检索结果-内蒙古大学图书馆

Corrigendum to: The TianQin project: current progress on science and technology

Progress of Theoretical and Experimental Physics 2021年第5期2021卷

作者： Mei, Jianwei Bai, Yan-Zheng Bao, Jiahui Barausse, Enrico Cai, Lin Canuto, Enrico Cao, Bin Chen, Wei-Ming Chen, Yu Ding, Yan-Wei Duan, Hui-Zong Fan, Huimin Feng, Wen-Fan Fu, Honglin Gao, Qing Gao, TianQuan Gong, Yungui Gou, Xingyu Gu, Chao-Zheng Gu, De-Feng He, Zi-Qi Hendry, Martin Hong, Wei Hu, Xin-Chun Hu, Yi-Ming Hu, Yuexin Huang, Shun-Jia Huang, Xiang-Qing Jiang, Qinghua Jiang, Yuan-Ze Jiang, Yun Jiang, Zhen Jin, Hong-Ming Korol, Valeriya Li, Hong-Yin Li, Ming Li, Pengcheng Li, Rongwang Li, Yuqiang Li, Zhu Li, Zhulian Li, Zhu-Xi Liang, Yu-Rong Liang, Zheng-Cheng Liao, Fang-Jie Liu, Qi Liu, Shuai Liu, Yan-Chong Liu, Li Liu, Pei-Bo Liu, Xuhui Liu, Yuan Lu, Xiong-Fei Lu, Yang Lu, Ze-Huang Luo, Yan Luo, Zhi-Cai Milyukov, Vadim Ming, Min Pi, Xiaoyu Qin, Chenggang Qu, Shao-Bo Sesana, Alberto Shao, Chenggang Shi, Changfu Su, Wei Tan, Ding-Yin Tan, Yujie Tan, Zhuangbin Tu, Liang-Cheng Wang, Bin Wang, Cheng-Rui Wang, Fengbin Wang, Guan-Fang Wang, Haitian Wang, Jian Wang, Lijiao Wang, Panpan Wang, Xudong Wang, Yan Wang, Yi-Fan Wei, Ran Wu, Shu-Chao Xiao, Chun-Yu Xu, Xiao-Shi Xue, Chao Yang, Fang-Chao Yang, Liang Yang, Ming-Lin Yang, Shan-Qing Ye, Bobing Yeh, Hsien-Chi Yu, Shenghua Zhai, Dongsheng Zhang, Caishi Zhang, Haitao Zhang, Jian-dong Zhang, Jie Zhang, Lihua Zhang, Xin Zhang, Xuefeng Zhou, Hao Zhou, Ming-Yue Zhou, Ze-Bing Zhu, Dong-Dong Zi, Tie-Guang Luo, Jun TianQin Research Center for Gravitational Physics & School of Physics and Astronomy Sun Yat-sen University (Zhuhai Campus) Zhuhai 519082 P.R. China Centre for Gravitational Experiments School of Physics MOE Key Laboratory of Fundamental Physical Quantities Measurement & Hubei Key Laboratory of Gravitation and Quantum Physics PGMF Huazhong University of Science and Technology Wuhan 430074 P.R. China SISSA Via Bonomea 265 34136 Trieste Italy and INFN Sezione di Trieste & IFPU – Institute for Fundamental Physics of the Universe Via Beirut 2 34014 Trieste Italy Former Faculty Politecnico di Torino Corso Duca degli Abruzzi 24 10129 Torino Italy Yunnan Observatories Chinese Academy of Sciences Kunming 650011 China School of Physical Science and Technology Southwest University Chongqing 400715 China Beijing Institute of Control Engineering Beijing 100094 P.R. China SUPA School of Physics and Astronomy University of Glasgow Glasgow G12 8QQ UK DFH Satellite Co. Ltd. Beijing 100094 P.R. China National Astronomical Observatories Chinese Academy of Sciences Beijing 100012 China School of Astronomy and Space Science University of Chinese Academy of Sciences Beijing 100049 China School of Physics and Astronomy University of Birmingham Birmingham B15 2TT United Kingdom Center for High Energy Physics & Department of Physics and State Key Laboratory of Nuclear Physics and Technology Peking University No. 5 Yiheyuan Rd Beijing 100871 P.R. China Lomonosov Moscow State University Sternberg Astronomical Institute Moscow 119992 Russia Dipartimento di Fisica “G. Occhialini” Universitá degli Studi Milano Bicocca Piazza della Scienza 3 I-20126 Milano Italy School of Aeronautics and Astronautics Shanghai Jiao Tong University Shanghai 200240 China Purple Mountain Observatory Chinese Academy of Sciences Nanjing 210023 & School of Astronomy and Space Science University of Science and Technology of China Hefei Anhui 230026 P.R. China Max-Planck-Institut für Gravitationsphysik (Al

