检索结果-内蒙古大学图书馆

IFIP/ieee International symposium on Integrated Network Management (IM)

作者： Orsini, Gabriel Bade, Dirk Lamersdorf, Winfried Univ Hamburg Dept Comp Sci Distributed Syst Grp Hamburg Germany

ISBN: (纸本)9783901882760

The widespread use of mobile devices such as smartphones and tablets is flanked by an ever increasing supply of mobile applications. Along with this trend, expectations and requirements of users rise as well. For example, users do not want to compromise on comfortable daily routines as available on desktop computers. However, an intrinsic characteristic of mobile devices is their limited availability of resources (e.g., CPU, storage, bandwidth, energy) hindering in particular computation-intensive tasks. In this scenario, mobile cloud computing (MCC) promises to overcome these limitations by offering apparently infinite resources in the infrastructure that are transparently accessible also for mobile applications. In order to easily benefit from these offerings, dynamic code offloading has been proposed by several approaches recently. However, such solutions either do not consider the complexity arising from the dynamically changing context in mobile environments adequately or have a steep learning curve inhibiting easy adoption by developers. Therefore, this paper presents a novel approach towards context-adaptive mobile cloud computing. For that, first an extensive requirements analysis was conducted merging ISO standards with users', applications' and developers' needs. Based on this, an evaluation of related MCC-approaches allowed identifying promising concepts as well as current shortcomings. As a result, an MCC-framework, called CloudAware, is proposed that eases the development of MCC-applications by offering programming abstractions, multi-level distribution transparency, context adaptation features and is hands-free for end-users.

关键词： Cloud Computing Mobile Applications Mobile devices User needs desktop computers hands-free Requirements analysis ISO standard Mobile Smartphone End users learning Curve Consumers DEVELOPERS Developers

来源：评论

学校读者我要写书评

暂无评论

Infinite Horizon Self-learning Optimal Control of Nonaffine Discrete-Time Nonlinear Systems

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2015年第4期26卷 866-879页

作者： Wei, Qinglai Liu, Derong Yang, Xiong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, a novel iterative adaptive dynamic programming (ADP)-based infinite horizon self-learning optimal control algorithm, called generalized policy iteration algorithm, is developed for nonaffine discrete-time (DT) nonlinear systems. Generalized policy iteration algorithm is a general idea of interacting policy and value iteration algorithms of ADP. The developed generalized policy iteration algorithm permits an arbitrary positive semidefinite function to initialize the algorithm, where two iteration indices are used for policy improvement and policy evaluation, respectively. It is the first time that the convergence, admissibility, and optimality properties of the generalized policy iteration algorithm for DT nonlinear systems are analyzed. Neural networks are used to implement the developed algorithm. Finally, numerical examples are presented to illustrate the performance of the developed algorithm.

关键词： adaptive critic designs adaptive dynamic programming (ADP) approximate dynamic programming generalized policy iteration neural networks (NNs) neurodynamic programming nonlinear systems optimal control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

2009 ieee symposium on adaptive dynamic programming and reinforcement learning, ADPRL 2009 - Proceedings

2009 IEEE Symposium on Adaptive Dynamic Programming and Rein...

引用

2009 ieee symposium on adaptive dynamic programming and reinforcement learning, ADPRL 2009

ISBN: (纸本)9781424427611

The proceedings contain 34 papers. The topics discussed include: a unified framework for temporal difference methods;efficient data reuse in value function approximation;constrained optimal control of affine nonlinear discrete-time systems using GHJB method;algorithm and stability of ATC receding horizon control;online policy iteration based algorithms to solve the continuous-time infinite horizon optimal control problem;real-time motor control using recurrent neural networks;hierarchical optimal control of a 7-DOF Arm model;coupling perception and action using minimax optimal control;a convergent recursive least squares policy iteration algorithm for multi-dimensional Markov Decision Process with continuous state and action spaces;basis function adaptation methods for cost approximation in MDP;and executing concurrent actions with multiple Markov Decision Processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Data-based Online reinforcement learning Algorithm with High-efficient Exploration

A Data-based Online Reinforcement Learning Algorithm with Hi...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Zhu, Yuanheng Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China

ISBN: (纸本)9781479945528

An online reinforcement learning algorithm is proposed in this paper to directly utilizes online data efficiently for continuous deterministic systems without system parameters. The dependence on some specific approximation structures is crucial to limit the wide application of online reinforcement learning algorithms. We utilize the online data directly with the kd-tree technique to remove this limitation. Moreover, we design the algorithm in the Probably Approximately Correct principle. Two examples are simulated to verify its good performance.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

adaptive dynamic programming-based optimal tracking control for nonlinear systems using general value iteration

Adaptive dynamic programming-based optimal tracking control ...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Lin, Xiaofeng Ding, Qiang Kong, Weikai Song, Chunning Huang, Qingbao Guangxi Univ Sch Elect Engn Nanning Peoples R China

ISBN: (纸本)9781479945528

For the optimal tracking control problem of affine nonlinear systems, a general value iteration algorithm based on adaptive dynamic programming is proposed in this paper. By system transformation, the optimal tracking problem is converted into the optimal regulating problem for the tracking error dynamics. Then, general value iteration algorithm is developed to obtain the optimal control with convergence analysis. Considering the advantages of echo state network, we use three echo state networks with levenberg-Marquardt (LM) adjusting algorithm to approximate the system, the cost function and the control law. A simulation example is given to demonstrate the effectiveness of the presented scheme.

