教学效果。本文进一步评估了棋类博弈平台在人工智能课程的实际使用情况与实践效果。     

一种基于合作博弈的均衡路由方法

网络资源公平性分配是网络可存性研究中的关键问题，路由选择算法是影响网络资源分配的公平性和均衡性的关键因素。本文研究路由器路径选择中的均衡性问题，提出了基于博弈论思想的解决方案，即将IPv6协议中的任意播路由问题看作是合作参与者间的博弈；针对该博弈问题，建立了路由算法的合作博弈模型，求得了该博弈均衡点，并在此基础上，提出了一种基于合作博弈的均衡路由方法；最后通过实验仿真了算法结果。     

面向量子博弈论的光量子芯片设计及实验

量子博弈论是量子信息和经典博弈论的交叉研究方向。理论研究表明，量子博弈模型不仅能够突破经典博弈模型的收益上限，更是有望用于深入理解和突破量子通信、量子计算等领域的很多基础问题。针对一种利益冲突的贝叶斯量子博弈模型，提出了一种可编程的光量子芯片结构，首次运用硅基光量子芯片实验完成了量子博弈实验。通过动态生成和调控片上量子纠缠态，实验证实了量子博弈相对经典博弈的博弈优势，展示了光量子芯片在量子博弈论研究中的重要作用，为量子信息领域更复杂问题的研究提供了重要的实验手段。     

无线传感器网络中安全数据传输的配对同步博弈模型研究

无线传感器网络具有其无人值守和动态开放的特点,因此容易遭受恶意攻击.针对该问题,提出利用博弈理论来支持无线传感器网络中的安全数据传输.基于博弈理论对隐含恶意节点的无线传感器网络中的数据传输过程进行建模,对节点之间的攻击与入侵检测问题用空间结构上的配对同步博弈进行模拟.在进行博弈建模时,充分考虑节点之间的合作与竞争关系,并给出了详细的博弈算法.模拟实验表明,所提出和研究的博弈模型较为有效地解决了隐含恶意节点在无线传感器网络中的安全数据传输问题.     

一种求解二人序贯博弈均衡的新算法

虽然线性规划方法处理正规型零和博弈均衡问题有其独特的优点,但对零和序贯博弈均衡问题的求解却无能为力,而常用的逆向归纳法求解该类问题也有其固有的不足。鉴于上述原因,首先在序贯型博弈中定义了行动序列和实现概率等概念并给出相关定理。在此基础上,结合线性规划的思想,推出了求解二人零和序贯博弈均衡的新算法。该算法的目的是把序贯型博弈纳什均衡求解问题转化为线性规划问题,然后通过使用现成的线性规划软件（比如LINDO/LINGO软件）进行求解。该算法对解决该类问题提供了新的途径,具有一定的理论价值和实用价值。最后的算例对比分析说明了算法的可行性和有效性。     

基于神经网络的微分对策控制器设计

采用伴随－BP技术，将微分对策的两点边值求解问题转化两个神经网络的学习问题，训练后的两个神经网络分别作为对策双方的最优控制器在线使用，避免了直接求解复杂的两点边值问题，对追逃微分对策问题的仿真结果表明，该方法对初始条件和噪声具有较好的鲁棒性。     

Neural network solution for finite-horizon H-infinity constrained optimal control of nonlinear systems

In this paper, neural networks are used to approximately solve the finite-horizon constrained input H-infinity state feedback control problem. The method is based on solving a related Hamilton-Jacobi-Isaacs equation of the corresponding finite-horizon zero-sum game. The game value function is approximated by a neural network with time- varying weights. It is shown that the neural network approximation converges uniformly to the game-value function and the resulting almost optimal constrained feedback controller provides closed-loop stability and bounded L2 gain. The result is an almost optimal H-infinity feedback controller with time-varying coefficients that is solved a priori off-line. The effectiveness of the method is shown on the Rotational/Translational Actuator benchmark nonlinear control problem.     

Online solution of nonlinear two‐player zero‐sum games using synchronous policy iteration

The two‐player zero‐sum (ZS) game problem provides the solution to the bounded L₂‐gain problem and so is important for robust control. However, its solution depends on solving a design Hamilton–Jacobi–Isaacs (HJI) equation, which is generally intractable for nonlinear systems. In this paper, we present an online adaptive learning algorithm based on policy iteration to solve the continuous‐time two‐player ZS game with infinite horizon cost for nonlinear systems with known dynamics. That is, the algorithm learns online in real time an approximate local solution to the game HJI equation. This method finds, in real time, suitable approximations of the optimal value and the saddle point feedback control policy and disturbance policy, while also guaranteeing closed‐loop stability. The adaptive algorithm is implemented as an actor/critic/disturbance structure that involves simultaneous continuous‐time adaptation of critic, actor, and disturbance neural networks. We call this online gaming algorithm ‘synchronous’ ZS game policy iteration. A persistence of excitation condition is shown to guarantee convergence of the critic to the actual optimal value function. Novel tuning algorithms are given for critic, actor, and disturbance networks. The convergence to the optimal saddle point solution is proven, and stability of the system is also guaranteed. Simulation examples show the effectiveness of the new algorithm in solving the HJI equation online for a linear system and a complex nonlinear system. Copyright © 2011 John Wiley & Sons, Ltd.     