来源：评论

学校读者我要写书评

暂无评论

Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge

arXiv

引用

arXiv 2018年

作者： Bakas, Spyridon Reyes, Mauricio Jakab, Andras Bauer, Stefan Rempfler, Markus Crimi, Alessandro Shinohara, Russell Takeshi Berger, Christoph Ha, Sung Min Rozycki, Martin Prastawa, Marcel Alberts, Esther Lipkova, Jana Freymann, John Kirby, Justin Bilello, Michel Fathallah-Shaykh, Hassan M. Wiest, Roland Kirschke, Jan Wiestler, Benedikt Colen, Rivka Kotrotsou, Aikaterini Lamontagne, Pamela Marcus, Daniel Milchenko, Mikhail Nazeri, Arash Weber, Marc-Andr Mahajan, Abhishek Baid, Ujjwal Gerstner, Elizabeth Kwon, Dongjin Acharya, Gagan Agarwal, Manu Alam, Mahbubul Albiol, Alberto Albiol, Antonio Albiol, Francisco J. Alex, Varghese Allinson, Nigel Amorim, Pedro H.A. Amrutkar, Abhijit Anand, Ganesh Andermatt, Simon Arbel, Tal Arbelaez, Pablo Avery, Aaron Azmat, Muneeza Pranjal, B. Bai, Wenjia Banerjee, Subhashis Barth, Bill Batchelder, Thomas Batmanghelich, Kayhan Battistella, Enzo Beers, Andrew Belyaev, Mikhail Bendszus, Martin Benson, Eze Bernal, Jose Bharath, Halandur Nagaraja Biros, George Bisdas, Sotirios Brown, James Cabezas, Mariano Cao, Shilei Cardoso, Jorge M. Carver, Eric N. Casamitjana, Adri Castillo, Laura Silvana Cat, Marcel Cattin, Philippe Cérigues, Albert Chagas, Vinicius S. Chandra, Siddhartha Chang, Yi-Ju Chang, Shiyu Chang, Ken Chazalon, Joseph Chen, Shengcong Chen, Wei Chen, Jefferson W. Chen, Zhaolin Cheng, Kun Choudhury, Ahana Roy Chylla, Roger Clrigues, Albert Colleman, Steven Colmeiro, Ramiro German Rodriguez Combalia, Marc Costa, Anthony Cui, Xiaomeng Dai, Zhenzhen Dai, Lutao Daza, Laura Alexandra Deutsch, Eric Ding, Changxing Dong, Chao Dong, Shidu Dudzik, Wojciech Eaton-Rosen, Zach Egan, Gary Escudero, Guilherme Estienne, Tho Everson, Richard Fabrizio, Jonathan Fan, Yong Fang, Longwei Feng, Xue Ferrante, Enzo Fidon, Lucas Fischer, Martin French, Andrew P. Fridman, Naomi Fu, Huan Fuentes, David Gao, Yaozong Gates, Evan Gering, David Gholami, Amir Gierke, Willi Glocker, Ben Gong, Mingming Gonzlez-Vill, Sandra Grosges, T. Guan, Yuanfang Guo, Sheng Gupta, Sudeep Han, Woo-Sup Han, Il Song Harmuth, Ko Center for Biomedical Image Computing and Analytics University of Pennsylvania PhiladelphiaPA United States Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Institute for Surgical Technology and Biomechanics University of Bern Bern Switzerland Center for MR-Research University Children's Hospital Zurich Zurich Switzerland Support Centre for Advanced Neuroimaging Inselspital Institute for Diagnostic and Interventional Neuroradiology Bern University Hospital Bern Switzerland University Hospital of Zurich Zurich Switzerland Center for Clinical Epidemiology and Biostatistics University of Pennsylvania Philadelphia United States Image-Based Biomedical Modeling Group Technical University of Munich Munich Germany Icahn School of Medicine Mount Sinai Health System New YorkNY United States Leidos Biomedical Research Inc. Frederick National Laboratory for Cancer Research FrederickMD21701 United States Cancer Imaging Program National Cancer Institute National Institutes of Health BethesdaMD20814 United States Department of Neurology University of Alabama at Birmingham BirminghamAL United States Department of Diagnostic Radiology University of Texas MD Anderson Cancer Center HoustonTX United States Department of Psychology Washington University St. LouisMO United States Neuroimaging Informatics and Analysis Center Washington University St. LouisMO United States Department of Radiology Washington University St. LouisMO United States Institute of Diagnostic and Interventional Radiology Pediatric Radiology and Neuroradiology University Medical Center Rostock Ernst-Heydemann-Str. 6 Rostock18057 Germany Tata Memorial Centre Homi Bhabha National Institute Mumbai India Shri Guru Gobind Singhji Institute of Engineering and Technology Nanded India NVIDIA Santa Clara

Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumor is a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross total resection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Joint hierarchical category structure learning and large-scale image classification

arXiv

引用

arXiv 2017年

作者： Qu, Yanyun Lin, Li Shen, Fumin Lu, Chang Wu, Yang Xie, Yuan Tao, Dacheng Department of Computer Science Xiamen University Xiamen361005 China School of Computer Science and Engineering University of Electric Science and technology of China Chengdu611731 China Institute for Research Initiatives Nara Institute of Science and Technology Japan Research Center of Precision Sensing and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China Centre for Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia

—We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching for the best path over the entire tree. The proposed method is extensively evaluated on the ILSVRC2010 and Caltech 256 benchmark datasets. Experimental results show that our method obtains significantly better category hierarchies than other state-of-the-art visual tree-based methods and, therefore, much more accurate classification. Copyright © 2017, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Ultra-thin, High-efficiency Mid-Infrared Transmissive Huygens Meta-Optics

arXiv

引用

arXiv 2017年

作者： Zheng, Hanyu Ding, Jun Zhang, Li An, Sensong Lin, Hongtao Zheng, Bowen Du, Qingyang Yin, Gufan Michon, Jerome Zhang, Yifei Fang, Zhuoran Deng, Longjiang Gu, Tian Zhang, Hualiang Hu, Juejun State Key Laboratory of Electronic Thin Films and Integrated Devices National Engineering Research Center of Electromagnetic Radiation Control Materials University of Electronic Science and Technology of China ChengduSichuan China Department of Materials Science & Engineering Massachusetts Institute of Technology CambridgeMA United States Department of Electrical & Computer Engineering University of Massachusetts Lowell LowellMA United States

