A Reinforcement Learning Adaptive Fuzzy Controller for Differential Games

In this paper we develop a reinforcement fuzzy learning scheme for robots playing a differential game. Differential games are games played in continuous time, with continuous states and actions. Fuzzy controllers are used to approximate the calculation of future reinforcements of the game due to actions taken at a specific time. If an immediate reinforcement reward function is defined, we may use a fuzzy system to tell what is the predicted reinforcement in a specified time ahead. This reinforcement is then used to adapt a fuzzy controller that stores the experience accumulated by the player. Simulations of a modified two car game are provided in order to show the potentiality of the technique. Experiments are performed in order to validate the method. Finally, it should be noted that although the game used as an example involves only two players, the technique may also be used in a multi-game environment.     

Decentralized Learning in Markov Games

Learning automata (LA) were recently shown to be valuable tools for designing multiagent reinforcement learning algorithms. One of the principal contributions of the LA theory is that a set of decentralized independent LA is able to control a finite Markov chain with unknown transition probabilities and rewards. In this paper, we propose to extend this algorithm to Markov games—a straightforward extension of single-agent Markov decision problems to distributed multiagent decision problems. We show that under the same ergodic assumptions of the original theorem, the extended algorithm will converge to a pure equilibrium point between agent policies.      

A Fuzzy Adaptive Differential Evolution Algorithm

The differential evolution algorithm is a floating-point encoded evolutionary algorithm for global optimization over continuous spaces. The algorithm has so far used empirically chosen values for its search parameters that are kept fixed through an optimization process. The objective of this paper is to introduce a new version of the Differential Evolution algorithm with adaptive control parameters – the fuzzy adaptive differential evolution algorithm, which uses fuzzy logic controllers to adapt the search parameters for the mutation operation and crossover operation. The control inputs incorporate the relative objective function values and individuals of the successive generations. The emphasis of this paper is analysis of the dynamics and behavior of the algorithm. Experimental results, provided by the proposed algorithm for a set of standard test functions, outperformed those of the standard differential evolution algorithm for optimization problems with higher dimensionality.     

模糊非线性随机微分对策的鲁棒设计

研究模糊不确定微分对策的鲁棒性。采用Takagi-Sugeno模糊模型描述多人非合作的非线性随机微分对策系统,并将全局模糊模型表示成不确定的形式,采用鲁棒次优H∞控制策略,定义了微分对策系统的鲁棒控制,并设计出稳定的模糊控制器。     

一种精英反向学习的差分演化算法

为提高差分演化算法的性能,提出一种精英反向学习策略的差分演化算法.该算法以一定的概率通过反向学习生成种群中精英个体的反向解,引入一般化系数k,构造动态搜索边界下的反向群体形成反向搜索空间,之后同时评估当前种群与反向种群的解来指导算法的搜索空间向包含全局最优解的空间逼近,有利于均衡算法的勘探与开采能力.对13个典型的测试函数进行实验,将本文算法与5种代表性的差分演化算法进行对比,结果表明本文算法不仅在求解精度上更优,在收敛速度上也有非常大的优势.     

具有快速学习算法的补偿模糊神经网络的故障诊断

在融合了模糊逻辑的推理能力和神经网络的自适应、自学习能力。同时采用输出空间模式聚类的快速学习算法,引入补偿模糊神经元,模糊运算采用动态的全局优化运算,使学习后的网络具有更高的容错性,并弥补了神经网络学习耗时的缺点,提高了效率,进行了故障检测的仿真分析,并且将其运用于未建模系统的故障诊断中取得良好的效果。     

基于微分博弈的群智频谱感知算法

计算机技术和通信技术的融合是一个必然的趋势,频谱感知作为计算机通信技术的一个组成部分,是解决现有无线系统频谱利用率低的关键技术之一.将群智感知与频谱感知相结合,提出了一种基于微分博弈的群智频谱感知算法.平台的效用定义为第三方支付的报酬减去付给次用户的报酬,次用户的效用定义为平台支付的报酬减去次用户参与频谱感知任务的成本...     

