检索结果-内蒙古大学图书馆

cross-entropy optimization of Control Policies With Adaptive Basis Functions

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 2011年第1期41卷 196-209页

作者： Busoniu, Lucian Ernst, Damien De Schutter, Bart Babuska, Robert Delft Univ Technol Delft Ctr Syst & Control NL-2628 CD Delft Netherlands Belgian Natl Fund Sci Res FRS FNRS B-1000 Brussels Belgium Univ Liege Syst & Modeling Res Unit B-4000 Liege Belgium Delft Univ Technol Marine & Transport Technol Dept NL-2628 CD Delft Netherlands

This paper introduces an algorithm for direct search of control policies in continuous-state discrete-actionMarkov decision processes. The algorithm looks for the best closed-loop policy that can be represented using a given number of basis functions (BFs), where a discrete action is assigned to each BF. The type of the BFs and their number are specified in advance and determine the complexity of the representation. Considerable flexibility is achieved by optimizing the locations and shapes of the BFs, together with the action assignments. The optimization is carried out with the cross-entropy method and evaluates the policies by their empirical return from a representative set of initial states. The return for each representative state is estimated using Monte Carlo simulations. The resulting algorithm for cross-entropy policy search with adaptive BFs is extensively evaluated in problems with two to six state variables, for which it reliably obtains good policies with only a small number of BFs. In these experiments, cross-entropy policy search requires vastly fewer BFs than value-function techniques with equidistant BFs, and outperforms policy search with a competing optimization algorithm called DIRECT.

关键词： Adaptive basis functions cross-entropy optimization direct policy search Markov decision processes

来源：评论

学校读者我要写书评

暂无评论

cross-entropy optimization for the Design of Triangular FBG Filter With Asymmetrical Spectrum

引用

IEEE PHOTONICS TECHNOLOGY LETTERS 2013年第3期25卷 295-298页

作者： Chen, Jung-Chieh Wen, Chao-Kai Ting, Pangan Natl Kaohsiung Normal Univ Dept Optoelect & Commun Engn Kaohsiung 802 Taiwan Natl Sun Yat Sen Univ Inst Commun Engn Kaohsiung 804 Taiwan Ind Technol Res Inst Hsinchu 310 Taiwan

This letter reports the use of optimization methods to design triangular fiber Bragg grating (TFBG) filter with asymmetrical spectrum. In the optimization methods, TFBG synthesis problems are formulated as nonlinear objective functions, and stochastic optimization techniques are applied to search for index modulation profiles that minimize the difference between the synthesized and targeted spectra. However, the performances of traditional stochastic optimization techniques are affected by the initial guess. A poor initial guess may result in low-efficiency optimizations and easily get trapped into local solutions;in some cases, it may even lead to a false result. Accordingly, we introduce the use of cross-entropy optimization (CEO) in searching for the optimal index modulation profiles. CEO is an effective algorithm that solves various continuous multiextremal optimization problems and demonstrates robustness with respect to starting conditions. Computer simulation results show that the index modulation profiles obtained using the proposed method performed better compared with those obtained using the conventional covariance matrix adaptation evolution strategy (CMAES). In addition, CEO also provides a reliable convergence to the near-optimum solution. These findings indicate the CEO is more suitable than CMAES for the design of TFBG filters with asymmetrical spectrum for sensor applications.

关键词： cross-entropy optimization fiber Bragg grating filter design optimization methods

来源：评论

学校读者我要写书评

暂无评论

Refined first-order reliability method using cross-entropy optimization method

引用

ENGINEERING WITH COMPUTERS 2019年第4期35卷 1507-1519页

作者： Arab, Hamed Ghohani Rashki, Mohsen Rostamian, Mehdi Ghavidel, Alireza Shahraki, Hossein Keshtegar, Behrooz Univ Sistan & Baluchestan Dept Civil Engn Zahedan Iran Univ Sistan & Baluchestan Dept Architecture Engn Zahedan Iran Univ Memphis Memphis TN 38152 USA Univ Bojnord Dept Civil Engn Bojnord Iran Univ Zabol Dept Civil Engn Zabol Iran

Generally, the first-order reliability method (FORM) is an efficient and accurate reliability method for problems with linear limit state functions (LSFs). It is showed that the FORM formula may produce inaccurate results when the LSF is defined by mathematical forms introduced as gray function. Thus, the original FORM formula may provide the results with huge errors. In this paper, a probabilistic optimization model as refined FORM (R-FORM) is presented to search most probable failure point (MPP) with the accurate results for gray LSFs. The cross-entropy optimization (CEO) method is utilized to search MPP in proposed R-FORM model. Several reliability problems are applied to illustrate the accuracy of the R-FORM compared to the conventional FORM formula. Results illustrate that the R-FORM provides more accurate results than the FORM for gray performance functions.