The mid-infrared (mid-IR) is a strategically important band for numerous applications ranging from night vision to biochemical sensing. Unlike visible or near-infrared optical parts which are commonplace and economically available off-the-shelf, mid-IR optics often requires exotic materials or complicated processing, which accounts for their high cost and inferior quality compared to their visible or near-infrared counterparts. Here we theoretically analyzed and experimentally realized a Huygens metasurface platform capable of fulfilling a diverse cross-section of optical functions in the mid-IR. The meta-optical elements were constructed using high-index chalcogenide films deposited on fluoride substrates: the choices of wide-band transparent materials allow the design to be scaled across a broad infrared spectrum. Capitalizing on a novel two-component Huygens’ meta-atom design, the meta-optical devices feature an ultra-thin profile (λ0/8 in thickness, where λ is the free-space wavelength) and measured optical efficiencies up to 75% in transmissive mode, both of which represent major improvements over state-of-the-art. We have also demonstrated, for the first time, mid-IR transmissive meta-lenses with diffraction-limited focusing and imaging performance. The projected size, weight and power advantages, coupled with the manufacturing scalability leveraging standard microfabrication technologies, make the Huygens meta-optical devices promising for next-generation mid-IR system applications. Copyright © 2017, The Authors. All rights reserved.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Satellite-relayed intercontinental quantum network

arXiv

引用

arXiv 2018年

作者： Liao, Sheng-Kai Cai, Wen-Qi Handsteiner, Johannes Liu, Bo Yin, Juan Zhang, Liang Rauch, Dominik Fink, Matthias Ren, Ji-Gang Liu, Wei-Yue Li, Yang Shen, Qi Cao, Yuan Li, Feng-Zhi Wang, Jian-Feng Huang, Yong-Mei Deng, Lei Xi, Tao Ma, Lu Hu, Tai Li, Li Liu, Nai-Le Koidl, Franz Wang, Peiyuan Chen, Yu-Ao Wang, Xiang-Bin Steindorfer, Michael Kirchner, Georg Lu, Chao-Yang Shu, Rong Ursin, Rupert Scheidl, Thomas Peng, Cheng-Zhi Wang, Jian-Yu Zeilinger, Anton Pan, Jian-Wei Hefei National Laboratory for Physical Sciences at the Microscale and Department of Modern Physics University of Science and Technology of China Hefei230026 China Center for Excellence Synergetic Innovation Center in Quantum Information and Quantum Physics University of Science and Technology of China Shanghai201315 China Vienna Center for Quantum Science and Technology Faculty of Physics University of Vienna Vienna1090 Austria Institute for Quantum Optics and Quantum Information Austrian Academy of Sciences Vienna1090 Austria School of Computer National University of Defense Technology Changsha410073 China Key Laboratory of Space Active Opto-Electronic Technology Shanghai Institute of Technical Physics Chinese Academy of Sciences Shanghai200083 China National Astronomical Observatories Chinese Academy of Sciences Beijing100012 China Key Laboratory of Optical Engineering Institute of Optics and Electronics Chinese Academy of Sciences Chengdu610209 Shanghai Engineering Center for Microsatellites Shanghai201203 China State Key Laboratory of Astronautic Dynamics Xi'an Satellite Control Center Xi’an710061 China Xinjiang Astronomical Observatory Chinese Academy of Sciences Urumqi830011 China National Space Science Center Chinese Academy of Sciences Beijing100080 China Space Research Institute Austrian Academy of Sciences Graz8042 Austria

We perform decoy-state quantum key distribution between a low-Earth-orbit satellite and multiple ground stations located in Xinglong, Nanshan, and Graz, which establish satellite-to-ground secure keys with ~kHz rate per passage of the satellite Micius over a ground station. The satellite thus establishes a secure key between itself and, say, Xinglong, and another key between itself and, say, Graz. Then, upon request from the ground command, Micius acts as a trusted relay. It performs bitwise exclusive OR operations between the two keys and relays the result to one of the ground stations. That way, a secret key is created between China and Europe at locations separated by 7600 km on Earth. These keys are then used for intercontinental quantum-secured communication. This was on the one hand the transmission of images in a one-time pad configuration from China to Austria as well as from Austria to China. Also, a videoconference was performed between the Austrian Academy of sciences and the Chinese Academy of sciences, which also included a 280 km optical ground connection between Xinglong and Beijing. Our work points towards an efficient solution for an ultra-long-distance global quantum network, laying the groundwork for a future quantum internet. Copyright © 2018, The Authors. All rights reserved.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Event-triggered communication and control of networked systems for multi-agent consensus

arXiv

引用

arXiv 2017年

作者： Nowzari, Cameron Garcia, Eloy Cortés, Jorge Department of Electrical and Computer Engineering George Mason University FairfaxVA22030 United States Control Science Center of Excellence Air Force Research Laboratory Wright-Patterson AFBOH45433 United States Department of Mechanical and Aerospace Engineering University of California San DiegoCA92093 United States