A Nash Equilibrium for Differential Games with Moving-Horizon Strategies

Computational Economics - Our paper aims at introducing a moving-horizon interaction in a strategic context. We assume that, in each instant of time, players can predict the effects of their...     

A New Algorithm for the Decentralized Aggregation Problem

This paper describes a new algorithm for solving the distributed aggregation problem in which individual values from N nodes have to be aggregated in an associative and commutative manner, and the final result must be either computed at all sites or communicated to them. Our algorithm has a message-delay product of (dN(N )) where N is the number of nodes, and d is a parameter that corresponds to the number of dimensions of the hypercube into which the nodes are logically organized. This reflects an improvement upon existing algorithms by a factor of d. The algorithm can be initiated by any node, and works by creating multiple parallel streams that collect partial aggregates and finally converge at a node to compute the final result.     

一种基于改进的FCNN网络模型的学习算法

本文给出了基于模糊聚类神经网络的新的网络模型及相应的学习算法,该算法可以有 效地克服FCNN算法的不足。     

A Weighted Average Consensus Approach for Decentralized Federated Learning

Machine Intelligence Research - Federated learning (FedL) is a machine learning (ML) technique utilized to train deep neural networks (DeepNNs) in a distributed way without the need to share data...     

一种广义模糊神经网络的参数解耦学习算法

对于强非线性系统采用分段建模十分有效,广义模糊神经网络能实现这种思想。在此基础上,给出一种模糊规则前、后件参数可分别进行学习的算法,仿真结果表明该方法拟合能力强、学习效率高。     

含噪声模糊逻辑系统的参数学习算法

当采用最小方差型的误差成本函数进行输入含噪系统的参数学习时，参数不能收敛至真值，利用包含噪声方差的误差成本函数可解决此问题．本文将此误差成本函数推广到多人单出系统，将之引入到模糊逻辑系统的参数学习中，并且输入输出数据中的噪声方差也通过学习而得到，不必进行多次测量．最后通过仿真对比验证表明了该方法的有效性．     

模糊神经网络快速学习算法的研究

在分析模糊模型及相应模糊神经网络的基础上，提出一种快速学习算法－－择近学习算法，它公需对每个训练数据学习一次，就可得了较好的结果，因此，其效率非常高。在算法中还引进了置信度的概念，以提高学习结果的可靠性，择近学习算法特别适用于捕获表达各种变量之间的结果信息。仿真结果证实了算法的有效性。     

一种模糊强化学习算法及其在RoboCup中的应用

传统的强化学习算法只能解决离散状态空间和动作空间的学习问题。论文提出一种模糊强化学习算法,通过模糊推理系统将连续的状态空间映射到连续的动作空间,然后通过学习得到一个完整的规则库。这个规则库为Agent的行为选择提供了先验知识,通过这个规则库可以实现动态规划。作者在RoboCup环境中验证了这个算法,实现了踢球策略的优化。     

Differential Games with Fixed Time

In this paper, we consider differential games, the termination time of which is fixed. These games constitute a special class suitable for more complete investigation.     

一类离散模糊系统的迭代学习控制算法

针对离散T-S模糊系统的终端控制问题,提出了一种基于离散Legendre正交多项式的迭代学习算法。该算法把待求控制量表示为离散Legendre正交多项式的线性组合,将求控制量问题转化为求离散Legendre正交多项式系数问题。在此基础上,用迭代学习的方式来修正控制量的离散Legendre系数,并运用不确定离散系统的H∞设计方法求解学习增益矩阵。最后以机器人为例进行仿真,仿真结果表明了所提算法能实现工业机器人的精确定位。     

基于直觉模糊集的集成学习算法

为提高传统机器学习算法的分类精度和泛化能力,提出一种基于直觉模糊集的集成学习算法.根据传统分类器分类精度构建直觉模糊偏好关系矩阵,确定分类器权重,结合多属性群决策方法确定样本分类结果.在UCI中的7个数据集上进行测试,与目前流行的传统分类算法以及集成学习分类算法SVM,LR,NB,Boosting,Bagging相比,...