关键词： Failure probability Probabilistic model Refined FORM cross-entropy optimization

来源：评论

学校读者我要写书评

暂无评论

Hierarchical cross-entropy optimization for Fast On-Chip Decap Budgeting

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2011年第11期30卷 1610-1620页

作者： Zhao, Xueqian Guo, Yonghe Chen, Xiaodao Feng, Zhuo Hu, Shiyan Michigan Technol Univ Dept Elect & Comp Engn Houghton MI 49931 USA

Decoupling capacitor (decap) has been widely used to effectively reduce dynamic power supply noise. Traditional decap budgeting algorithms usually explore the sensitivity-based nonlinear optimizations or conjugate gradient (CG) methods, which can be prohibitively expensive for large-scale decap budgeting problems and cannot be easily parallelized. In this paper, we propose a hierarchical cross-entropy based optimization technique which is more efficient and parallel-friendly. cross-entropy (CE) is an advanced optimization framework which explores the power of rare event probability theory and importance sampling. To achieve the high efficiency, a sensitivity-guided cross-entropy (SCE) algorithm is introduced which integrates CE with a partitioning-based sampling strategy to effectively reduce the solution space in solving the large-scale decap budgeting problems. Compared to improved CG method and conventional CE method, SCE with Latin hypercube sampling method (SCE-LHS) can provide 2x speedups, while achieving up to 25% improvement on power supply noise. To further improve decap optimization solution quality, SCE with sequential importance sampling (SCE-SIS) method is also studied and implemented. Compared to SCE-LHS, in similar runtime, SCE-SIS can lead to 16.8% further reduction on the total power supply noise.

关键词： Adjoint sensitivity analysis cross-entropy optimization decoupling capacitor budgeting power grid design power supply noise

来源：评论

学校读者我要写书评

暂无评论

Oblique decision tree induction by cross-entropy optimization based on the von Mises-Fisher distribution

引用

COMPUTATIONAL STATISTICS 2022年第5期37卷 2203-2229页

作者： Bollwein, Ferdinand Westphal, Stephan Tech Univ Clausthal Inst Math Erzstr 1 D-38678 Clausthal Zellerfeld Germany

Oblique decision trees recursively divide the feature space by using splits based on linear combinations of attributes. Compared to their univariate counterparts, which only use a single attribute per split, they are often smaller and more accurate. A common approach to learn decision trees is by iteratively introducing splits on a training set in a top-down manner, yet determining a single optimal oblique split is in general computationally intractable. Therefore, one has to rely on heuristics to find near-optimal splits. In this paper, we adapt the cross-entropy optimization method to tackle this problem. The approach is motivated geometrically by the observation that equivalent oblique splits can be interpreted as connected regions on a unit hypersphere which are defined by the samples in the training data. In each iteration, the algorithm samples multiple candidate solutions from this hypersphere using the von Mises-Fisher distribution which is parameterized by a mean direction and a concentration parameter. These parameters are then updated based on the best performing samples such that when the algorithm terminates a high probability mass is assigned to a region of near-optimal solutions. Our experimental results show that the proposed method is well-suited for the induction of compact and accurate oblique decision trees in a small amount of time.

关键词： Oblique decision trees cross-entropy optimization von Mises-Fisher distribution Classification Regression

来源：评论

学校读者我要写书评

暂无评论

cross entropy optimization of Action Modification Policies for Continuous-Valued MDPs 21st

Cross Entropy Optimization of Action Modification Policies f...

引用

21st IFAC World Congress on Automatic Control - Meeting Societal Challenges

作者： Mirkamali, Kamelia Busoniu, Lucian Khaje Nasir Toosi Univ Technol Dept Comp Engn Tehran Iran Tech Univ Cluj Napoca Automat Dept Cluj Napoca Romania

We propose an algorithm to search for parametrized policies in continuous state and action Markov Decision Processes (MDPs). The policies are represented via a number of basis functions, and the main novelty is that each basis function corresponds to a small, discrete modification of the continuous action. In each state, the policy chooses a discrete action modification associated with a basis function having the maximum value at the current state. Empirical returns from a representative set of initial states are estimated in simulations to evaluate the policies. Instead of using slow gradient-based algorithms, we apply cross entropy method for updating the parameters. The proposed algorithm is applied to a double integrator and an inverted pendulum problem, with encouraging results. Copyright (C) 2020 The Authors.