This article provides an introduction to event-triggered coordination for multi-agent average consensus. We provide a comprehensive account of the motivations behind the use of event-triggered strategies for consensus, the methods for algorithm synthesis, the technical challenges involved in establishing desirable properties of the resulting implementations, and their applications in distributed control. We pay special attention to the assumptions on the capabilities of the network agents and the resulting features of the algorithm execution, including the interconnection topology, the evaluation of triggers, and the role of imperfect information. The issues raised in our discussion transcend the specific consensus problem and are indeed characteristic of cooperative algorithms for networked systems that solve other coordination tasks. As our discussion progresses, we make these connections clear, highlighting general challenges and tools to address them widespread in the event-triggered control of networked systems. Copyright © 2017, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Driving fatigue prediction with pre-event electroencephalography (EEG) via a recurrent fuzzy neural network

Driving fatigue prediction with pre-event electroencephalogr...

引用

2016 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2016

作者： Liu, Yu-Ting Wu, Shang-Lin Chou, Kuang-Pen Lin, Yang-Yin Lu, Jie Zhang, Guangquan Lin, Wen-Chieh Lin, Chin-Teng Institute of Electrical Control Engineering Taiwan Brain Research Center Taiwan Institute of Computer Science and Engineering Taiwan Department of Computer Science National Chiao-Tung University Hsinchu Taiwan Taoyuan Taiwan Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

ISBN: (纸本)9781509006250

We propose an electroencephalography (EEG) prediction system based on a recurrent fuzzy neural network (RFNN) architecture to assess drivers' fatigue degrees during a virtual-reality (VR) dynamic driving environment. Prediction of fatigue degrees is a crucial and arduous biomedical issue for driving safety, which has attracted growing attention of the research community in the recent past. Meanwhile, combined with the benefits of measuring EEG signals facilitates, many EEG-based brain-computer interfaces (BCIs) have been developed for use in real-Time mental assessment. In the literature, EEG signals are severely blended with stochastic noise;therefore, the performance of BCIs is constrained by low resolution in recognition tasks. For this rationale, independent component analysis (ICA) is usually used to find a source mapping from original data that has been blended with unrelated artificial noise. However, the mechanism of ICA cannot be used in real-Time BCI design. To overcome this bottleneck, the proposed system in this paper utilizes a recurrent self-evolving fuzzy neural work (RSEFNN) to increase memory capability for adaptive noise cancellation when assessing drivers' mental states during a car driving task. The experimental results without the use of ICA procedure indicate that the proposed RSEFNN model remains superior performance compared with the state-of-Thearts models. © 2016 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Distributed kalman filter in a network of linear dynamical systems

arXiv

引用

arXiv 2017年

作者： Marelli, Damián Zamani, Mohsen Fu, Minyue Department of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University 388 Yuhangtang Road Hangzhou Zhejiang Province310058 French-Argentinean International Center for Information and Systems Sciences National Scientific and Technical Research Council Ocampo Esmeralda Rosario2000 Argentina School of Electrical Engineering and Computer Science University of Newcastle University Drive CallaghanNSW2308 Australia