A novel neural network for nonlinear convex programming

In this paper, we present a neural network for solving the nonlinear convex programming problem in real time by means of the projection method. The main idea is to convert the convex programming problem into a variational inequality problem. Then a dynamical system and a convex energy function are constructed for resulting variational inequality problem. It is shown that the proposed neural network is stable in the sense of Lyapunov and can converge to an exact optimal solution of the original problem. Compared with the existing neural networks for solving the nonlinear convex programming problem, the proposed neural network has no Lipschitz condition, no adjustable parameter, and its structure is simple. The validity and transient behavior of the proposed neural network are demonstrated by some simulation results.     

Multi-agent graphical games with input constraints: an online learning solution

This paper studies an online iterative algorithm for solving discrete-time multi-agent dynamic graphical games with input constraints. In order to obtain the optimal strategy of each agent, it is necessary to solve a set of coupled Hamilton-Jacobi-Bellman (HJB) equations. It is very difficult to solve HJB equations by the traditional method. The relevant game problem will become more complex if the control input of each agent in the dynamic graphical game is constrained. In this paper, an online iterative algorithm is proposed to find the online solution to dynamic graphical game without the need for drift dynamics of agents. Actually, this algorithm is to find the optimal solution of Bellman equations online. This solution employs a distributed policy iteration process, using only the local information available to each agent. It can be proved that under certain conditions, when each agent updates its own strategy simultaneously, the whole multi-agent system will reach Nash equilibrium. In the process of algorithm implementation, for each agent, two layers of neural networks are used to fit the value function and control strategy, respectively. Finally, a simulation example is given to show the effectiveness of our method.     

Neural networks for solving multicriteria solid transportation problem

In this paper, we present neural networks for solving multicriteria solid transportation problems. The original problem is transformed into an equivalent continuous problem from the continuous-time dynamic system and its optimal solution can be got. The procedure and efficiency of this approach are shown with numerical simulations.     

Neural network solution for finite-horizon H ∞ state feedback control of nonlinear systems

In this article, neural networks are used to approximately solve the finite-horizon optimal H _∞ state feedback control problem. The method is based on solving a related Hamilton–Jacobi–Isaacs equation of the corresponding finite-horizon zero-sum game. The neural network approximates the corresponding game value function on a certain domain of the state-space and results in a control computed as the output of a neural network. It is shown that the neural network approximation converges uniformly to the game-value function and the resulting controller provides closed-loop stability and bounded L ₂ gain. The result is a nearly exact H _∞ feedback controller with time-varying coefficients that is solved a priori offline. The results of this article are applied to the rotational/translational actuator benchmark nonlinear control problem.     

Minimax神经网络收敛性分析

ｍｉｎｉｍａｘ问题的研究不仅在对策论、数学规划和最优控制中具有重要意义，而且许多类型的问题都需要寻求ｍｉｎｉｍａｘ问题的数值解．本文建立了连续动力系统神经网络来探讨ｍｉｎ－ｉｍａｘ问题，在适当的条件下利用Ｌｙａｐｕｎｏｖ函数讨论了网络的稳定性和收敛性，并证明了神经网络的稳定平衡点即为ｍｉｎｉｍａｘ问题的鞍点．这样的网络可由ＶＬＳＩ技术实现，且具有实时动力学行为，它们也很象生物处理的动力学．在适当的条件下，利用Ｌｙａｐｕｎｏｖ函数稳定性理论证明了该网络是Ｌｙａｐｕｎｏｖ稳定的，且网络收敛于鞍函数的鞍点     

基于Tank-Hopfield神经网络的有约束多变量广义预测控制器

通过对系统的信号约束，构成有约束多变量广义预测控制问题，并运用Ｔ－Ｈ优化神经网络来求解这一复杂的优化问题。在求解过程中，有约束广义预测控制的求解被转化为一个Ｔ－Ｈ优化电路网络的稳态解。因此可以通过硬件电路或龙格－库塔数值方法进行求取。在一个工业过程模型上的仿真研究证明这一方法是非常有效的。     

An improved dynamic structure-based neural networks determination approaches to simulation optimization problems

Simulation optimization studies the problem of optimizing simulation-based objectives. This field has a strong history in engineering but often suffers from several difficulties including being time-consuming and NP-hardness. Simulation optimization is a new and hot topic in the field of system simulation and operational research. This paper presents a hybrid approach that combines Evolutionary Algorithms with neural networks (NNs) for solving simulation optimization problems. In this hybrid approach, we use NNs to replace the known simulation model for evaluating subsequent iterative solutions. Further, we apply the dynamic structure-based neural networks to learn and replace the known simulation model. The determination of dynamic structure-based neural networks is the kernel of this paper. The final experimental results demonstrated that the proposed approach can find optimal or close-to-optimal solutions and is superior to other recent algorithms in simulation optimization.