关键词： adaptive dynamic programming value iteration tracking control echo state network

来源：评论

学校读者我要写书评

暂无评论

Model-Based Multi-Objective reinforcement learning

Model-Based Multi-Objective Reinforcement Learning

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Wiering, Marco A. Withagen, Maikel Drugan, Madalina M. Univ Groningen Inst Artificial Intelligence NL-9700 AB Groningen Netherlands Vrije Univ Brussel Artificial Intelligence Lab Ixelles Brunei

ISBN: (纸本)9781479945528

This paper describes a novel multi-objective reinforcement learning algorithm. The proposed algorithm first learns a model of the multi-objective sequential decision making problem, after which this learned model is used by a multi-objective dynamic programming method to compute Pareto optimal policies. The advantage of this model-based multi-objective reinforcement learning method is that once an accurate model has been estimated from the experiences of an agent in some environment, the dynamic programming method will compute all Pareto optimal policies. Therefore it is important that the agent explores the environment in an intelligent way by using a good exploration strategy. In this paper we have supplied the agent with two different exploration strategies and compare their effectiveness in estimating accurate models within a reasonable amount of time. The experimental results show that our method with the best exploration strategy is able to quickly learn all Pareto optimal policies for the Deep Sea Treasure problem.

关键词： Pareto optimisation decision making dynamic programming learning (artificial intelligence) Pareto optimal policies deep sea treasure problem model-based multiobjective reinforcement learning multiobjective dynamic programming method multiobjective sequential decision making problem Computational modeling dynamic programming Heuristic algorithms learning (artificial intelligence) Markov processes Pareto optimization Vectors Pareto optimisation dynamic programming exploration strategy Heuristic algorithms learning (artificial intelligence) Computational modeling Markov chain Agents optimal strategy decision making

来源：评论

学校读者我要写书评

暂无评论

An adaptive dynamic programming Algorithm to Solve Optimal Control of Uncertain Nonlinear Systems

An Adaptive Dynamic Programming Algorithm to Solve Optimal C...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Cui, Xiaohong Luo, Yanhong Zhang, Huaguang Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Liaoning Peoples R China

ISBN: (纸本)9781479945528

In this paper, an approximate optimal control method based on adaptive dynamic programming(ADP) is discussed for completely unknown nonlinear system. An online critic-action-identifier algorithm is developed using neural network systems, where the critic -action networks approximate the optimal value function and optimal control and the other two neural networks approximates the unknown system. Furthermore the adaptive tuning laws are given based on Lyapunov approach, which ensures the uniform ultimate bounded stability of the closed-loop system. Finally, the effectiveness is demonstrated by a simulation example.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

adaptive dynamic programming for Discrete-time LQR Optimal Tracking Control Problems with Unknown dynamics

Adaptive Dynamic Programming for Discrete-time LQR Optimal T...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Liu, Yang Luo, Yanhong Zhang, Huaguang Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Liaoning Peoples R China

ISBN: (纸本)9781479945528

In this paper, an optimal tracking control approach based on adaptive dynamic programming (ADP) algorithm is proposed to solve the linear quadratic regulation (LQR) problems for unknown discrete-time systems in an online fashion. First, we convert the optimal tracking problem into designing infinite-horizon optimal regulator for the tracking error dynamics based on the system transformation. Then we expand the error state equation by the history data of control and state. The iterative ADP algorithm of policy iteration (PI) and value iteration (VI) are introduced to solve the value function of the controlled system. It is shown that the proposed ADP algorithm solves the LQR without requiring any knowledge of the system dynamics. The simulation results show the convergence and effectiveness of the proposed control scheme.

关键词： Digital control systems

来源：评论

学校读者我要写书评

暂无评论

Convergent reinforcement learning Control with Neural Networks and Continuous Action Search

Convergent Reinforcement Learning Control with Neural Networ...

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Lee, Minwoo Anderson, Charles W. Colorado State Univ Dept Comp Sci Ft Collins CO 80523 USA

ISBN: (纸本)9781479945528

We combine a convergent TD-learning method and direct continuous action search with neural networks for function approximation to obtain both stability and generalization over inexperienced state-action pairs. We extend linear Greedy-GQ to nonlinear neural networks for convergent learning. Direct continuous action search with back-propagation leads to efficient high-precision control. A high dimensional continuous state and action problem, octopus arm control, is examined to test the proposed algorithm. Comparing TD, linear Greedy-GQ, and nonlinear Greedy-GQ, we discuss how the correction term contributes to learning with nonlinear Greedy-GQ algorithm and how continuous action search contributes to learning speed and stability.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On-policy Q-learning for adaptive Optimal Control

On-policy Q-learning for Adaptive Optimal Control

引用

ieee symposium on adaptive dynamic programming and reinforcement learning (ADPRL)

作者： Jha, Sumit Kumar Bhasin, Shubhendu Indian Inst Technol Dept Elect Engn New Delhi 110016 India

ISBN: (纸本)9781479945528

This paper presents a novel on-policy Q-learning approach for finding the optimal control policy online for continuous-time linear time invariant (LTI) systems with completely unknown dynamics. The proposed result estimates the unknown parameters of the optimal control policy based on the fixed point equation involving the Q-function. The gradient-based update laws, based on the minimization of the Bellman's error, are used to achieve online adaptation of parameters with the use of persistence of excitation condition. A novel asymptotically convergent state derivative estimator is presented to ensure that the proposed result is independent of knowledge of system dynamics. Simulation results are presented to validate the theoretical development.

关键词： Q-learning adaptive optimal control on-policy method

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：