关键词： Markov decision processes policy search cross-entropy optimization continuous actions

来源：评论

学校读者我要写书评

暂无评论

cross entropy optimization of Action Modification Policies for Continuous-Valued MDPs ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 8124-8129页

作者： Kamelia Mirkamali Lucian Buşoniu Department of Computer Engineering Khaje Nasir Toosi University of Technology Tehran Iran Automation Department Technical University of Cluj-Napoca Cluj-Napoca Romania

关键词： Markov decision processes policy search cross-entropy optimization continuous actions

来源：评论

学校读者我要写书评

暂无评论

The Research of Multi-mode PID Controller Parameters optimization Based on cross-entropy Method 33

The Research of Multi-mode PID Controller Parameters Optimiz...

引用

33rd Chinese Control Conference (CCC)

作者： Zhao, Duo Huang, Jin Li, Song Jin, Weidong Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China

ISBN: (纸本)9789881563842

This paper introduces cross-entropy optimization method and Multi-mode Proportional-Integral-Derivative (Multi-mode PID) control algorithm. With features of simple control parameter setting, low computation complexity and high robustness, the cross-entropy optimization method is applied to iterative optimization in Multi-mode PID controller parameters design. hi present paper, simulation investigations for an industrial process are carried out, and the feasibility, effectiveness and good performance of the proposed method is verified.

关键词： cross-entropy optimization Multi-mode PID Controller Controller Parameters optimization

来源：评论

学校读者我要写书评

暂无评论

cross-entropy Method for Design and optimization of Pixelated Metasurfaces

引用

IEEE ACCESS 2020年 8卷 224922-224931页

作者： Kovaleva, Maria Bulger, David Esselle, Karu P. Curtin Univ Int Ctr Radio Astron Res ICRAR Curtin Bentley WA 6102 Australia Macquarie Univ Dept Math & Stat N Ryde NSW 2109 Australia Univ Technol Sydney Sch Elect & Data Engn Ultimo NSW 2007 Australia

Electromagnetic metasurfaces are planar two-dimensional metamaterials, typically of subwavelength thickness. Unit cell elements of different shapes have been widely explored, including electric and magnetic dipoles, patches, arbitrary geometries and pixelated surfaces. Although pixelated metasurfaces have a great advantage of geometric versatility, their design and analysis requires algorithmic approach. One of the techniques for their design is via evolutionary simulation-driven optimization. Since full-wave electromagnetic simulations are time-consuming, optimization methods with fast convergence properties are preferable. In this article, we demonstrate the application of the cross-entropy optimization method to design of artificial magnetic conductors (AMCs) and thin printed phase shifters. Single-frequency AMCs at 10 GHz (X band) and dual-frequency AMCs at 8 and 12 GHz (X and Ku band) were produced that are more manufacturing-friendly, and thus cost effective, than previously reported AMCs. We also show that phase-shifting unit cells with transmission magnitudes over 0.9 (linear) can be designed using the proposed optimization technique. Other potential applications of these unit cells are in phase-correcting and beam-steering metasurfaces.

关键词： optimization Image quality Periodic structures Geometry Genetic algorithms Electromagnetics Dielectrics Binary electromagnetic structures beam steering cross-entropy optimization electromagnetic metamaterials evolutionary computation maximum likelihood estimation metasurfaces microwave propagation optimization methods phase shifters

来源：评论

学校读者我要写书评

暂无评论

The Research of Multi-mode PID Controller Parameters optimization Based on cross-entropy Method

The Research of Multi-mode PID Controller Parameters Optimiz...

引用

第三十三届中国控制会议

作者： Duo Zhao Jin Huang Song Li Weidong Jin School of Electrical Engineering Southwest Jiaotong University

ISBN: (纸本)9781479947249

This paper introduces cross-entropy optimization method and Multi-mode Proportional-Integral-Derivative(Multi-mode PID) control *** features of simple control parameter setting,low computation complexity and high robustness,the cross-entropy optimization method is applied to iterative optimization in Multi-mode PID controller parameters *** present paper,simulation investigations for an industrial process are carried out,and the feasibility,effectiveness and good performance of the proposed method is verified.

关键词： cross-entropy optimization Multi-mode PID Controller Controller Parameters optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：