This paper is concerned with the problem of distributed Kalman filtering in a network of interconnected subsystems with distributed control protocols. We consider networks, which can be either homogeneous or heterogeneous, of linear time-invariant subsystems, given in the state-space form. We propose a distributed Kalman filtering scheme for this setup. The proposed method provides, at each node, an estimation of the state parameter, only based on locally available measurements and those from the neighbor nodes. The special feature of this method is that it exploits the particular structure of the considered network to obtain an estimate using only one prediction/update step at each time step. We show that the estimate produced by the proposed method asymptotically approaches that of the centralized Kalman filter, i.e., the optimal one with global knowledge of all network parameters, and we are able to bound the convergence rate. Moreover, if the initial states of all subsystems are mutually uncorrelated, the estimates of these two schemes are identical at each time step. Copyright © 2017, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Non-linear feature extraction from HRV signal for mortality prediction of ICU cardiovascular patient

引用

Journal of Medical engineering and Technology 2016年第3期40卷 87-98页

作者： Moridani, Mohammad Karimi Setarehdan, Seyed Kamaledin Motie Nasrabadi, Ali Hajinasrollah, Esmaeil Department of Biomedical Engineering Science and Research Branch Islamic Azad University Tehran Iran Control and Intelligent Processing Centre of Excellence School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Departments of Biomedical Engineering Shahed University Tehran Iran Loghman Medical Center Shahid Beheshti University of Medical Sciences Tehran Iran

Intensive care unit (ICU) patients are at risk of in-ICU morbidities and mortality, making specific systems for identifying at-risk patients a necessity for improving clinical care. This study presents a new method for predicting in-hospital mortality using heart rate variability (HRV) collected from the times of a patients ICU stay. In this paper, a HRV time series processing based method is proposed for mortality prediction of ICU cardiovascular patients. HRV signals were obtained measuring R-R time intervals. A novel method, named return map, is then developed that reveals useful information from the HRV time series. This study also proposed several features that can be extracted from the return map, including the angle between two vectors, the area of triangles formed by successive points, shortest distance to 45° line and their various combinations. Finally, a thresholding technique is proposed to extract the risk period and to predict mortality. The data used to evaluate the proposed algorithm obtained from 80 cardiovascular ICU patients, from the first 48 h of the first ICU stay of 40 males and 40 females. This study showed that the angle feature has on average a sensitivity of 87.5% (with 12 false alarms), the area feature has on average a sensitivity of 89.58% (with 10 false alarms), the shortest distance feature has on average a sensitivity of 85.42% (with 14 false alarms) and, finally, the combined feature has on average a sensitivity of 92.71% (with seven false alarms). The results showed that the last half an hour before the patients death is very informative for diagnosing the patients condition and to save his/her life. These results confirm that it is possible to predict mortality based on the features introduced in this paper, relying on the variations of the HRV dynamic characteristics. © 2016 Taylor & Francis.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning policies for Markov decision processes from data

arXiv

引用

arXiv 2017年

作者： Hanawal, Manjesh K. Liu, Hao Zhu, Henghui Paschalidis, Ioannis Ch. Industrial Engineering and Operations Research IIT-Bombay PowaiMH 400076 India Center for Information and Systems Engineering Boston University BostonMA02215 United States College of Control Science and Engineering Zhejiang University Hangzhou Zhejiang310027 China Department of Electrical and Computer Engineering Division of Systems Engineering Boston University BostonMA02215 United States

We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are known a priori, however, only an unknown subset of them could be relevant. The policy parameters that correspond to an observed target policy are recovered using `1-regularized logistic regression that best fits the observed state-action samples. We establish bounds on the difference between the average reward of the estimated and the original policy (regret) in terms of the generalization error and the ergodic coefficient of the underlying Markov chain. To that end, we combine sample complexity theory and sensitivity analysis of the stationary distribution of Markov chains. Our analysis suggests that to achieve regret within order O(√Ε), it suffices to use training sample size on the order of Ω(log n · poly(1/Ε)), where n is the number of the features. We demonstrate the effectiveness of our method on a synthetic robot navigation example.90C40 (Primary) 90C39, 93E35, 60J10 (Secondary) Copyright © 2017, The Authors. All rights reserved.

关键词： Markov processes

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：